Compare commits
840
Commits
4a3ebc6b5b
...
main
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
ff01a6b14f | ||
|
|
fe8f2140ee | ||
|
|
e80b6c642f | ||
|
|
371745ebd6 | ||
|
|
072c0886d5 | ||
|
|
6b24947628 | ||
|
|
494663940b | ||
|
|
3c13653738 | ||
|
|
953fa442fa | ||
|
|
3f1b04e045 | ||
|
|
2365177ddd | ||
|
|
1b2a666391 | ||
|
|
83c9a547bf | ||
|
|
b510857d37 | ||
|
|
7c9042c05a | ||
|
|
da9134bc89 | ||
|
|
b2456c622b | ||
|
|
03ee2e134d | ||
|
|
9c778e9ff8 | ||
|
|
7879f3687b | ||
|
|
255f14599e | ||
|
|
03e8300d2c | ||
|
|
5c1c903501 | ||
|
|
bafb263664 | ||
|
|
0c5dd18e7a | ||
|
|
763e3f7c91 | ||
|
|
e744eacf68 | ||
|
|
c0b6f74bee | ||
|
|
c61a1e73c6 | ||
|
|
237d99b4af | ||
|
|
2d8efee9a7 | ||
|
|
21e09ea959 | ||
|
|
837e87e1c5 | ||
|
|
4e964b2623 | ||
|
|
ec8b20fbf0 | ||
|
|
2b85d9cb65 | ||
|
|
026f6ab268 | ||
|
|
b515648641 | ||
|
|
f98ae6a9fd | ||
|
|
2067297b2f | ||
|
|
3bf25c5097 | ||
|
|
e56b1603af | ||
|
|
eb8de8d1a1 | ||
|
|
b05ede5616 | ||
|
|
61bb590877 | ||
|
|
c3de0b37e2 | ||
|
|
08a65e287e | ||
|
|
ad2688ab30 | ||
|
|
5be4266f5c | ||
|
|
90d6d871d6 | ||
|
|
d74f4180cd | ||
|
|
39983a5e7a | ||
|
|
41b8c15809 | ||
|
|
a0e7137c4b | ||
|
|
7b6310c109 | ||
|
|
556ac15eb9 | ||
|
|
dcd07967ca | ||
|
|
ce49c47cbb | ||
|
|
ce8853d27a | ||
|
|
71c20f73f2 | ||
|
|
b3a7e2ff6e | ||
|
|
6b6a6c5c98 | ||
|
|
f8112704d5 | ||
|
|
f019e3e105 | ||
|
|
783380af39 | ||
|
|
be25977532 | ||
|
|
523d74e2ac | ||
|
|
a94c315711 | ||
|
|
b544587408 | ||
|
|
2268d83bd9 | ||
|
|
28e92eeff2 | ||
|
|
b088eba944 | ||
|
|
596e530675 | ||
|
|
153a17166e | ||
|
|
9731f30a03 | ||
|
|
68ebea789a | ||
|
|
cc2e4fecf2 | ||
|
|
9eb7fb9157 | ||
|
|
663e535640 | ||
|
|
5bf3d9f665 | ||
|
|
307c5844ad | ||
|
|
3dc6def360 | ||
|
|
e7a5bdb454 | ||
|
|
ae8f41238c | ||
|
|
cffc0cfa31 | ||
|
|
706791d516 | ||
|
|
76081b9ee4 | ||
|
|
1a5b187066 | ||
|
|
8e25bbca19 | ||
|
|
8a6c0449b3 | ||
|
|
de7eeaa87b | ||
|
|
64175d3827 | ||
|
|
4ab99ff136 | ||
|
|
024c5188bf | ||
|
|
9a16d43ef0 | ||
|
|
07f3857fb9 | ||
|
|
fa75d3456d | ||
|
|
074c83a09a | ||
|
|
e365792997 | ||
|
|
49cb2bbf71 | ||
|
|
4ac1f8d2ac | ||
|
|
92dc3dd393 | ||
|
|
b466fbacd2 | ||
|
|
642c18d64c | ||
|
|
3ddc6702a8 | ||
|
|
05ad0a8ace | ||
|
|
dd9e07a25f | ||
|
|
fb3fec970e | ||
|
|
29345f42a6 | ||
|
|
a956a8126e | ||
|
|
bee95149e2 | ||
|
|
8f93c64866 | ||
|
|
a8be1500ba | ||
|
|
ef38e8d006 | ||
|
|
af28c171f5 | ||
|
|
19b0efce30 | ||
|
|
4a89316efa | ||
|
|
3f1e57225a | ||
|
|
de7d70676d | ||
|
|
784d1fff0c | ||
|
|
d92a4f25f2 | ||
|
|
e711723352 | ||
|
|
9b99ccb56b | ||
|
|
9edcc7fa7e | ||
|
|
0c25849292 | ||
|
|
f8460ef236 | ||
|
|
33212db2c2 | ||
|
|
c414bf0295 | ||
|
|
54d9b1cb48 | ||
|
|
ee8c47961b | ||
|
|
21f4b6dc84 | ||
|
|
16532876e7 | ||
|
|
d12ea8e309 | ||
|
|
d486219fc2 | ||
|
|
49f944be3e | ||
|
|
105605b8e9 | ||
|
|
82b9ccaa79 | ||
|
|
4d58fa254a | ||
|
|
4d9a8d6a41 | ||
|
|
47fd76e4ce | ||
|
|
4f49b55c1f | ||
|
|
7cd7982dfd | ||
|
|
338dab077c | ||
|
|
957d512e96 | ||
|
|
a9e90b9d1d | ||
|
|
d6f0b7a416 | ||
|
|
ed3050add4 | ||
|
|
c825e1d235 | ||
|
|
a97d19d792 | ||
|
|
3dcfaeb4e8 | ||
|
|
011fa68ca9 | ||
|
|
d12d5460a5 | ||
|
|
24f632ca7e | ||
|
|
69425846f8 | ||
|
|
b7b20b1b8f | ||
|
|
71536bd5f8 | ||
|
|
0951fc183c | ||
|
|
1463501553 | ||
|
|
766c837bd5 | ||
|
|
9cede34a67 | ||
|
|
252be28c18 | ||
|
|
c6b772cf6b | ||
|
|
e8e1e96196 | ||
|
|
8b27d27402 | ||
|
|
81e42c9987 | ||
|
|
365aaa77bd | ||
|
|
e10c10a644 | ||
|
|
6fe7401fac | ||
|
|
716c5225ae | ||
|
|
7020600b1d | ||
|
|
80dd705c1d | ||
|
|
427915bed2 | ||
|
|
7f730b4cea | ||
|
|
0f0bc4dbb1 | ||
|
|
b965ee564d | ||
|
|
1c4c319792 | ||
|
|
48f17b77bb | ||
|
|
fc8e08a2a6 | ||
|
|
8fa5ae844a | ||
|
|
91ed2859c7 | ||
|
|
85c94c1706 | ||
|
|
8f111b22ee | ||
|
|
32feecd91f | ||
|
|
ab593678b5 | ||
|
|
a9fe30e9f6 | ||
|
|
c5f8adc0b1 | ||
|
|
c54dca96bd | ||
|
|
5341b5ba7d | ||
|
|
6605802904 | ||
|
|
a400804ce4 | ||
|
|
3f1bcfd82b | ||
|
|
81e1c3f183 | ||
|
|
96b5b0ee4b | ||
|
|
ff5a91a456 | ||
|
|
833665cded | ||
|
|
10d2c6083d | ||
|
|
f46021a7fa | ||
|
|
5d5c3d7c43 | ||
|
|
429a3da665 | ||
|
|
de2b869ee9 | ||
|
|
2abd479aee | ||
|
|
e57bb4ace7 | ||
|
|
bfdbfa1632 | ||
|
|
8530aed2b7 | ||
|
|
273a04964e | ||
|
|
7840bede98 | ||
|
|
4b61f300c0 | ||
|
|
a4d553a46a | ||
|
|
9a648b4649 | ||
|
|
4c5ea86f53 | ||
|
|
984c242ede | ||
|
|
fe98d90a9d | ||
|
|
2e8a5930f6 | ||
|
|
7c3f7e5500 | ||
|
|
2622ee21aa | ||
|
|
e73fa00981 | ||
|
|
ded7ae35e5 | ||
|
|
388a610dfb | ||
|
|
4975fda882 | ||
|
|
9b5c6707a3 | ||
|
|
222e00fc44 | ||
|
|
e96c822660 | ||
|
|
21e207efa1 | ||
|
|
06265beb25 | ||
|
|
857ddac4e5 | ||
|
|
c1407a7e86 | ||
|
|
ae94e9c9e8 | ||
|
|
3f729dafcc | ||
|
|
e534024e49 | ||
|
|
d1d8e6c096 | ||
|
|
0b6d07cbe2 | ||
|
|
d3f6b2a7b3 | ||
|
|
47232f3c7f | ||
|
|
52a8cc5316 | ||
|
|
9d3dfa2886 | ||
|
|
2c74fd1873 | ||
|
|
89cab55086 | ||
|
|
3895a8babe | ||
|
|
e2e3e2b834 | ||
|
|
3e851a7803 | ||
|
|
355553ac22 | ||
|
|
13dbf96093 | ||
|
|
eaf25f675a | ||
|
|
9e2b579aab | ||
|
|
e2aabc8b15 | ||
|
|
5d88c034f6 | ||
|
|
bf6c80c7e8 | ||
|
|
efad400092 | ||
|
|
02653fa22c | ||
|
|
b4b7eca0ef | ||
|
|
7115b70c01 | ||
|
|
2d09fdcdc2 | ||
|
|
3723a1ea96 | ||
|
|
2631afd3fe | ||
|
|
a68dbbad05 | ||
|
|
775fefa804 | ||
|
|
3a5a6b11a3 | ||
|
|
d39c2fb05a | ||
|
|
23fbc2ec2f | ||
|
|
81503550f3 | ||
|
|
c67c69e657 | ||
|
|
6ecb39eaa7 | ||
|
|
19aba3e4d5 | ||
|
|
f9b65c30c7 | ||
|
|
3f466c852c | ||
|
|
8a8e2baa02 | ||
|
|
be4ce2e505 | ||
|
|
937d6c19df | ||
|
|
d36158f919 | ||
|
|
bb1438a93f | ||
|
|
467b024f21 | ||
|
|
aa0c433a3e | ||
|
|
c9bfa574ce | ||
|
|
e1726d9142 | ||
|
|
4dc5add6ea | ||
|
|
ec8a372566 | ||
|
|
30e79c3a76 | ||
|
|
ec317a4618 | ||
|
|
badfcdbf91 | ||
|
|
a2fb482732 | ||
|
|
77154ca611 | ||
|
|
02d69c663a | ||
|
|
a78d050eff | ||
|
|
3ccc0a90b6 | ||
|
|
f4b8d43a68 | ||
|
|
2521446ac8 | ||
|
|
2308b6f00b | ||
|
|
a1f51a0226 | ||
|
|
449c05a0ca | ||
|
|
d5e62627a3 | ||
|
|
4e0681ed56 | ||
|
|
87e7dce3a7 | ||
|
|
f43d7e1a0f | ||
|
|
7a9d3db896 | ||
|
|
c923e7769b | ||
|
|
ad8d39cbab | ||
|
|
791f92135a | ||
|
|
6a03954b45 | ||
|
|
0da66a6e46 | ||
|
|
8082b62f32 | ||
|
|
96fc2da315 | ||
|
|
78b32b3fdc | ||
|
|
6463d04601 | ||
|
|
698e79f3bd | ||
|
|
e90158d912 | ||
|
|
292da21f9d | ||
|
|
c19c263ac8 | ||
|
|
67516b6c42 | ||
|
|
93d0bd9d50 | ||
|
|
a31054f5ef | ||
|
|
68fc395554 | ||
|
|
b33cb81237 | ||
|
|
2f18d13cf0 | ||
|
|
483e0c24c7 | ||
|
|
c068db0e1d | ||
|
|
3f550129e8 | ||
|
|
6d1daa9fe5 | ||
|
|
c5bda658d2 | ||
|
|
624a5ddafd | ||
|
|
e83222396f | ||
|
|
7fad7db330 | ||
|
|
6849ca696a | ||
|
|
ac71b17517 | ||
|
|
12b005eefa | ||
|
|
b9b401b2ef | ||
|
|
669f85e686 | ||
|
|
f395a6b1ad | ||
|
|
f5fefbffe5 | ||
|
|
61d9c777bf | ||
|
|
de8291e24f | ||
|
|
0fae39a014 | ||
|
|
31e90ac370 | ||
|
|
0838cd6593 | ||
|
|
7342dc0317 | ||
|
|
253e02b95e | ||
|
|
d9a543c500 | ||
|
|
818f70c295 | ||
|
|
cd7517fb17 | ||
|
|
e6e84f350c | ||
|
|
426f3bd36b | ||
|
|
54db759eea | ||
|
|
7173c64e2e | ||
|
|
877f6df889 | ||
|
|
c7a305ec10 | ||
|
|
206e45d470 | ||
|
|
656d0d4506 | ||
|
|
183625d4f9 | ||
|
|
6f11c220b5 | ||
|
|
24aa1191f4 | ||
|
|
ff305934f1 | ||
|
|
3ad096faf8 | ||
|
|
2cc2e68d1c | ||
|
|
bc3ddb198a | ||
|
|
4e4eab73ed | ||
|
|
e2ad0ce5f5 | ||
|
|
a6009ea85b | ||
|
|
86b1c2ef15 | ||
|
|
380638afbb | ||
|
|
0d2689e0df | ||
|
|
2ce8012fa0 | ||
|
|
f7ba007b5e | ||
|
|
b337523c11 | ||
|
|
5555a2d8f7 | ||
|
|
69d00bc264 | ||
|
|
28d679e762 | ||
|
|
657a2e9417 | ||
|
|
c5422f4c46 | ||
|
|
df6c7ad031 | ||
|
|
c077dc663d | ||
|
|
69d2b6f82d | ||
|
|
cc2a6eea1a | ||
|
|
f47792af7f | ||
|
|
c6566bb9f6 | ||
|
|
98f7211162 | ||
|
|
189bbfb9f4 | ||
|
|
1484266938 | ||
|
|
1bc6e072b0 | ||
|
|
802feb6770 | ||
|
|
44f0ddfd7b | ||
|
|
69d54eb078 | ||
|
|
fe341a53dd | ||
|
|
deedc7be00 | ||
|
|
654b725ea9 | ||
|
|
abad32a718 | ||
|
|
fabaecbfa5 | ||
|
|
7039c7f17b | ||
|
|
1bdd3fa2d5 | ||
|
|
08582942d8 | ||
|
|
d0948f754d | ||
|
|
d6aca837c3 | ||
|
|
56e3b081ae | ||
|
|
8055293353 | ||
|
|
c9e62f13c2 | ||
|
|
e1a5086256 | ||
|
|
5b0b8f251e | ||
|
|
a7b7bc1fbe | ||
|
|
45bb710eca | ||
|
|
12e6a585ae | ||
|
|
c599b5971f | ||
|
|
6e6e86078a | ||
|
|
fa39582756 | ||
|
|
d79b52b182 | ||
|
|
e0317b28ce | ||
|
|
50b21a2667 | ||
|
|
a686c8e1b7 | ||
|
|
ffec221276 | ||
|
|
f3cb10b690 | ||
|
|
716961cf1f | ||
|
|
a281ad32f0 | ||
|
|
b3ee560ae8 | ||
|
|
f022975964 | ||
|
|
4c36d21280 | ||
|
|
3facf822b7 | ||
|
|
092c35dd15 | ||
|
|
314ab8cffd | ||
|
|
ac28877f0e | ||
|
|
8c175f403a | ||
|
|
7900d2eabc | ||
|
|
c75cb63cd2 | ||
|
|
258b97ff6b | ||
|
|
aa1d44df16 | ||
|
|
8d7b93fec2 | ||
|
|
32b05addc1 | ||
|
|
f5cda48c90 | ||
|
|
3b9e462774 | ||
|
|
21445806bd | ||
|
|
ee8f7ea449 | ||
|
|
f7a3a7265f | ||
|
|
2534a96fcf | ||
|
|
5a09062632 | ||
|
|
0466bd36ea | ||
|
|
83773ecdf3 | ||
|
|
a33d46b471 | ||
|
|
e05201aa2e | ||
|
|
99b44c7a42 | ||
|
|
5bed289707 | ||
|
|
4163a80142 | ||
|
|
f4114e068e | ||
|
|
e3bbaf2369 | ||
|
|
36f3972812 | ||
|
|
6a70913590 | ||
|
|
74f4404f58 | ||
|
|
fe4df3df0e | ||
|
|
d4e92ccc37 | ||
|
|
bfa7e5b7af | ||
|
|
f147949be8 | ||
|
|
124b89d5b7 | ||
|
|
03091e28b8 | ||
|
|
cc9b0f097d | ||
|
|
3fe917abb1 | ||
|
|
f26d9f432c | ||
|
|
c059bee812 | ||
|
|
b99fdbe1f8 | ||
|
|
93d2cab35e | ||
|
|
239a3fa3a8 | ||
|
|
3e8e1364ff | ||
|
|
bd5bbce6e4 | ||
|
|
c85616efc6 | ||
|
|
f425a21208 | ||
|
|
2339bd39d6 | ||
|
|
1789f09588 | ||
|
|
fcae5c9887 | ||
|
|
26a488ad93 | ||
|
|
ef42b4385f | ||
|
|
61f084b5f3 | ||
|
|
2eb491e18b | ||
|
|
f8471164bf | ||
|
|
01abe975b5 | ||
|
|
b89852aad0 | ||
|
|
3c062d391d | ||
|
|
276fbcff27 | ||
|
|
187a0eb98a | ||
|
|
f2376cdc4d | ||
|
|
3709632ff2 | ||
|
|
838526c7e5 | ||
|
|
bf16c9c139 | ||
|
|
2bea22002d | ||
|
|
c41b2639e2 | ||
|
|
a98247ab4d | ||
|
|
c1692c85f1 | ||
|
|
699c892dd5 | ||
|
|
ff440c7805 | ||
|
|
a205fb3177 | ||
|
|
46fb84c2d4 | ||
|
|
fa5cfd48d5 | ||
|
|
7d0b4e57aa | ||
|
|
8ea646b827 | ||
|
|
364bc81a9e | ||
|
|
5ca26880ad | ||
|
|
acec1b1d84 | ||
|
|
d5f356dae0 | ||
|
|
9bd074a996 | ||
|
|
29e4d2d42e | ||
|
|
be0823357f | ||
|
|
f1a3c60558 | ||
|
|
2d69083c4a | ||
|
|
10cc2f6ae2 | ||
|
|
02aa10539f | ||
|
|
1dfe9fbdae | ||
|
|
193922d6ff | ||
|
|
3c802af3cf | ||
|
|
7d1d8660d6 | ||
|
|
9f1c783886 | ||
|
|
f8e6e365ae | ||
|
|
03a7d3776f | ||
|
|
04b02fc8a5 | ||
|
|
fa94ad4143 | ||
|
|
4c43254d52 | ||
|
|
783ac12071 | ||
|
|
ed7ae705a1 | ||
|
|
51144dd83e | ||
|
|
35e920d671 | ||
|
|
ffdde24f54 | ||
|
|
e0cb3efce0 | ||
|
|
02e55d2af3 | ||
|
|
3766a67a32 | ||
|
|
04462732a4 | ||
|
|
ad8a6065f4 | ||
|
|
1dc60dd367 | ||
|
|
a0f28d73a8 | ||
|
|
c811943137 | ||
|
|
5dc9bcd8cd | ||
|
|
ce4603cad6 | ||
|
|
9a585c62aa | ||
|
|
1a3a7a8f01 | ||
|
|
89ac8d971b | ||
|
|
b74233860d | ||
|
|
75e3b17c05 | ||
|
|
90ba2f34b5 | ||
|
|
970dc63478 | ||
|
|
a6b39f0262 | ||
|
|
fc39317392 | ||
|
|
3d52578e13 | ||
|
|
81c993658e | ||
|
|
9adba10f3f | ||
|
|
1ee69dde9c | ||
|
|
c17fadcfdc | ||
|
|
0cc0460870 | ||
|
|
196483e25b | ||
|
|
1c47ebfc57 | ||
|
|
d095e61c0b | ||
|
|
7368fadebd | ||
|
|
83ed0c7c09 | ||
|
|
28d76f3bad | ||
|
|
b027ac8312 | ||
|
|
5cadabfafd | ||
|
|
4e318ac563 | ||
|
|
efd141047d | ||
|
|
b8bd335754 | ||
|
|
59ffd73e85 | ||
|
|
2186b89a9a | ||
|
|
2c99ee9333 | ||
|
|
bc713cf8cc | ||
|
|
18c19eaf23 | ||
|
|
a6f43e57d6 | ||
|
|
bacbbe1878 | ||
|
|
560fae64cd | ||
|
|
8a03ccf7b3 | ||
|
|
f43e4c39e3 | ||
|
|
efaca9547d | ||
|
|
82e89e9944 | ||
|
|
19c0bed584 | ||
|
|
dd30786fef | ||
|
|
f0a5f111f2 | ||
|
|
ad73a4740d | ||
|
|
8cbd5d0300 | ||
|
|
88a419649e | ||
|
|
fa312090cb | ||
|
|
81d9c45e4b | ||
|
|
e31b823bf5 | ||
|
|
9824159d94 | ||
|
|
112a282915 | ||
|
|
51ef239768 | ||
|
|
a1cd0ec650 | ||
|
|
702ce313f4 | ||
|
|
295c062db8 | ||
|
|
4611c2c3d2 | ||
|
|
201e537d98 | ||
|
|
581692cc0f | ||
|
|
4274ae956c | ||
|
|
ab905a885d | ||
|
|
8d10c38b73 | ||
|
|
240785b82c | ||
|
|
2ddde19e8e | ||
|
|
c5c1161382 | ||
|
|
ae9adec905 | ||
|
|
72d59adc2c | ||
|
|
1afb029839 | ||
|
|
c23ca06b6d | ||
|
|
bab0ac61f8 | ||
|
|
e3a29aa9b3 | ||
|
|
fff10d2072 | ||
|
|
fc494822ea | ||
|
|
18751bc6a7 | ||
|
|
9bbc581560 | ||
|
|
56e6da2c47 | ||
|
|
c4a5ff5c18 | ||
|
|
2274e86842 | ||
|
|
30c7405890 | ||
|
|
d8fa463e2b | ||
|
|
1664c4f444 | ||
|
|
972195f4f5 | ||
|
|
705e124c05 | ||
|
|
242e4213fc | ||
|
|
8674a794c7 | ||
|
|
f4dde3132c | ||
|
|
9f3d70e081 | ||
|
|
e2414ec1db | ||
|
|
0fc0cefb4e | ||
|
|
e41d5d5543 | ||
|
|
0751f5272f | ||
|
|
194bd72be7 | ||
|
|
072d49bb6e | ||
|
|
fd928e5f3c | ||
|
|
994b8b77be | ||
|
|
d80ddaac73 | ||
|
|
d33872dfeb | ||
|
|
273e099693 | ||
|
|
2f7f05c256 | ||
|
|
daa9085143 | ||
|
|
4ed4c4433b | ||
|
|
194da61de1 | ||
|
|
458ba2edf8 | ||
|
|
73c742b09c | ||
|
|
b49c921a27 | ||
|
|
ba77c4c130 | ||
|
|
e161a0798c | ||
|
|
459764104d | ||
|
|
e73895a5df | ||
|
|
dfaabf91ac | ||
|
|
24be8c0bca | ||
|
|
e265b77982 | ||
|
|
7816afdb25 | ||
|
|
c4cd88d9fe | ||
|
|
21d9758459 | ||
|
|
0004536dd0 | ||
|
|
70bdce6133 | ||
|
|
7d47ac2ddb | ||
|
|
4cf1307e72 | ||
|
|
0f112d1800 | ||
|
|
29ae81fe83 | ||
|
|
fd0216d3b5 | ||
|
|
e58f8dde7f | ||
|
|
032d39e9b4 | ||
|
|
814301b268 | ||
|
|
ee406adf0c | ||
|
|
f226af0e11 | ||
|
|
fb2ac82458 | ||
|
|
95307ac6d4 | ||
|
|
816173ca9d | ||
|
|
81198e97ba | ||
|
|
4ac0179f8a | ||
|
|
775792f2d5 | ||
|
|
4187ade7b8 | ||
|
|
1fbbfa1657 | ||
|
|
5dd4a628dd | ||
|
|
8352b2427f | ||
|
|
87d9996abe | ||
|
|
3722645539 | ||
|
|
caff2b44cb | ||
|
|
a4b14e57b6 | ||
|
|
9dba339d07 | ||
|
|
8733a21d55 | ||
|
|
fdfc171a74 | ||
|
|
2dd887426e | ||
|
|
9e3e37cb3c | ||
|
|
1995c0fcd0 | ||
|
|
1283362e76 | ||
|
|
a58bdd0d4e | ||
|
|
8faac3dd2a | ||
|
|
ed825aafc0 | ||
|
|
38dc8ee500 | ||
|
|
d6fe5dca68 | ||
|
|
4ac5a36a8e | ||
|
|
ef63c23d35 | ||
|
|
d169c5a903 | ||
|
|
f38c6778ce | ||
|
|
b803edbc9f | ||
|
|
947dd62c07 | ||
|
|
b47ec440bc | ||
|
|
a982c81e3e | ||
|
|
08567505b0 | ||
|
|
e572e02d21 | ||
|
|
17c70c8953 | ||
|
|
b9767299db | ||
|
|
32fbfa15e8 | ||
|
|
6ee9be6b3c | ||
|
|
fba462e008 | ||
|
|
554340f3d3 | ||
|
|
3d6853b32c | ||
|
|
a8260cbc5c | ||
|
|
d64a18832b | ||
|
|
240ee8de9e | ||
|
|
c741bfca70 | ||
|
|
f7f62d1916 | ||
|
|
9367d8b969 | ||
|
|
71f9a74920 | ||
|
|
14e3902d51 | ||
|
|
548597367e | ||
|
|
f6e3944e31 | ||
|
|
c83935b300 | ||
|
|
5281e49908 | ||
|
|
efb8d85f24 | ||
|
|
2a54f6b625 | ||
|
|
d9503dc503 | ||
|
|
3ca00a8261 | ||
|
|
6b75dfb8a1 | ||
|
|
02d8a94e61 | ||
|
|
df417f780a | ||
|
|
42ecc8eebe | ||
|
|
bc8dd4ad27 | ||
|
|
90f4936d9e | ||
|
|
7436a7f119 | ||
|
|
e6fc81bc78 | ||
|
|
cbee82324c | ||
|
|
43b4aaea3e | ||
|
|
aecb717f10 | ||
|
|
ef014bdf06 | ||
|
|
2342343746 | ||
|
|
8a26869bca | ||
|
|
956960f85f | ||
|
|
283d76d56a | ||
|
|
fe51194e2d | ||
|
|
4b4eb6277a | ||
|
|
13f8c453ee | ||
|
|
703c29179c | ||
|
|
db6e3cd8c4 | ||
|
|
6c2925fe5f | ||
|
|
d77cf81156 | ||
|
|
5ab4e4445b | ||
|
|
b6d8e8afd9 | ||
|
|
ae19af883a | ||
|
|
385d86a6cf | ||
|
|
819852df6b | ||
|
|
dac35c5b66 | ||
|
|
e43db1f5e2 | ||
|
|
d1f3d8b870 | ||
|
|
bb87d227d4 | ||
|
|
e37e51dd24 | ||
|
|
ad0f67a7ec | ||
|
|
3403e0f176 | ||
|
|
02b83919aa | ||
|
|
7b665f7a58 | ||
|
|
e82b80099a | ||
|
|
fba31f31a9 | ||
|
|
f8d92cae41 | ||
|
|
29f955cce0 | ||
|
|
4516896626 | ||
|
|
fcf53d240c | ||
|
|
4ea0c28bc4 | ||
|
|
aad4579bbe | ||
|
|
cc73cca9c8 | ||
|
|
cbe1f9740d | ||
|
|
0719975cee | ||
|
|
8bd7737a03 | ||
|
|
4a99ca40d6 | ||
|
|
bf049ddb8f | ||
|
|
b267fe4881 | ||
|
|
049507aa76 | ||
|
|
1a86733c7b | ||
|
|
3faf214051 | ||
|
|
25385102fe | ||
|
|
3e182185aa | ||
|
|
3313825983 | ||
|
|
09e0ce3d82 | ||
|
|
68088ed392 | ||
|
|
888074b42d | ||
|
|
6bbad6acdf | ||
|
|
31e2443c90 | ||
|
|
e11962fc1c | ||
|
|
edfccc9469 | ||
|
|
15c1cc12ac | ||
|
|
6ad2e06c4a | ||
|
|
1e5d0ea888 | ||
|
|
40c86ae1ce | ||
|
|
b3082d3044 | ||
|
|
5145e35e50 | ||
|
|
6fddc9b21e | ||
|
|
9a1f6fd4cb | ||
|
|
533d81b4b0 | ||
|
|
eb2901b735 | ||
|
|
21d93d0d8c | ||
|
|
30ab428235 | ||
|
|
a3e0243b1c | ||
|
|
8c417a2dae | ||
|
|
48eb44b719 | ||
|
|
6fa67afed9 | ||
|
|
2b32d9ac6a | ||
|
|
b0b23a48d4 | ||
|
|
9465e1c783 | ||
|
|
9bf4e51030 | ||
|
|
efd001756b | ||
|
|
2537629eb2 | ||
|
|
0e8f8ecba8 | ||
|
|
4e198cef83 | ||
|
|
97bd8c74eb | ||
|
|
b2863c0de9 | ||
|
|
5cd8a2626b | ||
|
|
fa423b614c | ||
|
|
6dd813e0b7 | ||
|
|
0eac152707 | ||
|
|
4a705c7b54 | ||
|
|
89a00995c9 | ||
|
|
2e06395fd3 | ||
|
|
3fb1cd796b | ||
|
|
2e3154aa18 | ||
|
|
8542c3eff5 | ||
|
|
18c8a65edd | ||
|
|
74c5cbcd7b | ||
|
|
c32495d58f | ||
|
|
88f3c601b3 | ||
|
|
d09ff77637 | ||
|
|
877ddcc456 | ||
|
|
182247257f | ||
|
|
54d93af9fb | ||
|
|
64cb683842 | ||
|
|
87954c5b04 | ||
|
|
d23af12cb1 | ||
|
|
528772a4bf | ||
|
|
edde9d2ce4 | ||
|
|
f2d8fbf459 | ||
|
|
9e931a0c6c | ||
|
|
60932a6401 | ||
|
|
30d4032363 | ||
|
|
f9c9e8ac24 | ||
|
|
d3547f9d03 | ||
|
|
0e468adb43 | ||
|
|
ff53f32409 | ||
|
|
d0d6e5f3a2 | ||
|
|
51eeb0c58f | ||
|
|
4ff028d77e | ||
|
|
55b80221ed | ||
|
|
710ac56e69 | ||
|
|
edca360f13 | ||
|
|
c04c79e50d | ||
|
|
b1401e0aa7 | ||
|
|
ae53b06898 | ||
|
|
b1f229fb75 | ||
|
|
e3af5bf3ce | ||
|
|
4a30c4cad0 |
@@ -0,0 +1,115 @@
|
|||||||
|
---
|
||||||
|
name: model-microbenchmark
|
||||||
|
description: Time a vLLM model's forward pass on exact batch shapes (decode, prefill, chunked prefill, prefix hit, spec-decode verify, or mixes) with `vllm bench forward`, single-GPU or DP/TP/EP across nodes. Use for per-step model latency, layout/parallelism comparisons, and checking a model-level optimization. Not for single kernels (use kernel-microbenchmark) or end-to-end serving (use `vllm bench serve`).
|
||||||
|
---
|
||||||
|
|
||||||
|
# Model Microbenchmark (`vllm bench forward`)
|
||||||
|
|
||||||
|
Builds the batch without the scheduler, runs it through MRV2's real
|
||||||
|
`execute_model`, and times the forward as a one-shot CUDA graph (prefill
|
||||||
|
included). Sampling, the speculator, and CPU step overhead are excluded, so
|
||||||
|
expect results somewhat below a serving step.
|
||||||
|
|
||||||
|
## Usage
|
||||||
|
|
||||||
|
```bash
|
||||||
|
vllm bench forward --model deepseek-ai/DeepSeek-V4-Flash \
|
||||||
|
--case decode=64*1@8192 --case prefill=8192 --case mix=4096,32*1@8192
|
||||||
|
|
||||||
|
# DP/TP/EP: one process per GPU (multi-node: add --nnodes/--node-rank/--master-addr)
|
||||||
|
torchrun --nproc-per-node=4 -m vllm.entrypoints.cli.main bench forward \
|
||||||
|
--model ... -dp 4 --enable-expert-parallel --case decode=128*1@100000
|
||||||
|
```
|
||||||
|
|
||||||
|
Requests: `[N*]Q[@K][c][:D]`, comma-separated, per DP rank.
|
||||||
|
|
||||||
|
| Form | Meaning |
|
||||||
|
| --- | --- |
|
||||||
|
| `8192` | fresh prefill, 8192 tokens |
|
||||||
|
| `32*1@8192` | 32 decodes, KV length 8192 (KV length **includes** the query) |
|
||||||
|
| `4@4096:3` | spec-decode verify, 3 draft tokens |
|
||||||
|
| `2048@10240` | prefill after an 8192-token prefix-cache hit |
|
||||||
|
| `2048@10240c` | chunked prefill: the prefix came from earlier chunks |
|
||||||
|
|
||||||
|
Verify cases require `--speculative-config` with `num_speculative_tokens`
|
||||||
|
at least as large as the case's draft count; insufficient capacity is rejected.
|
||||||
|
|
||||||
|
Hit vs chunk only differs on models with SWA bounded replay (DSV4.1): a hit
|
||||||
|
also recomputes the last window (128 tokens) of the prefix.
|
||||||
|
|
||||||
|
Or `--shapes file.json|yaml`:
|
||||||
|
`{"cases": [{"name": ..., "requests": [{"query_len", "kv_len", "num_draft_tokens", "chunked", "count"}]}]}`.
|
||||||
|
|
||||||
|
Key flags (plus all `EngineArgs`):
|
||||||
|
|
||||||
|
- `--kv-len-jitter 0.5` (default): prefixes drawn within ±50%, same on every
|
||||||
|
DP rank, capped at `max_model_len`. Use `0` for exact lengths.
|
||||||
|
- `--routing auto|real|balanced`: `auto` = balanced with dummy weights.
|
||||||
|
- `--iters 20 --samples 5`, `--output-json out.json` (per-rank latency stats,
|
||||||
|
`samples_us`, graph-vs-eager check).
|
||||||
|
- Defaults: `--load-format dummy`, prefix caching off, no torch.compile.
|
||||||
|
|
||||||
|
Read `median_us` (each replay is already the max over ranks).
|
||||||
|
|
||||||
|
## Kernel breakdown
|
||||||
|
|
||||||
|
Add `--profile-dir DIR` to see where the time goes. After timing, each case is
|
||||||
|
replayed 3 more times under `torch.profiler`; every rank writes
|
||||||
|
`DIR/<case>.rank<r>.kernels.json` (GPU time per kernel per forward, sorted)
|
||||||
|
and `DIR/<case>.rank<r>.trace.json.gz` (open in Perfetto). Rank 0's top
|
||||||
|
kernels are printed and included in `--output-json`.
|
||||||
|
|
||||||
|
```bash
|
||||||
|
python -m vllm.benchmarks.forward.profile DIR/decode.rank0.kernels.json
|
||||||
|
# Before/after a change, same case: per-kernel deltas, largest first.
|
||||||
|
python -m vllm.benchmarks.forward.profile base/decode.rank0.kernels.json new/decode.rank0.kernels.json
|
||||||
|
```
|
||||||
|
|
||||||
|
- Kernels are grouped by name without template or function arguments; the
|
||||||
|
JSON keeps one full name per group in `example`.
|
||||||
|
- Only the timed forward is included: the in-graph KV restore and rank
|
||||||
|
rendezvous are excluded (`pre_forward_us`). `span_us` (first to last
|
||||||
|
forward kernel) should be close to `median_us`, a bit higher from profiler
|
||||||
|
overhead; `busy_us` can exceed it when streams overlap.
|
||||||
|
- Compare the same rank across runs: under EP, ranks differ (e.g. collective
|
||||||
|
wait time shows up inside communication kernels).
|
||||||
|
|
||||||
|
For Nsight Systems (NVTX, NCCL, CPU side, GPU metrics), skip `--profile-dir`:
|
||||||
|
the two can't share CUPTI. Each case's 3 profiled replays run between
|
||||||
|
`cudaProfilerStart`/`Stop` in an NVTX range `forward/<case>`, so a capture range
|
||||||
|
records only them, one report per case (and rank):
|
||||||
|
|
||||||
|
```bash
|
||||||
|
nsys profile --capture-range=cudaProfilerApi --capture-range-end=repeat \
|
||||||
|
--cuda-graph-trace=node -o prof vllm bench forward ... # prof.1, prof.2, ...
|
||||||
|
torchrun --nproc-per-node=4 --no-python nsys profile ... -o prof_rank%q{RANK} \
|
||||||
|
python -m vllm.entrypoints.cli.main bench forward ...
|
||||||
|
nsys stats --report cuda_gpu_kern_sum --format csv -o kern prof.1.nsys-rep
|
||||||
|
```
|
||||||
|
|
||||||
|
Keep `--capture-range-end=repeat`: nsys's default stops after the first case
|
||||||
|
and leaves the bench hanging. `nsys stats` also counts the KV restore copies
|
||||||
|
that the JSON summary excludes.
|
||||||
|
|
||||||
|
## Caveats
|
||||||
|
|
||||||
|
- **Dummy weights lie for data-dependent kernels.** Dummy gates route every
|
||||||
|
token to the same experts (hence balanced routing). Cross-check suspicious
|
||||||
|
kernels with real weights.
|
||||||
|
- **torch.compile models (e.g. Qwen3/3.5) look slow**: no compile here. Use
|
||||||
|
them for correctness only; trust perf for models under `vllm/models/`.
|
||||||
|
- `sample spread > 0.5%` warns of unstable timing. DSV4.1 DEP prefill is
|
||||||
|
inherently ~0.5–1% (MegaMoE cross-rank sync, host engram reads).
|
||||||
|
- `graph_vs_eager` may be nonzero for small batches where models branch on
|
||||||
|
`is_current_stream_capturing()`; that's expected, not a bug.
|
||||||
|
- KV cache is zero-initialized (`--kv-init zeros`); random KV was within 3%.
|
||||||
|
- Uniform DP only: every rank gets the same case; no idle ranks.
|
||||||
|
- CUDA only: it hangs on ROCm (untested cause: likely the in-graph timing
|
||||||
|
events).
|
||||||
|
- Large prefills/prefix hits need room: raise `--max-num-batched-tokens` /
|
||||||
|
`--max-model-len` / `--gpu-memory-utilization` if build fails on KV blocks.
|
||||||
|
- Startup cost is JIT/autotune, not the bench: install FlashInfer jit-cache
|
||||||
|
and cubin; DeepGEMM warmup is skipped (each case's eager pass compiles its
|
||||||
|
own shapes).
|
||||||
|
- To compare against serving decode: `vllm bench latency` with 65- vs
|
||||||
|
1-token outputs, divided by 64, with a FULL decode graph.
|
||||||
@@ -0,0 +1,157 @@
|
|||||||
|
---
|
||||||
|
name: model-recipes
|
||||||
|
description: Find vLLM deployment recipes and configs for LLMs and Hugging Face models by model and hardware. Use for recipe lookup, creation, and updates.
|
||||||
|
---
|
||||||
|
|
||||||
|
# Model Recipes
|
||||||
|
|
||||||
|
Model serving recipes are maintained in this repository's
|
||||||
|
[recipes/models/ directory](../../../recipes/models). Omni (image, video,
|
||||||
|
audio) recipes stay in vllm-project/recipes for now (moving to vllm-omni),
|
||||||
|
and Ascend NPU content is inline in these recipes (moving to vllm-ascend
|
||||||
|
overlays). The published catalog, rendered by
|
||||||
|
[vllm-project/recipes](https://github.com/vllm-project/recipes), is at
|
||||||
|
[recipes.vllm.ai](https://recipes.vllm.ai).
|
||||||
|
|
||||||
|
## Usage notes
|
||||||
|
|
||||||
|
1. Recipe lookup returns commands and deployment guidance without launching
|
||||||
|
`vllm serve`.
|
||||||
|
2. Use published configurations or the recipes repository's command generator
|
||||||
|
for supported selections. Return commands as published, including their
|
||||||
|
flags and parallelism settings.
|
||||||
|
3. Recipes are starting points for deployment and may not be tuned for your
|
||||||
|
workload. Check each recipe for its verified configurations, and use
|
||||||
|
benchmarks of your workload to guide further tuning.
|
||||||
|
4. To create or update a recipe, follow the
|
||||||
|
[authoring workflow below](#create-or-update-a-recipe).
|
||||||
|
|
||||||
|
## Find a recipe
|
||||||
|
|
||||||
|
Read recipes from the published JSON on recipes.vllm.ai. It is generated from
|
||||||
|
the source YAML with variant, hardware, and strategy settings already
|
||||||
|
resolved; the YAML contains comments and conditional overrides, so do not use
|
||||||
|
it for lookup. When presenting results, link the website page. Read the source
|
||||||
|
YAML only when creating or updating a recipe.
|
||||||
|
|
||||||
|
Each recipe has a page at `https://recipes.vllm.ai/<org>/<repo>` and JSON at
|
||||||
|
the same path plus `.json`. Paths use the full Hugging Face ID, preserving
|
||||||
|
case; do not substitute `meta.slug` or a display title. For example,
|
||||||
|
`Qwen/Qwen3.8-27B` maps to
|
||||||
|
[recipes.vllm.ai/Qwen/Qwen3.8-27B](https://recipes.vllm.ai/Qwen/Qwen3.8-27B).
|
||||||
|
|
||||||
|
Recipe JSON is often over 20 KB, mostly the `guide`. Instead of printing it,
|
||||||
|
read only what the request needs: each step below returns the paths for the
|
||||||
|
next, so stop once the request is answered. Commands need `curl` and `jq`.
|
||||||
|
[scripts/read_recipe.sh](scripts/read_recipe.sh) is in this skill's directory;
|
||||||
|
the examples use its path from the vLLM repository root.
|
||||||
|
|
||||||
|
### Search the catalog
|
||||||
|
|
||||||
|
Skip this step if the exact HF ID is known. Otherwise search by model ID,
|
||||||
|
family, or provider using case-insensitive keywords. Each
|
||||||
|
whitespace-separated word must occur in the ID, title, or provider:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
curl -fsSL https://recipes.vllm.ai/models.json |
|
||||||
|
jq --arg q 'qwen 27b' '
|
||||||
|
($q | ascii_downcase | [scan("\\S+")]) as $words | .[] |
|
||||||
|
([.hf_id, .title, .provider] | join(" ") | ascii_downcase) as $text |
|
||||||
|
select(all($words[]; . as $word | $text | contains($word))) |
|
||||||
|
{hf_id, json, url, derived_from}'
|
||||||
|
```
|
||||||
|
|
||||||
|
`json` is the recipe data path; `url` is its page path. Prefix both with
|
||||||
|
`https://recipes.vllm.ai`. A `derived_from` entry is a variant of a parent
|
||||||
|
recipe: fetch its own `json` to get that checkpoint's command. Its page may
|
||||||
|
belong to the parent, so link the returned `url` rather than assuming every
|
||||||
|
checkpoint has a separate page.
|
||||||
|
|
||||||
|
If there is no exact match, search the family and inspect `variants` before
|
||||||
|
concluding the recipe is missing.
|
||||||
|
|
||||||
|
### Summarize the recipe
|
||||||
|
|
||||||
|
Save the recipe JSON to a file and summarize it:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
read_recipe=.agents/skills/model-recipes/scripts/read_recipe.sh
|
||||||
|
recipe=$(mktemp)
|
||||||
|
curl -fsSL https://recipes.vllm.ai/Qwen/Qwen3.8-27B.json -o "$recipe"
|
||||||
|
"$read_recipe" "$recipe"
|
||||||
|
```
|
||||||
|
|
||||||
|
`default` is the recommended hardware, strategy, and variant; `hardware` maps
|
||||||
|
each hardware ID to its command path; `recipe_verified_hardware` lists hardware
|
||||||
|
where the recipe as a whole was verified end to end. For capability
|
||||||
|
requirements, such as tool calling or text-to-video, check `features` and
|
||||||
|
`omni_tasks`, then confirm in the guide.
|
||||||
|
Some recipes, including Omni, lack `hardware`; skip hardware selection and
|
||||||
|
use the guide's launch and task-specific sections.
|
||||||
|
|
||||||
|
### Select hardware and strategy
|
||||||
|
|
||||||
|
Match a hardware ID to the user's GPU and fetch its path from `hardware`,
|
||||||
|
prefixed with `https://recipes.vllm.ai`, rather than constructing a URL. That
|
||||||
|
response is the command object itself: single-node objects carry `command`,
|
||||||
|
and multi-node objects carry `head_command` and `worker_commands` instead, so
|
||||||
|
list its keys before selecting fields.
|
||||||
|
Check `hardware_profile` to confirm that the selected configuration matches
|
||||||
|
the user's GPU model and specifications. Its `gpu_count` describes the profile,
|
||||||
|
not necessarily the number of GPUs used by the command. Check the command's
|
||||||
|
parallelism settings, `node_count`, and all `worker_commands` against the
|
||||||
|
user's available topology, and compare the variant's `vram_minimum_gb`, an
|
||||||
|
estimate, with the total memory of the GPUs the command uses; a configuration
|
||||||
|
below that minimum is not a working option unless the guide says it was
|
||||||
|
tested. Ask when the user's hardware is unclear. If no
|
||||||
|
published command or guide command fits, report the mismatch and return the
|
||||||
|
closest one unchanged; list any adjustments the user's setup would need
|
||||||
|
separately and mark them unverified instead of editing the command.
|
||||||
|
|
||||||
|
For another strategy, follow `alternatives` in the same response. These are
|
||||||
|
static files; query parameters do not change their configuration. For other
|
||||||
|
feature/topology selections, use the recipes repository's command synthesis.
|
||||||
|
|
||||||
|
### Read deployment guidance
|
||||||
|
|
||||||
|
Read the guide sections that apply to the selection, such as prerequisites,
|
||||||
|
launch notes for the selected hardware or variant, troubleshooting, and known
|
||||||
|
limitations. Pass entries from `guide_sections` or prefixes of their text.
|
||||||
|
The script prints every matching section with its subsections and fails when
|
||||||
|
a section matches nothing:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
"$read_recipe" "$recipe" prerequisites troubleshooting
|
||||||
|
```
|
||||||
|
|
||||||
|
Query other fields with `jq` on the saved file, such as `features.<name>`,
|
||||||
|
`hardware_overrides`, or `omni.tasks` for request examples.
|
||||||
|
|
||||||
|
### Return the result
|
||||||
|
|
||||||
|
Return the website link, selected checkpoint and hardware, the requested
|
||||||
|
command, and relevant prerequisites and caveats from the guide. Pick one
|
||||||
|
command and copy it, including its Docker form, exactly as the command object
|
||||||
|
or guide section gives it; do not combine commands from different sections or
|
||||||
|
add, drop, or reorder flags. List optional changes separately.
|
||||||
|
|
||||||
|
For each command, state its source, either a generated hardware or strategy
|
||||||
|
configuration or a named guide section, and whether that source says it was
|
||||||
|
tested. A `recipe_verified_hardware` entry covers the recipe on that
|
||||||
|
hardware, not every variant, strategy, or guide command, so it does not make a
|
||||||
|
command verified. Generated configurations are not automatically verified.
|
||||||
|
|
||||||
|
## Create or update a recipe
|
||||||
|
|
||||||
|
Recipes cover official or widely used checkpoints, with configurations verified
|
||||||
|
end to end on real hardware. Do not add recipes for arbitrary community
|
||||||
|
uploads, untested hardware claims, or non-standard flags that only work for one
|
||||||
|
setup. Before opening a pull request, confirm that the user ran the
|
||||||
|
configuration and can share the results.
|
||||||
|
|
||||||
|
Edit the YAML under [recipes/models/](../../../recipes/models) in this
|
||||||
|
repository, following the recipes repository's
|
||||||
|
[add-recipe skill](https://github.com/vllm-project/recipes/blob/main/.agents/skills/add-recipe/SKILL.md)
|
||||||
|
for the schema. Validate and preview it from a checkout of
|
||||||
|
`vllm-project/recipes` pointed at this directory, as
|
||||||
|
[recipes/README.md](../../../recipes/README.md) describes.
|
||||||
@@ -0,0 +1,4 @@
|
|||||||
|
interface:
|
||||||
|
display_name: "Model Recipes"
|
||||||
|
short_description: "Find vLLM deployment recipes and configs for LLMs and Hugging Face models by model and hardware."
|
||||||
|
default_prompt: "Use $model-recipes to find a recipe for my model and hardware, and return its commands and deployment caveats."
|
||||||
+66
@@ -0,0 +1,66 @@
|
|||||||
|
#!/bin/bash
|
||||||
|
# Usage: read_recipe.sh <recipe.json> [guide-section...]
|
||||||
|
# Without sections, print a compact summary of a recipes.vllm.ai recipe JSON.
|
||||||
|
# With sections, print each guide section whose heading starts with one of
|
||||||
|
# them (case-insensitive), including its subsections.
|
||||||
|
|
||||||
|
set -euo pipefail
|
||||||
|
|
||||||
|
if [ $# -lt 1 ]; then
|
||||||
|
echo "Usage: $0 <recipe.json> [guide-section...]" >&2
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
|
||||||
|
# Print "<level>\t<heading text>\t<line>" for guide lines, marking headings
|
||||||
|
# outside code fences with their level and other lines with 0.
|
||||||
|
guide_lines() {
|
||||||
|
jq -r '.guide // ""' "$1" | awk '
|
||||||
|
/^[[:space:]]*(```|~~~)/ { fence = !fence }
|
||||||
|
!fence && match($0, /^#+ /) {
|
||||||
|
print RLENGTH - 1 "\t" substr($0, RLENGTH + 1) "\t" $0
|
||||||
|
next
|
||||||
|
}
|
||||||
|
{ print "0\t\t" $0 }'
|
||||||
|
}
|
||||||
|
|
||||||
|
if [ $# -gt 1 ]; then
|
||||||
|
recipe=$1
|
||||||
|
shift
|
||||||
|
status=0
|
||||||
|
for section in "$@"; do
|
||||||
|
guide_lines "$recipe" | awk -F '\t' -v h="$section" '
|
||||||
|
BEGIN { h = tolower(h); sub(/^#+[[:space:]]*/, "", h) }
|
||||||
|
$1 > 0 && lvl && $1 <= lvl { lvl = 0 }
|
||||||
|
$1 > 1 && !lvl && index(tolower($2), h) == 1 { lvl = $1; found = 1 }
|
||||||
|
lvl { sub(/^[^\t]*\t[^\t]*\t/, ""); print }
|
||||||
|
END {
|
||||||
|
if (!found) {
|
||||||
|
print "No guide section starts with: " h > "/dev/stderr"
|
||||||
|
exit 1
|
||||||
|
}
|
||||||
|
}' || status=1
|
||||||
|
done
|
||||||
|
exit $status
|
||||||
|
fi
|
||||||
|
|
||||||
|
sections=$(guide_lines "$1" | awk -F '\t' '$1 == 2 || $1 == 3 { print $3 }' |
|
||||||
|
jq -R . | jq -s .)
|
||||||
|
|
||||||
|
jq --argjson sections "$sections" '{
|
||||||
|
hf_id,
|
||||||
|
title: .meta.title,
|
||||||
|
tasks: .meta.tasks,
|
||||||
|
recipe_verified_hardware: .meta.hardware,
|
||||||
|
omni_tasks: (.omni.tasks // null |
|
||||||
|
if . then map(objects |= {id, label, endpoint, model_id, description})
|
||||||
|
else null end),
|
||||||
|
variants: (.variants // {} | map_values(
|
||||||
|
{model_id, precision, vram_minimum_gb, supported_hardware} |
|
||||||
|
with_entries(select(.value != null)))),
|
||||||
|
features: (.features // {} | keys),
|
||||||
|
opt_in_features,
|
||||||
|
default: (.recommended_command // null |
|
||||||
|
if . then {hardware, strategy, variant} else null end),
|
||||||
|
hardware: .recommended_command.by_hardware,
|
||||||
|
guide_sections: $sections
|
||||||
|
} | with_entries(select(.value != null))' "$1"
|
||||||
@@ -1,6 +1,6 @@
|
|||||||
---
|
---
|
||||||
name: pr-checklist
|
name: pr-checklist
|
||||||
description: Prepare a vLLM change for human PR review or re-review, or analyze an open pull request. Use to check design fit, behavioral coverage, performance evidence, diff quality, and closure of previous feedback before requesting maintainer attention.
|
description: Prepare a vLLM change for human PR review or re-review, or analyze an open pull request. Use before opening a PR, drafts included (e.g. `gh pr create`), or pushing review fixes, to check design fit, behavioral coverage, performance evidence, diff quality, and closure of previous feedback.
|
||||||
---
|
---
|
||||||
|
|
||||||
# PR Checklist
|
# PR Checklist
|
||||||
@@ -181,6 +181,8 @@ Summarize model evaluations and benchmarks in compact tables with the configurat
|
|||||||
|
|
||||||
When fixing bugs or issues, provide a clear root-cause analysis. Explain what caused the problem, how it was identified, and why the chosen solution effectively addresses it. A patch which resolves the issue without a proper root-cause analysis may lead to recurring problems and increased maintenance overhead.
|
When fixing bugs or issues, provide a clear root-cause analysis. Explain what caused the problem, how it was identified, and why the chosen solution effectively addresses it. A patch which resolves the issue without a proper root-cause analysis may lead to recurring problems and increased maintenance overhead.
|
||||||
|
|
||||||
|
For fixes that involve disaggregated prefill/decode (PD) logic, such as the NIXL connector (`vllm/distributed/kv_transfer/kv_connector/v1/nixl/`), make a best effort to include a minimal example of the flow being changed and/or the initial flow that caused the failure. A short numbered sequence (or diagram) of a request's path across the P and D instances, e.g. scheduler admission, prefill execution, KV transfer registration and write, decode-side read, token generation, lets reviewers trace the root cause and the fix without reconstructing the distributed flow from the diff. Keep the example minimal: only the steps and components involved in the change. See the [disaggregated prefill](../../../docs/features/disagg_prefill.md), [NIXL KV push](../../../docs/design/nixl_kv_push_connector.md), and [NIXL KV cache lease](../../../docs/design/nixl_kv_cache_lease.md) docs for the flows involved.
|
||||||
|
|
||||||
#### 4.4: Implementation Details
|
#### 4.4: Implementation Details
|
||||||
|
|
||||||
Provide a detailed explanation of the implementation, including design decisions, trade-offs, and any relevant technical details. Highlight any non-obvious choices, tradeoffs, potential limitations, and areas where maintainer attention is required.
|
Provide a detailed explanation of the implementation, including design decisions, trade-offs, and any relevant technical details. Highlight any non-obvious choices, tradeoffs, potential limitations, and areas where maintainer attention is required.
|
||||||
|
|||||||
@@ -0,0 +1,191 @@
|
|||||||
|
---
|
||||||
|
name: transformers-upgrade
|
||||||
|
description: "Playbook for changing vLLM's Transformers version bounds. Use when bumping the pinned or maximum Transformers version, raising the minimum Transformers version, or deleting vendored configs, processors, or compat shims that upstream Transformers now provides."
|
||||||
|
---
|
||||||
|
|
||||||
|
# Upgrading Transformers
|
||||||
|
|
||||||
|
The supported range lives in `requirements/common.txt`. CI pins one exact
|
||||||
|
version in `requirements/test/*.in` and the compiled `requirements/test/*.txt`.
|
||||||
|
A version change is one of two jobs, and they usually come as a pair:
|
||||||
|
|
||||||
|
- **Bump the pin**: a new Transformers release becomes the CI version and
|
||||||
|
the upper bound. vLLM grows compat code for it.
|
||||||
|
- **Raise the floor**: the minimum moves up. That compat code, and every
|
||||||
|
vendored config or processor upstream now ships, becomes dead weight.
|
||||||
|
Every floor raise ends with an **unvendoring pass**.
|
||||||
|
|
||||||
|
## Bump the pin
|
||||||
|
|
||||||
|
1. Edit the pin line in each `requirements/test/*.in` and `*.txt` and the
|
||||||
|
upper bound in `requirements/common.txt`. Past bumps edit only the pin
|
||||||
|
line in the compiled files; see `git log -- requirements/common.txt`.
|
||||||
|
2. Read the release notes for config validation changes, renamed auto-mapping
|
||||||
|
formats, and removed attributes; these are what break vLLM.
|
||||||
|
3. Search `tests/` for `min_transformers_version` and skip markers naming the
|
||||||
|
new version, and un-gate them.
|
||||||
|
4. Run the suites in [Testing](#testing) and fix what breaks. Mark every
|
||||||
|
shim with a `# Transformers >= X` comment so the next floor raise finds it.
|
||||||
|
|
||||||
|
Done when the [Testing](#testing) suites pass on the new pin and every test
|
||||||
|
waiting on this version is un-gated.
|
||||||
|
|
||||||
|
## Raise the floor (unvendoring pass)
|
||||||
|
|
||||||
|
### 1. Inventory
|
||||||
|
|
||||||
|
Inventory candidates with the floor version installed (no vLLM install needed):
|
||||||
|
|
||||||
|
```bash
|
||||||
|
uv run --no-project --with transformers==<floor> \
|
||||||
|
python .agents/skills/transformers-upgrade/scripts/find_upstreamed.py
|
||||||
|
```
|
||||||
|
|
||||||
|
It lists:
|
||||||
|
|
||||||
|
- vendored configs whose `model_type` upstream now owns;
|
||||||
|
- `_CONFIG_REGISTRY` overrides of upstream types;
|
||||||
|
- registered processors that collide with upstream class names or models;
|
||||||
|
- version-gated code at or below the floor;
|
||||||
|
- code that reads the installed Transformers version, whatever its threshold;
|
||||||
|
- patches citing a Transformers issue or PR (with whether a referenced PR is
|
||||||
|
in the floor release) or a future minimum version.
|
||||||
|
|
||||||
|
It finds candidates by name only. Every hit still needs a verdict.
|
||||||
|
|
||||||
|
### 2. Port each candidate to upstream
|
||||||
|
|
||||||
|
Every hit is deleted by default. A vendored copy is a liability: it drifts
|
||||||
|
from upstream, hides upstream fixes, and shadows the native class. Port the
|
||||||
|
vLLM model code to the upstream schema instead, renaming attribute reads and
|
||||||
|
deriving values from upstream fields.
|
||||||
|
|
||||||
|
Fan candidates out to parallel subagents. Each one compares the vendored and
|
||||||
|
upstream classes, then greps every attribute the vLLM model code reads.
|
||||||
|
[Upstreaming hazards](#upstreaming-hazards) lists the usual fixes.
|
||||||
|
|
||||||
|
Keep a vendored class only when upstream cannot load a checkpoint vLLM must
|
||||||
|
keep serving, and record why in the PR description. A different upstream
|
||||||
|
schema, a model-code rewrite, or a needed eval is work for the PR, not a
|
||||||
|
reason to keep.
|
||||||
|
|
||||||
|
### 3. Prove it on real checkpoints
|
||||||
|
|
||||||
|
For every checkpoint in `tests/models/registry.py` that uses a ported
|
||||||
|
config, dump what vLLM builds before and after the change, then diff the two.
|
||||||
|
Run both dumps; each catches what the other misses:
|
||||||
|
|
||||||
|
- `dump_configs.py`: the resolved config, attribute by attribute.
|
||||||
|
- `dump_model.py`: the model built on the meta device with no GPU or weights.
|
||||||
|
It records ModelConfig sizes, every parameter shape, and every module's
|
||||||
|
scalar attributes (`head_dim`, `num_kv_heads`, `scaling`, ...). Missing
|
||||||
|
fields that are read with defaults only show up here.
|
||||||
|
|
||||||
|
```bash
|
||||||
|
git worktree add --detach <scratch>/vllm-base upstream/main
|
||||||
|
S=.agents/skills/transformers-upgrade/scripts
|
||||||
|
for dump in dump_configs dump_model; do
|
||||||
|
PYTHONPATH=<scratch>/vllm-base .venv/bin/python $S/$dump.py before.jsonl <repos>
|
||||||
|
PYTHONPATH=$PWD .venv/bin/python $S/$dump.py after.jsonl <repos>
|
||||||
|
.venv/bin/python $S/diff_dumps.py before.jsonl after.jsonl
|
||||||
|
done
|
||||||
|
```
|
||||||
|
|
||||||
|
Add `--trust-remote-code` for checkpoints whose `config.json` has an
|
||||||
|
`auto_map`, and dump both ways.
|
||||||
|
|
||||||
|
How to read the diffs:
|
||||||
|
|
||||||
|
- **A `<MISSING>` config field the model reads:** this crashes or silently
|
||||||
|
falls back to a default. Port the model code to the upstream field.
|
||||||
|
- **New upstream-only defaults** (`attention_bias=False`,
|
||||||
|
`pad_token_id=None`): usually benign. A model diff of 0 confirms it.
|
||||||
|
- **Any model diff:** this is a numerics change, and the PR needs a model
|
||||||
|
eval. For example, A.X-K1 gained the checkpoint's YaRN rope scaling, which
|
||||||
|
the vendored class had been dropping; it shows up as
|
||||||
|
`layers.*.self_attn.scaling (x61)`.
|
||||||
|
|
||||||
|
### 4. Delete
|
||||||
|
|
||||||
|
For each deleted config:
|
||||||
|
|
||||||
|
- Delete the file.
|
||||||
|
- Remove its entries from `_CLASS_TO_MODULE` and `__all__` in
|
||||||
|
`vllm/transformers_utils/configs/__init__.py`.
|
||||||
|
- Remove its entries from `_CONFIG_REGISTRY` in
|
||||||
|
`vllm/transformers_utils/config.py`.
|
||||||
|
- Switch every importer, including tests, to `from transformers import ...`.
|
||||||
|
- Remove the `source_file_dependencies` lines naming the file from
|
||||||
|
`.buildkite/`.
|
||||||
|
|
||||||
|
Deleted processors follow the same steps in
|
||||||
|
`vllm/transformers_utils/processors/__init__.py`.
|
||||||
|
|
||||||
|
Before merging, rebase and grep again for the old field names: PRs that land
|
||||||
|
in between still read them.
|
||||||
|
|
||||||
|
Done when every line of the inventory output is deleted, or kept with a
|
||||||
|
reason that meets the bar in step 2. The PR also carries the config diff
|
||||||
|
results and evals for any changed values.
|
||||||
|
|
||||||
|
## Upstreaming hazards
|
||||||
|
|
||||||
|
Upstream configs are `@strict` dataclasses. Checkpoint keys upstream does not
|
||||||
|
declare survive as plain attributes, but only when the checkpoint sets them.
|
||||||
|
Defaults that only vLLM sets, and values vLLM derives, vanish.
|
||||||
|
|
||||||
|
| Hazard | Signal | Fix |
|
||||||
|
| --- | --- | --- |
|
||||||
|
| Upstream consumes legacy keys | `__post_init__` pops keys the model reads (`deepseek_v4` `compress_ratios`) | Read the upstream replacement (`layer_types`, `mlp_layer_types`, per-layer `rope_parameters`) |
|
||||||
|
| Renamed or dropped fields | Diff shows `<MISSING>` for a field the model reads | Read the upstream name; derive dropped flags from what implies them (`enable_moe_block` from `num_experts`) |
|
||||||
|
| Undeclared field without a default | `config.x` raises `AttributeError` for configs that omit `x`, e.g. minimal test configs (A.X-K1 `scoring_func`). Dumps of real checkpoints miss it | Upstream ignoring `x` usually means vLLM can stop reading it; if vLLM truly needs it, read `getattr(config, "x", <old default>)` |
|
||||||
|
| Top-level config stops forwarding | The vendored top-level config forwarded reads to `text_config`; upstream does not. `getattr(config, "x", default)` silently takes the default, e.g. on MTP draft configs from `SpeculativeConfig.hf_config_override`, which the dumps do not build | Read from `get_text_config()`; grep `getattr` reads of every field, including speculative-decoding paths |
|
||||||
|
| Type check on the config | `ctx.get_hf_config(SomeConfig)` relies on the vendored base class | Accept the upstream class too, e.g. a `Cosmos3ProcessingInfo` overriding `get_hf_config` |
|
||||||
|
| Remote code takes over | Checkpoint `config.json` has `auto_map`; with `--trust-remote-code`, the hub class replaces the native one once vLLM stops registering its own | Check the remote class loads; if not, register the upstream class for that `model_type` |
|
||||||
|
| Read-only upstream fields | Properties or derived fields break subclasses and `hf_overrides` (`nemotron_h` `hybrid_override_pattern`) | Override the source field (`layers_block_type`) instead |
|
||||||
|
| Behavioural rewrite | Upstream derives fields differently (`diffusion_gemma` `sliding_window`) | Upstream matches the reference implementation; verify with an eval |
|
||||||
|
| Original checkpoint format | Upstream targets `-hf` conversions; vLLM serves the originals (`qwen3_asr`, `qianfan_ocr`) | Keep only if upstream cannot load the original at all |
|
||||||
|
| Processor output contract | Model code consumes keys upstream does not emit | Port the model to upstream's keys |
|
||||||
|
| Name collision | A registered vendored processor shares an upstream class name and hijacks `get_processor` (`InternVLProcessor`) | Drop the registry entry |
|
||||||
|
|
||||||
|
Version gates from the inventory need a decision:
|
||||||
|
|
||||||
|
- **Code** only reachable below the floor is deleted. This covers:
|
||||||
|
- comparisons against `TRANSFORMERS_VERSION`;
|
||||||
|
- branches labelled `# Transformers < X`;
|
||||||
|
- fallbacks for fields that upstream configs now always set, e.g.
|
||||||
|
`mlp_layer_types`, `per_layer_config` or legacy `layer_types` names.
|
||||||
|
|
||||||
|
A `skipif` whose condition is now always true becomes an unconditional
|
||||||
|
`skip` with the same reason.
|
||||||
|
- **`min_transformers_version`** at or below the floor is removed.
|
||||||
|
- **`max_transformers_version`** below the floor means CI never tests that
|
||||||
|
model; report it rather than deleting it silently.
|
||||||
|
- **Patches citing a Transformers issue or PR:**
|
||||||
|
- Delete the patch when its fix is in the floor release.
|
||||||
|
- For an issue, find the PR that closed it and check that PR. A closed
|
||||||
|
issue is not a fixed one: issues get closed while the bug is still in
|
||||||
|
the release.
|
||||||
|
- Re-run the patched behaviour before deleting. A fix in the release does
|
||||||
|
not always cover vLLM's path: Emu3's processor gained BOS upstream, but
|
||||||
|
vLLM tokenizes without the processor.
|
||||||
|
- Links that only explain a design choice (e.g. a float32 RoPE note) are
|
||||||
|
not patches; leave them.
|
||||||
|
|
||||||
|
## Testing
|
||||||
|
|
||||||
|
```bash
|
||||||
|
.venv/bin/python -m pytest tests/transformers_utils tests/config tests/tokenizers_
|
||||||
|
.venv/bin/python -m pytest tests/models/multimodal/processing/test_common.py -k "<models>"
|
||||||
|
```
|
||||||
|
|
||||||
|
Add `tests/models/test_initialization.py -k "<archs>"` where a GPU is
|
||||||
|
available, and a model eval for any model whose resolved config changed.
|
||||||
|
|
||||||
|
Models in `vllm/models/` are high priority: whenever their config or model
|
||||||
|
code changes, run GSM8k (`tests/evals/gsm8k/`) and GPQA Diamond
|
||||||
|
(`tests/evals/gpt_oss/`) on `main` and the branch, even when the dumps show
|
||||||
|
no diff, and put both scores in the PR. FlashInfer autotuning picks kernel
|
||||||
|
tactics afresh on every server start, which moved DeepSeek-V4-Flash GSM8k by
|
||||||
|
about 1 point; pass `--kernel-config '{"enable_flashinfer_autotune": false}'`
|
||||||
|
to both servers so greedy outputs are comparable.
|
||||||
@@ -0,0 +1,4 @@
|
|||||||
|
interface:
|
||||||
|
display_name: "Transformers Upgrade"
|
||||||
|
short_description: "Bump vLLM's Transformers version and delete vendored code upstream now provides."
|
||||||
|
default_prompt: "Use $transformers-upgrade to raise the minimum Transformers version and remove vendored configs, processors, and shims it makes redundant."
|
||||||
@@ -0,0 +1,51 @@
|
|||||||
|
# SPDX-License-Identifier: Apache-2.0
|
||||||
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||||
|
"""Diff two dump_configs.py or dump_model.py outputs, per repo.
|
||||||
|
|
||||||
|
python diff_dumps.py before.jsonl after.jsonl
|
||||||
|
"""
|
||||||
|
|
||||||
|
import json
|
||||||
|
import sys
|
||||||
|
from collections import Counter
|
||||||
|
|
||||||
|
import regex as re
|
||||||
|
|
||||||
|
IGNORED = {"transformers_version", "_name_or_path", "architectures", "auto_map"}
|
||||||
|
|
||||||
|
|
||||||
|
def load(path: str) -> dict[str, dict]:
|
||||||
|
with open(path) as f:
|
||||||
|
return {record["repo"]: record for record in map(json.loads, f)}
|
||||||
|
|
||||||
|
|
||||||
|
def diff(before: dict, after: dict, prefix: str = ""):
|
||||||
|
for key in sorted(set(before) | set(after)):
|
||||||
|
if key in IGNORED:
|
||||||
|
continue
|
||||||
|
old, new = before.get(key, "<MISSING>"), after.get(key, "<MISSING>")
|
||||||
|
if isinstance(old, dict) and isinstance(new, dict) and key != "rope_parameters":
|
||||||
|
yield from diff(old, new, f"{prefix}{key}.")
|
||||||
|
elif old != new:
|
||||||
|
yield f"{prefix}{key}", json.dumps(old), json.dumps(new)
|
||||||
|
|
||||||
|
|
||||||
|
def collapse(diffs) -> Counter:
|
||||||
|
"""Merge diffs that differ only by layer index, e.g. `layers.*.scaling`."""
|
||||||
|
return Counter(
|
||||||
|
(re.sub(r"\.\d+\.", ".*.", path), old, new) for path, old, new in diffs
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
before, after = load(sys.argv[1]), load(sys.argv[2])
|
||||||
|
for repo, old in before.items():
|
||||||
|
new = after.get(repo, {"error": "missing from after"})
|
||||||
|
if "error" in old or "error" in new:
|
||||||
|
print(f"== {repo}\n before: {old.get('error', 'ok')}")
|
||||||
|
print(f" after: {new.get('error', 'ok')}")
|
||||||
|
continue
|
||||||
|
diffs = collapse(diff(old["cfg"], new["cfg"]))
|
||||||
|
print(f"== {repo}: {old['cls']} -> {new['cls']} ({sum(diffs.values())} diffs)")
|
||||||
|
for (path, old_value, new_value), count in diffs.items():
|
||||||
|
times = f" (x{count})" if count > 1 else ""
|
||||||
|
print(f" {path}{times}: before={old_value} after={new_value}")
|
||||||
@@ -0,0 +1,30 @@
|
|||||||
|
# SPDX-License-Identifier: Apache-2.0
|
||||||
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||||
|
"""Dump the config vLLM resolves for each checkpoint, one JSON line per repo.
|
||||||
|
|
||||||
|
Run once per vLLM tree (before and after a change), then compare the two
|
||||||
|
outputs with diff_dumps.py:
|
||||||
|
|
||||||
|
PYTHONPATH=<vllm tree> .venv/bin/python dump_configs.py out.jsonl <repo>...
|
||||||
|
|
||||||
|
Pass --trust-remote-code to resolve checkpoints the way users who set it do.
|
||||||
|
"""
|
||||||
|
|
||||||
|
import json
|
||||||
|
import sys
|
||||||
|
|
||||||
|
from vllm.transformers_utils.config import get_config
|
||||||
|
|
||||||
|
out, *args = sys.argv[1:]
|
||||||
|
trust_remote_code = "--trust-remote-code" in args
|
||||||
|
with open(out, "w") as f:
|
||||||
|
for repo in (arg for arg in args if arg != "--trust-remote-code"):
|
||||||
|
try:
|
||||||
|
config = get_config(repo, trust_remote_code=trust_remote_code)
|
||||||
|
cls = f"{type(config).__module__}.{type(config).__name__}"
|
||||||
|
record = {"repo": repo, "cls": cls, "cfg": config.to_dict()}
|
||||||
|
except Exception as e:
|
||||||
|
error = f"{type(e).__name__}: {e}".splitlines()[0]
|
||||||
|
record = {"repo": repo, "error": error}
|
||||||
|
f.write(json.dumps(record, default=str, sort_keys=True) + "\n")
|
||||||
|
f.flush()
|
||||||
@@ -0,0 +1,114 @@
|
|||||||
|
# SPDX-License-Identifier: Apache-2.0
|
||||||
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||||
|
"""Build each model on the meta device and dump what vLLM constructs.
|
||||||
|
|
||||||
|
Records ModelConfig-derived sizes, every parameter shape, and scalar
|
||||||
|
attributes of every module (head_dim, num_kv_heads, sliding_window, ...).
|
||||||
|
Needs no GPU and no weights. Run once per vLLM tree, then compare the two
|
||||||
|
outputs with diff_dumps.py:
|
||||||
|
|
||||||
|
PYTHONPATH=<vllm tree> .venv/bin/python dump_model.py out.jsonl <repo>...
|
||||||
|
|
||||||
|
Pass --trust-remote-code to resolve checkpoints the way users who set it do.
|
||||||
|
"""
|
||||||
|
|
||||||
|
import json
|
||||||
|
import socket
|
||||||
|
import sys
|
||||||
|
|
||||||
|
import torch
|
||||||
|
|
||||||
|
from vllm.config import set_current_vllm_config
|
||||||
|
from vllm.config.vllm import VllmConfig
|
||||||
|
from vllm.distributed import (
|
||||||
|
init_distributed_environment,
|
||||||
|
initialize_model_parallel,
|
||||||
|
model_parallel_is_initialized,
|
||||||
|
)
|
||||||
|
from vllm.engine.arg_utils import EngineArgs
|
||||||
|
from vllm.model_executor.model_loader.utils import initialize_model
|
||||||
|
from vllm.utils.torch_utils import set_default_torch_dtype
|
||||||
|
|
||||||
|
# Construction only: skip model runner checks that need a GPU or Triton
|
||||||
|
VllmConfig._get_v1_model_runner_unsupported_features = lambda self: [] # type: ignore[method-assign]
|
||||||
|
|
||||||
|
# Model code that moves submodules to a device must leave them on meta
|
||||||
|
_module_to = torch.nn.Module.to
|
||||||
|
|
||||||
|
|
||||||
|
def _meta_safe_to(self, *args, **kwargs):
|
||||||
|
kwargs.pop("device", None)
|
||||||
|
args = tuple(a for a in args if not isinstance(a, (torch.device, str, int)))
|
||||||
|
return _module_to(self, *args, **kwargs)
|
||||||
|
|
||||||
|
|
||||||
|
torch.nn.Module.to = _meta_safe_to # type: ignore[method-assign]
|
||||||
|
|
||||||
|
SCALARS = (bool, int, float, str)
|
||||||
|
|
||||||
|
|
||||||
|
def module_attrs(model: torch.nn.Module) -> dict[str, dict]:
|
||||||
|
attrs = {}
|
||||||
|
for name, module in model.named_modules():
|
||||||
|
scalars = {
|
||||||
|
key: value
|
||||||
|
for key, value in vars(module).items()
|
||||||
|
if not key.startswith("_") and isinstance(value, SCALARS)
|
||||||
|
}
|
||||||
|
if scalars:
|
||||||
|
attrs[name or "<root>"] = scalars
|
||||||
|
return attrs
|
||||||
|
|
||||||
|
|
||||||
|
def dump(repo: str, trust_remote_code: bool) -> dict:
|
||||||
|
args = EngineArgs(
|
||||||
|
model=repo,
|
||||||
|
load_format="dummy",
|
||||||
|
enforce_eager=True,
|
||||||
|
max_model_len=4096,
|
||||||
|
trust_remote_code=trust_remote_code,
|
||||||
|
)
|
||||||
|
vllm_config = args.create_engine_config()
|
||||||
|
model_config = vllm_config.model_config
|
||||||
|
with set_current_vllm_config(vllm_config):
|
||||||
|
if not model_parallel_is_initialized():
|
||||||
|
with socket.socket() as sock:
|
||||||
|
sock.bind(("", 0))
|
||||||
|
port = sock.getsockname()[1]
|
||||||
|
init_distributed_environment(1, 0, f"tcp://127.0.0.1:{port}", 0, "gloo")
|
||||||
|
initialize_model_parallel(1, 1)
|
||||||
|
with set_default_torch_dtype(model_config.dtype), torch.device("meta"):
|
||||||
|
model = initialize_model(vllm_config=vllm_config)
|
||||||
|
return {
|
||||||
|
"repo": repo,
|
||||||
|
"cls": type(model).__name__,
|
||||||
|
"cfg": {
|
||||||
|
"model_config": {
|
||||||
|
"head_size": model_config.get_head_size(),
|
||||||
|
"total_num_kv_heads": model_config.get_total_num_kv_heads(),
|
||||||
|
"sliding_window": model_config.get_sliding_window(),
|
||||||
|
"num_layers": model_config.get_num_layers(vllm_config.parallel_config),
|
||||||
|
},
|
||||||
|
"params": {n: list(p.shape) for n, p in model.named_parameters()},
|
||||||
|
"modules": module_attrs(model),
|
||||||
|
},
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
def main() -> None:
|
||||||
|
out, *args = sys.argv[1:]
|
||||||
|
trust_remote_code = "--trust-remote-code" in args
|
||||||
|
repos = [arg for arg in args if arg != "--trust-remote-code"]
|
||||||
|
with open(out, "w") as f:
|
||||||
|
for repo in repos:
|
||||||
|
try:
|
||||||
|
record = dump(repo, trust_remote_code)
|
||||||
|
except Exception as e:
|
||||||
|
error = f"{type(e).__name__}: {e}".splitlines()[0]
|
||||||
|
record = {"repo": repo, "error": error}
|
||||||
|
f.write(json.dumps(record, default=str, sort_keys=True) + "\n")
|
||||||
|
f.flush()
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
main()
|
||||||
@@ -0,0 +1,147 @@
|
|||||||
|
# SPDX-License-Identifier: Apache-2.0
|
||||||
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||||
|
"""List vendored vLLM code that the installed Transformers may make redundant.
|
||||||
|
|
||||||
|
Run with the Transformers version under test, from the vLLM repo root:
|
||||||
|
|
||||||
|
uv run --no-project --with transformers==<version> \
|
||||||
|
python .agents/skills/transformers-upgrade/scripts/find_upstreamed.py
|
||||||
|
|
||||||
|
Imports nothing from vLLM, so no vLLM install is needed. Uses the `gh` CLI, if
|
||||||
|
available, to check whether referenced Transformers PRs are in this release.
|
||||||
|
"""
|
||||||
|
|
||||||
|
import json
|
||||||
|
import subprocess
|
||||||
|
import sys
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
import regex as re
|
||||||
|
import transformers
|
||||||
|
from packaging.version import Version
|
||||||
|
from transformers.models.auto.configuration_auto import CONFIG_MAPPING_NAMES
|
||||||
|
from transformers.models.auto.processing_auto import PROCESSOR_MAPPING_NAMES
|
||||||
|
|
||||||
|
ROOT = Path(sys.argv[1] if len(sys.argv) > 1 else ".")
|
||||||
|
FLOOR = Version(transformers.__version__)
|
||||||
|
UPSTREAM_NAMES = set(dir(transformers))
|
||||||
|
|
||||||
|
MODEL_TYPE = re.compile(r'model_type\s*(?::\s*str\s*)?=\s*"([^"]+)"')
|
||||||
|
REGISTRY_KEY = re.compile(r'^\s+(?:\*\*\{)?"?([\w-]+)"?(?:=|": )"(\w+)"', re.M)
|
||||||
|
CLASS_KEY = re.compile(r'^\s+"(\w+)": ', re.M)
|
||||||
|
UPSTREAM_REF = re.compile(
|
||||||
|
r"huggingface/transformers(?:/(?:issues|pull)/|#)(\d+)"
|
||||||
|
r"|(?:once|until|when) [Tt]ransformers [\d.]+ is the minimum"
|
||||||
|
)
|
||||||
|
VERSIONED = re.compile(
|
||||||
|
r"(?:min_transformers_version|max_transformers_version|check_version|Version)"
|
||||||
|
r'\(?\s*=?\s*"([45]\.\d+(?:\.\d+)?)[^"]*"'
|
||||||
|
r"|[Tt]ransformers\s*(?:v|[<>]=?\s*)([45]\.\d+(?:\.\d+)?|4)\b"
|
||||||
|
)
|
||||||
|
READS_VERSION = re.compile(
|
||||||
|
r"transformers import __version__|transformers\.__version__"
|
||||||
|
r"|version\([\"']transformers[\"']\)|TRANSFORMERS_VERSION|check_version\("
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
def section(title: str) -> None:
|
||||||
|
print(f"\n## {title}")
|
||||||
|
|
||||||
|
|
||||||
|
def vendored_configs() -> None:
|
||||||
|
section(f"Vendored configs whose model_type is upstream in {FLOOR}")
|
||||||
|
files = sorted(ROOT.glob("vllm/transformers_utils/configs/*.py"))
|
||||||
|
files += sorted(ROOT.glob("vllm/models/*/config*.py"))
|
||||||
|
files += sorted(ROOT.glob("vllm/models/*/configs/*.py"))
|
||||||
|
for path in files:
|
||||||
|
types = sorted(set(MODEL_TYPE.findall(path.read_text())))
|
||||||
|
hits = [t for t in types if t in CONFIG_MAPPING_NAMES]
|
||||||
|
if hits:
|
||||||
|
upstream = ", ".join(f"{t} -> {CONFIG_MAPPING_NAMES[t]}" for t in hits)
|
||||||
|
print(f"- {path.relative_to(ROOT)}: {upstream}")
|
||||||
|
|
||||||
|
registry = (ROOT / "vllm/transformers_utils/config.py").read_text()
|
||||||
|
start = registry.index("_CONFIG_REGISTRY")
|
||||||
|
body = registry[start : registry.index("\n)\n", start)]
|
||||||
|
section("_CONFIG_REGISTRY entries that override an upstream model_type")
|
||||||
|
for model_type, cls in REGISTRY_KEY.findall(body):
|
||||||
|
if model_type in CONFIG_MAPPING_NAMES:
|
||||||
|
print(f"- {model_type}: vLLM {cls} over {CONFIG_MAPPING_NAMES[model_type]}")
|
||||||
|
|
||||||
|
|
||||||
|
def vendored_processors() -> None:
|
||||||
|
init = (ROOT / "vllm/transformers_utils/processors/__init__.py").read_text()
|
||||||
|
names = sorted(set(CLASS_KEY.findall(init)))
|
||||||
|
section("Registered processor names that collide with upstream classes")
|
||||||
|
for name in names:
|
||||||
|
if name in UPSTREAM_NAMES:
|
||||||
|
print(f"- {name}")
|
||||||
|
section("Processor files named after a model_type with an upstream processor")
|
||||||
|
for path in sorted(ROOT.glob("vllm/transformers_utils/processors/*.py")):
|
||||||
|
if path.stem in PROCESSOR_MAPPING_NAMES:
|
||||||
|
upstream = PROCESSOR_MAPPING_NAMES[path.stem]
|
||||||
|
print(f"- {path.relative_to(ROOT)} -> {upstream}")
|
||||||
|
|
||||||
|
|
||||||
|
def version_gates() -> None:
|
||||||
|
files = sorted([*ROOT.glob("vllm/**/*.py"), *ROOT.glob("tests/**/*.py")])
|
||||||
|
section(f"Version-gated code at or below {FLOOR} (review each)")
|
||||||
|
for path in files:
|
||||||
|
for lineno, line in enumerate(path.read_text().splitlines(), 1):
|
||||||
|
for match in VERSIONED.finditer(line):
|
||||||
|
version = Version(match.group(1) or match.group(2))
|
||||||
|
if version <= FLOOR:
|
||||||
|
print(f"- {path.relative_to(ROOT)}:{lineno}: {line.strip()}")
|
||||||
|
break
|
||||||
|
section("Code that reads the installed Transformers version (review each)")
|
||||||
|
for path in files:
|
||||||
|
for lineno, line in enumerate(path.read_text().splitlines(), 1):
|
||||||
|
if READS_VERSION.search(line):
|
||||||
|
print(f"- {path.relative_to(ROOT)}:{lineno}: {line.strip()}")
|
||||||
|
|
||||||
|
|
||||||
|
def upstream_status(number: str) -> str:
|
||||||
|
"""Whether Transformers issue/PR `number` is resolved in this release."""
|
||||||
|
|
||||||
|
def gh(path: str) -> dict | None:
|
||||||
|
try:
|
||||||
|
out = subprocess.run(["gh", "api", path], capture_output=True, text=True)
|
||||||
|
except FileNotFoundError:
|
||||||
|
return None
|
||||||
|
return json.loads(out.stdout) if out.returncode == 0 else None
|
||||||
|
|
||||||
|
repo = "repos/huggingface/transformers"
|
||||||
|
if (issue := gh(f"{repo}/issues/{number}")) is None:
|
||||||
|
return "status unknown"
|
||||||
|
if "pull_request" not in issue:
|
||||||
|
return f"issue {issue['state']}, check which PR fixed it"
|
||||||
|
pr = gh(f"{repo}/pulls/{number}")
|
||||||
|
if pr is None or not pr["merged_at"]:
|
||||||
|
return "PR not merged"
|
||||||
|
compare = gh(f"{repo}/compare/v{FLOOR}...{pr['merge_commit_sha']}")
|
||||||
|
included = compare and compare["status"] in ("behind", "identical")
|
||||||
|
return f"PR merged, {'in' if included else 'not in'} v{FLOOR}"
|
||||||
|
|
||||||
|
|
||||||
|
def upstream_refs() -> None:
|
||||||
|
section("Patches referencing Transformers issues/PRs or a future minimum")
|
||||||
|
files = sorted([*ROOT.glob("vllm/**/*.py"), *ROOT.glob("tests/**/*.py")])
|
||||||
|
statuses: dict[str, str] = {}
|
||||||
|
for path in files:
|
||||||
|
for lineno, line in enumerate(path.read_text().splitlines(), 1):
|
||||||
|
if (match := UPSTREAM_REF.search(line)) is None:
|
||||||
|
continue
|
||||||
|
note = ""
|
||||||
|
if number := match.group(1):
|
||||||
|
if number not in statuses:
|
||||||
|
statuses[number] = upstream_status(number)
|
||||||
|
note = f" [#{number}: {statuses[number]}]"
|
||||||
|
print(f"- {path.relative_to(ROOT)}:{lineno}:{note} {line.strip()}")
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
print(f"# Transformers {FLOOR}")
|
||||||
|
vendored_configs()
|
||||||
|
vendored_processors()
|
||||||
|
version_gates()
|
||||||
|
upstream_refs()
|
||||||
@@ -17,7 +17,6 @@ ALLOWED_UNSTABLE_LIBRARIES: tuple[str, ...] = (
|
|||||||
# _C_stable_libtorch, but these two modules still bind libtorch directly.
|
# _C_stable_libtorch, but these two modules still bind libtorch directly.
|
||||||
"_C.abi3.so",
|
"_C.abi3.so",
|
||||||
"_rocm_C.abi3.so",
|
"_rocm_C.abi3.so",
|
||||||
"third_party/deep_gemm/_C*.so",
|
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
@@ -56,7 +56,6 @@ steps:
|
|||||||
- "!vllm/distributed/device_communicators/shm_object_storage.py"
|
- "!vllm/distributed/device_communicators/shm_object_storage.py"
|
||||||
- "!vllm/distributed/device_communicators/symm_mem.py"
|
- "!vllm/distributed/device_communicators/symm_mem.py"
|
||||||
- "!vllm/distributed/device_communicators/mnnvl_compat.py"
|
- "!vllm/distributed/device_communicators/mnnvl_compat.py"
|
||||||
- "!vllm/distributed/device_communicators/ray_communicator.py"
|
|
||||||
- "!vllm/third_party/flashmla/"
|
- "!vllm/third_party/flashmla/"
|
||||||
- "!vllm/third_party/pynvml.py"
|
- "!vllm/third_party/pynvml.py"
|
||||||
- "!vllm/_custom_ops.py"
|
- "!vllm/_custom_ops.py"
|
||||||
|
|||||||
@@ -20,8 +20,10 @@ steps:
|
|||||||
- tests/kernels/moe/test_cpu_fused_moe.py
|
- tests/kernels/moe/test_cpu_fused_moe.py
|
||||||
- tests/kernels/moe/test_cpu_quant_fused_moe.py
|
- tests/kernels/moe/test_cpu_quant_fused_moe.py
|
||||||
- tests/kernels/moe/test_zen_cpu_int8_moe.py
|
- tests/kernels/moe/test_zen_cpu_int8_moe.py
|
||||||
|
- tests/test_zentorch_version_pin.py
|
||||||
- vllm/model_executor/layers/fused_moe/experts/cpu_moe.py
|
- vllm/model_executor/layers/fused_moe/experts/cpu_moe.py
|
||||||
- tests/kernels/test_onednn.py
|
- tests/kernels/test_onednn.py
|
||||||
|
- tests/kernels/test_cpu_fused_sampling.py
|
||||||
- tests/kernels/test_awq_int4_to_int8.py
|
- tests/kernels/test_awq_int4_to_int8.py
|
||||||
- tests/kernels/quantization/test_cpu_fp8_scaled_mm.py
|
- tests/kernels/quantization/test_cpu_fp8_scaled_mm.py
|
||||||
- tests/kernels/quantization/test_zen_da8w4.py
|
- tests/kernels/quantization/test_zen_da8w4.py
|
||||||
@@ -45,8 +47,10 @@ steps:
|
|||||||
tests/kernels/moe/test_cpu_fused_moe.py \
|
tests/kernels/moe/test_cpu_fused_moe.py \
|
||||||
tests/kernels/moe/test_cpu_quant_fused_moe.py \
|
tests/kernels/moe/test_cpu_quant_fused_moe.py \
|
||||||
tests/kernels/moe/test_zen_cpu_int8_moe.py \
|
tests/kernels/moe/test_zen_cpu_int8_moe.py \
|
||||||
|
tests/test_zentorch_version_pin.py \
|
||||||
tests/kernels/mamba/test_cpu_short_conv.py \
|
tests/kernels/mamba/test_cpu_short_conv.py \
|
||||||
tests/kernels/test_onednn.py \
|
tests/kernels/test_onednn.py \
|
||||||
|
tests/kernels/test_cpu_fused_sampling.py \
|
||||||
tests/kernels/test_awq_int4_to_int8.py \
|
tests/kernels/test_awq_int4_to_int8.py \
|
||||||
tests/kernels/quantization/test_cpu_fp8_scaled_mm.py \
|
tests/kernels/quantization/test_cpu_fp8_scaled_mm.py \
|
||||||
tests/kernels/quantization/test_zen_da8w4.py \
|
tests/kernels/quantization/test_zen_da8w4.py \
|
||||||
@@ -85,7 +89,7 @@ steps:
|
|||||||
- |
|
- |
|
||||||
bash .buildkite/scripts/hardware_ci/run-cpu-test.sh 30m "
|
bash .buildkite/scripts/hardware_ci/run-cpu-test.sh 30m "
|
||||||
pytest -x -v -s \
|
pytest -x -v -s \
|
||||||
tests/v1/worker/test_gpu_autoregressive_speculator.py \
|
tests/v1/worker/test_gpu_target_dependent_ar_speculator.py \
|
||||||
tests/v1/worker/test_gpu_extract_hidden_states_speculator.py \
|
tests/v1/worker/test_gpu_extract_hidden_states_speculator.py \
|
||||||
tests/v1/worker/test_gpu_batch_ordering.py \
|
tests/v1/worker/test_gpu_batch_ordering.py \
|
||||||
tests/v1/worker/test_gpu_rejection_sampler_chunking.py \
|
tests/v1/worker/test_gpu_rejection_sampler_chunking.py \
|
||||||
@@ -228,3 +232,57 @@ steps:
|
|||||||
"$$BUILDKITE_PARALLEL_JOB"
|
"$$BUILDKITE_PARALLEL_JOB"
|
||||||
"$REGISTRY/$REPO:$BUILDKITE_COMMIT-arm64-cpu"
|
"$REGISTRY/$REPO:$BUILDKITE_COMMIT-arm64-cpu"
|
||||||
parallelism: 3
|
parallelism: 3
|
||||||
|
|
||||||
|
- label: ":docker: Build Zen CPU image"
|
||||||
|
key: zen-cpu-image-build
|
||||||
|
# Reuse the shared `<repo>:<commit>-cpu` image that image-build-cpu publishes
|
||||||
|
# to public ECR, so Dockerfile.zen just layers on top instead of recompiling
|
||||||
|
# vLLM from source. If the pull fails, the build script still falls back to
|
||||||
|
# building the CPU base from source.
|
||||||
|
depends_on:
|
||||||
|
- image-build-cpu
|
||||||
|
soft_fail: true
|
||||||
|
agents:
|
||||||
|
queue: amd-cpu
|
||||||
|
source_file_dependencies:
|
||||||
|
- .buildkite/hardware_tests/cpu.yaml
|
||||||
|
- .buildkite/image_build/image_build_zen_cpu.sh
|
||||||
|
- docker/Dockerfile.zen
|
||||||
|
- docker/Dockerfile.cpu
|
||||||
|
- requirements/cpu.txt
|
||||||
|
- requirements/build/cpu.txt
|
||||||
|
- requirements/test/cpu.txt
|
||||||
|
- cmake/cpu_extension.cmake
|
||||||
|
- vllm/model_executor/layers/utils.py
|
||||||
|
- vllm/model_executor/kernels/linear/zentorch_utils.py
|
||||||
|
- vllm/model_executor/kernels/linear/scaled_mm/zentorch.py
|
||||||
|
- vllm/model_executor/kernels/linear/mixed_precision/zentorch.py
|
||||||
|
- vllm/platforms/cpu.py
|
||||||
|
- vllm/platforms/zen_cpu.py
|
||||||
|
- vllm/platforms/__init__.py
|
||||||
|
- tests/model_executor/test_cpu_unquantized_gemm_dispatch.py
|
||||||
|
- tests/test_zen_cpu_platform_detection.py
|
||||||
|
- tests/kernels/moe/test_zen_cpu_fused_moe.py
|
||||||
|
- tests/kernels/moe/test_zen_cpu_int8_moe.py
|
||||||
|
- vllm/v1/attention/backends/zentorch_sdpa.py
|
||||||
|
- tests/test_zentorch_version_pin.py
|
||||||
|
- vllm/v1/attention/backends/mla/prefill/zen_cpu_sdpa.py
|
||||||
|
- vllm/model_executor/layers/fused_moe/experts/zentorch_moe.py
|
||||||
|
- tests/kernels/quantization/test_zen_da8w4.py
|
||||||
|
commands:
|
||||||
|
- .buildkite/image_build/image_build_zen_cpu.sh "$REGISTRY" "$REPO" "$BUILDKITE_COMMIT"
|
||||||
|
env:
|
||||||
|
DOCKER_BUILDKIT: "1"
|
||||||
|
# Install zentorch directly (if-branch in Dockerfile.zen) instead of
|
||||||
|
# `uv pip install "vllm[zen]"`, which forces uv to re-resolve vLLM's full
|
||||||
|
# dependency closure and chokes on its transitive triton-cpu URL dependency.
|
||||||
|
# Keep this pin in sync with the `zen` extra in setup.py.
|
||||||
|
ZENTORCH_VERSION: "2.14.0.1"
|
||||||
|
retry:
|
||||||
|
automatic:
|
||||||
|
- exit_status: 1 # Transient Docker/BuildKit failure
|
||||||
|
limit: 1
|
||||||
|
- exit_status: -1 # Agent was lost
|
||||||
|
limit: 2
|
||||||
|
- exit_status: -10 # Agent was lost
|
||||||
|
limit: 2
|
||||||
|
|||||||
@@ -2,10 +2,15 @@ group: Hardware
|
|||||||
steps:
|
steps:
|
||||||
- label: "GH200 Test"
|
- label: "GH200 Test"
|
||||||
key: gh200-test
|
key: gh200-test
|
||||||
|
timeout_in_minutes: 30
|
||||||
soft_fail: true
|
soft_fail: true
|
||||||
device: gh200
|
device: gh200
|
||||||
no_plugin: true
|
|
||||||
optional: true
|
optional: true
|
||||||
|
working_dir: "/vllm-workspace"
|
||||||
|
depends_on:
|
||||||
|
- arm64-image-build
|
||||||
|
env:
|
||||||
|
VLLM_WORKER_MULTIPROC_METHOD: "spawn"
|
||||||
commands:
|
commands:
|
||||||
- nvidia-smi
|
- nvidia-smi
|
||||||
- bash .buildkite/scripts/hardware_ci/run-gh200-test.sh
|
- python3 examples/basic/offline_inference/generate.py --model meta-llama/Llama-3.2-1B
|
||||||
|
|||||||
@@ -15,7 +15,7 @@ steps:
|
|||||||
limit: 2
|
limit: 2
|
||||||
- exit_status: -10 # Agent was lost
|
- exit_status: -10 # Agent was lost
|
||||||
limit: 2
|
limit: 2
|
||||||
- label: "XPU example Test"
|
- label: ":intel: (BMG) Example Test"
|
||||||
key: xpu-example-test
|
key: xpu-example-test
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-xpu
|
- image-build-xpu
|
||||||
@@ -37,7 +37,7 @@ steps:
|
|||||||
- >-
|
- >-
|
||||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
'bash .buildkite/scripts/hardware_ci/run-intel-ci-test.sh example'
|
'bash .buildkite/scripts/hardware_ci/run-intel-ci-test.sh example'
|
||||||
- label: "XPU V1 test"
|
- label: ":intel: (BMG) V1 test"
|
||||||
key: xpu-v1-test
|
key: xpu-v1-test
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-xpu
|
- image-build-xpu
|
||||||
@@ -60,7 +60,7 @@ steps:
|
|||||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
'bash .buildkite/scripts/hardware_ci/run-intel-ci-test.sh v1'
|
'bash .buildkite/scripts/hardware_ci/run-intel-ci-test.sh v1'
|
||||||
parallelism: 2
|
parallelism: 2
|
||||||
- label: "XPU W8A8 FP8 Linear Examples"
|
- label: ":intel: (BMG) W8A8 FP8 Linear Examples"
|
||||||
key: xpu-w8a8-fp8-linear-examples
|
key: xpu-w8a8-fp8-linear-examples
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-xpu
|
- image-build-xpu
|
||||||
@@ -83,7 +83,7 @@ steps:
|
|||||||
- >-
|
- >-
|
||||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
'bash .buildkite/scripts/hardware_ci/run-intel-ci-test.sh w8a8-fp8-linear'
|
'bash .buildkite/scripts/hardware_ci/run-intel-ci-test.sh w8a8-fp8-linear'
|
||||||
- label: "XPU server test"
|
- label: ":intel: (BMG) Server test"
|
||||||
key: xpu-server-test
|
key: xpu-server-test
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-xpu
|
- image-build-xpu
|
||||||
@@ -105,7 +105,7 @@ steps:
|
|||||||
- >-
|
- >-
|
||||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
'bash .buildkite/scripts/hardware_ci/run-intel-ci-test.sh server'
|
'bash .buildkite/scripts/hardware_ci/run-intel-ci-test.sh server'
|
||||||
- label: "XPU quantization test"
|
- label: ":intel: (BMG) Quantization test"
|
||||||
key: xpu-quantization-test
|
key: xpu-quantization-test
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-xpu
|
- image-build-xpu
|
||||||
@@ -127,7 +127,7 @@ steps:
|
|||||||
- >-
|
- >-
|
||||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
'bash .buildkite/scripts/hardware_ci/run-intel-ci-test.sh quantization'
|
'bash .buildkite/scripts/hardware_ci/run-intel-ci-test.sh quantization'
|
||||||
- label: "XPU compressed tensors FP8 test"
|
- label: ":intel: (BMG) Compressed tensors FP8 test"
|
||||||
key: xpu-compressed-tensors-fp8-test
|
key: xpu-compressed-tensors-fp8-test
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-xpu
|
- image-build-xpu
|
||||||
@@ -150,7 +150,7 @@ steps:
|
|||||||
- >-
|
- >-
|
||||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
'bash .buildkite/scripts/hardware_ci/run-intel-ci-test.sh compressed-tensors-fp8'
|
'bash .buildkite/scripts/hardware_ci/run-intel-ci-test.sh compressed-tensors-fp8'
|
||||||
- label: "XPU Graph"
|
- label: ":intel: (BMG) Graph"
|
||||||
key: xpu-graph
|
key: xpu-graph
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-xpu
|
- image-build-xpu
|
||||||
|
|||||||
@@ -61,6 +61,8 @@ NIGHTLY_UBUNTU_VERSION="24.04"
|
|||||||
NIGHTLY_FINAL_BASE_IMAGE="nvidia/cuda:${NIGHTLY_CUDA_VERSION}-base-ubuntu${NIGHTLY_UBUNTU_VERSION}"
|
NIGHTLY_FINAL_BASE_IMAGE="nvidia/cuda:${NIGHTLY_CUDA_VERSION}-base-ubuntu${NIGHTLY_UBUNTU_VERSION}"
|
||||||
|
|
||||||
echo "--- :docker: Building torch nightly image (CUDA ${NIGHTLY_CUDA_VERSION})"
|
echo "--- :docker: Building torch nightly image (CUDA ${NIGHTLY_CUDA_VERSION})"
|
||||||
|
# Provenance labels match the bake `_labels` target in docker/docker-bake.hcl;
|
||||||
|
# the initialized-snapshot E2E refuses images whose commit labels differ.
|
||||||
docker buildx build --file docker/Dockerfile \
|
docker buildx build --file docker/Dockerfile \
|
||||||
--build-arg max_jobs=16 \
|
--build-arg max_jobs=16 \
|
||||||
--build-arg buildkite_commit="$BUILDKITE_COMMIT" \
|
--build-arg buildkite_commit="$BUILDKITE_COMMIT" \
|
||||||
@@ -70,6 +72,10 @@ docker buildx build --file docker/Dockerfile \
|
|||||||
--build-arg BUILD_BASE_IMAGE="${NIGHTLY_BUILD_BASE_IMAGE}" \
|
--build-arg BUILD_BASE_IMAGE="${NIGHTLY_BUILD_BASE_IMAGE}" \
|
||||||
--build-arg FINAL_BASE_IMAGE="${NIGHTLY_FINAL_BASE_IMAGE}" \
|
--build-arg FINAL_BASE_IMAGE="${NIGHTLY_FINAL_BASE_IMAGE}" \
|
||||||
--build-arg torch_cuda_arch_list="8.0 8.9 9.0 10.0 12.0" \
|
--build-arg torch_cuda_arch_list="8.0 8.9 9.0 10.0 12.0" \
|
||||||
|
--label "org.opencontainers.image.revision=${BUILDKITE_COMMIT}" \
|
||||||
|
--label "ai.vllm.build.commit=${BUILDKITE_COMMIT}" \
|
||||||
|
--label "ai.vllm.build.pipeline=${BUILDKITE_PIPELINE_SLUG:-local}" \
|
||||||
|
--label "ai.vllm.build.url=${BUILDKITE_BUILD_URL:-}" \
|
||||||
--tag "$IMAGE_TAG" \
|
--tag "$IMAGE_TAG" \
|
||||||
--push \
|
--push \
|
||||||
--target test \
|
--target test \
|
||||||
|
|||||||
+75
@@ -0,0 +1,75 @@
|
|||||||
|
#!/bin/bash
|
||||||
|
# SPDX-License-Identifier: Apache-2.0
|
||||||
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||||
|
#
|
||||||
|
# Build the AMD Zen CPU image (vLLM + zentorch) by layering docker/Dockerfile.zen
|
||||||
|
# on top of a CPU base image that already has vLLM installed.
|
||||||
|
#
|
||||||
|
# To avoid recompiling vLLM from source, prefer reusing the shared CPU image that
|
||||||
|
# the image-build-cpu step already builds and publishes for this commit
|
||||||
|
# (`<repo>:<commit>-cpu`). It lives in public ECR, which allows anonymous pulls,
|
||||||
|
# so no registry credentials are required. If the pull fails (e.g. the image
|
||||||
|
# isn't published yet), fall back to building the base from docker/Dockerfile.cpu.
|
||||||
|
#
|
||||||
|
# The zen image is not pushed to a registry.
|
||||||
|
#
|
||||||
|
# See docker/Dockerfile.zen for the build workflow this mirrors.
|
||||||
|
set -euo pipefail
|
||||||
|
|
||||||
|
if [[ $# -lt 3 ]]; then
|
||||||
|
echo "Usage: $0 <registry> <repo> <commit>"
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
|
||||||
|
REGISTRY=$1
|
||||||
|
REPO=$2
|
||||||
|
BUILDKITE_COMMIT=$3
|
||||||
|
|
||||||
|
image_repo() {
|
||||||
|
if [[ -n "${REGISTRY}" ]]; then
|
||||||
|
printf '%s/%s' "${REGISTRY}" "${REPO}"
|
||||||
|
else
|
||||||
|
printf '%s' "${REPO}"
|
||||||
|
fi
|
||||||
|
}
|
||||||
|
|
||||||
|
IMAGE_REPO="$(image_repo)"
|
||||||
|
|
||||||
|
# The shared CPU image published by image-build-cpu (public ECR, anonymous pull).
|
||||||
|
SHARED_CPU_IMAGE=""
|
||||||
|
if [[ -n "${REGISTRY}" ]]; then
|
||||||
|
SHARED_CPU_IMAGE="$REGISTRY/$REPO:$BUILDKITE_COMMIT-cpu"
|
||||||
|
fi
|
||||||
|
FALLBACK_BASE_IMAGE="zen-cpu-base:$BUILDKITE_COMMIT"
|
||||||
|
IMAGE="$IMAGE_REPO:$BUILDKITE_COMMIT-zen-cpu"
|
||||||
|
|
||||||
|
# ZENTORCH_VERSION is optional; when unset the Dockerfile falls back to
|
||||||
|
# installing zentorch via `vllm[zen]`.
|
||||||
|
ZENTORCH_VERSION=${ZENTORCH_VERSION:-}
|
||||||
|
|
||||||
|
# Step 1: obtain the CPU base image that Dockerfile.zen layers on. Prefer pulling
|
||||||
|
# the published `-cpu` image; fall back to building it from source if unavailable.
|
||||||
|
if [[ -n "${SHARED_CPU_IMAGE}" ]] && docker pull "$SHARED_CPU_IMAGE"; then
|
||||||
|
echo "--- :docker: Using published CPU image as base: $SHARED_CPU_IMAGE"
|
||||||
|
BASE_IMAGE="$SHARED_CPU_IMAGE"
|
||||||
|
else
|
||||||
|
echo "--- :docker: Published CPU image unavailable; building base from source"
|
||||||
|
docker build --file docker/Dockerfile.cpu \
|
||||||
|
--platform linux/amd64 \
|
||||||
|
--build-arg buildkite_commit="$BUILDKITE_COMMIT" \
|
||||||
|
--build-arg VLLM_CPU_X86=true \
|
||||||
|
--tag "$FALLBACK_BASE_IMAGE" \
|
||||||
|
--target vllm-openai \
|
||||||
|
--progress plain .
|
||||||
|
BASE_IMAGE="$FALLBACK_BASE_IMAGE"
|
||||||
|
fi
|
||||||
|
|
||||||
|
# Step 2: build the zen test image on top of the CPU base.
|
||||||
|
echo "--- :docker: Building Zen test image"
|
||||||
|
docker build --file docker/Dockerfile.zen \
|
||||||
|
--platform linux/amd64 \
|
||||||
|
--build-arg BASE_IMAGE="$BASE_IMAGE" \
|
||||||
|
${ZENTORCH_VERSION:+--build-arg ZENTORCH_VERSION="$ZENTORCH_VERSION"} \
|
||||||
|
--tag "$IMAGE" \
|
||||||
|
--target vllm-zen-test \
|
||||||
|
--progress plain .
|
||||||
@@ -1,8 +1,8 @@
|
|||||||
group: Basic Correctness
|
group: Basic Correctness Intel
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-xpu
|
- image-build-xpu
|
||||||
steps:
|
steps:
|
||||||
- label: XPU Sleep Mode
|
- label: ":intel: (BMG) Sleep Mode"
|
||||||
key: xpu-sleep-mode
|
key: xpu-sleep-mode
|
||||||
timeout_in_minutes: 45
|
timeout_in_minutes: 45
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
|
|||||||
@@ -1,8 +1,8 @@
|
|||||||
group: Benchmarks
|
group: Benchmarks Intel
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-xpu
|
- image-build-xpu
|
||||||
steps:
|
steps:
|
||||||
- label: Benchmarks CLI Test
|
- label: ":intel: (BMG) Benchmarks CLI"
|
||||||
key: benchmarks-cli-test
|
key: benchmarks-cli-test
|
||||||
timeout_in_minutes: 40
|
timeout_in_minutes: 40
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
|
|||||||
@@ -0,0 +1,33 @@
|
|||||||
|
group: Distributed Intel
|
||||||
|
depends_on:
|
||||||
|
- image-build-xpu
|
||||||
|
steps:
|
||||||
|
- label: ":intel: (BMG) Distributed Torchrun + Shutdown"
|
||||||
|
key: distributed-torchrun-shutdown-tests-2-gpus
|
||||||
|
timeout_in_minutes: 50
|
||||||
|
device: intel_gpu
|
||||||
|
agent_tags:
|
||||||
|
label: production
|
||||||
|
gpu: 2+
|
||||||
|
mem: 24+
|
||||||
|
no_plugin: true
|
||||||
|
working_dir: "."
|
||||||
|
env:
|
||||||
|
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||||
|
REPO: "vllm-ci-test-repo"
|
||||||
|
VLLM_TEST_DEVICE: "xpu"
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/distributed/
|
||||||
|
- "!vllm/distributed/kv_transfer/"
|
||||||
|
- vllm/engine/
|
||||||
|
- vllm/executor/
|
||||||
|
- vllm/worker/worker_base.py
|
||||||
|
- vllm/v1/engine/
|
||||||
|
- vllm/v1/worker/
|
||||||
|
- tests/distributed/
|
||||||
|
- tests/v1/shutdown
|
||||||
|
- tests/v1/worker/test_worker_memory_snapshot.py
|
||||||
|
commands:
|
||||||
|
- >-
|
||||||
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
|
'cd tests && pytest -v -s v1/shutdown'
|
||||||
@@ -2,7 +2,7 @@ group: Engine Intel
|
|||||||
depends_on:
|
depends_on:
|
||||||
- image-build-xpu
|
- image-build-xpu
|
||||||
steps:
|
steps:
|
||||||
- label: Engine
|
- label: ":intel: (BMG) Engine"
|
||||||
key: engine
|
key: engine
|
||||||
timeout_in_minutes: 40
|
timeout_in_minutes: 40
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
@@ -40,7 +40,7 @@ steps:
|
|||||||
'cd tests &&
|
'cd tests &&
|
||||||
pytest -v -s engine/test_arg_utils.py test_sequence.py test_logger.py test_vllm_port.py jit_monitor/test_hooks.py'
|
pytest -v -s engine/test_arg_utils.py test_sequence.py test_logger.py test_vllm_port.py jit_monitor/test_hooks.py'
|
||||||
|
|
||||||
- label: Engine (1 GPU)
|
- label: ":intel: (BMG) Engine (1 GPU)"
|
||||||
key: engine-1-gpu
|
key: engine-1-gpu
|
||||||
timeout_in_minutes: 30
|
timeout_in_minutes: 30
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
@@ -65,7 +65,7 @@ steps:
|
|||||||
pytest -v -s v1/engine --ignore v1/engine/test_preprocess_error_handling.py --ignore v1/engine/test_core_engine_actor_manager.py &&
|
pytest -v -s v1/engine --ignore v1/engine/test_preprocess_error_handling.py --ignore v1/engine/test_core_engine_actor_manager.py &&
|
||||||
pytest -v -s test_config.py'
|
pytest -v -s test_config.py'
|
||||||
|
|
||||||
- label: V1 e2e (2 GPUs)
|
- label: ":intel: (BMG) V1 e2e (2 GPUs)"
|
||||||
key: v1-e2e-2-gpus
|
key: v1-e2e-2-gpus
|
||||||
timeout_in_minutes: 30
|
timeout_in_minutes: 30
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
|
|||||||
@@ -1,4 +1,4 @@
|
|||||||
group: Entrypoints
|
group: Entrypoints Intel
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-xpu
|
- image-build-xpu
|
||||||
steps:
|
steps:
|
||||||
@@ -19,14 +19,14 @@ steps:
|
|||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- vllm/entrypoints
|
- vllm/entrypoints
|
||||||
- tests/entrypoints/unit_tests
|
- tests/entrypoints/unit_tests
|
||||||
- tests/entrypoints/weight_transfer
|
- tests/entrypoints/rl/weight_transfer
|
||||||
- tests/entrypoints/launchers
|
- tests/entrypoints/launchers
|
||||||
commands:
|
commands:
|
||||||
- >-
|
- >-
|
||||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
'cd tests &&
|
'cd tests &&
|
||||||
pytest -v -s entrypoints/unit_tests &&
|
pytest -v -s entrypoints/unit_tests &&
|
||||||
pytest -v -s entrypoints/weight_transfer'
|
pytest -v -s entrypoints/rl/weight_transfer'
|
||||||
|
|
||||||
- label: ":intel: (BMG) Entrypoints Integration (LLM)"
|
- label: ":intel: (BMG) Entrypoints Integration (LLM)"
|
||||||
key: entrypoints-integration-llm-intel
|
key: entrypoints-integration-llm-intel
|
||||||
@@ -71,14 +71,17 @@ steps:
|
|||||||
- vllm/
|
- vllm/
|
||||||
- "!vllm/distributed/kv_transfer/"
|
- "!vllm/distributed/kv_transfer/"
|
||||||
- tests/entrypoints/serve
|
- tests/entrypoints/serve
|
||||||
|
- tests/entrypoints/rl
|
||||||
commands:
|
commands:
|
||||||
- >-
|
- >-
|
||||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
'export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
|
'export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
|
||||||
cd tests &&
|
cd tests &&
|
||||||
pytest -v -s entrypoints/serve --ignore=entrypoints/serve/dev/rpc
|
pytest -v -s entrypoints/serve --ignore=entrypoints/serve/dev/rpc &&
|
||||||
--ignore=entrypoints/serve/dev/rlhf/test_weight_operation_metrics.py
|
pytest -v -s entrypoints/rl --ignore=entrypoints/rl/weight_transfer
|
||||||
--deselect="tests/entrypoints/serve/dev/rlhf/state_transitions/test_pause_resume.py::TestPauseResume::test_clear_cache_preserves_output_and_controls_prefix_cache[MRV1]" &&
|
--ignore=entrypoints/rl/return_routed_experts/test_openai_api.py
|
||||||
|
--ignore=entrypoints/rl/weight_transfer_metrics
|
||||||
|
--deselect="tests/entrypoints/rl/state_transitions/test_pause_resume.py::TestPauseResume::test_clear_cache_preserves_output_and_controls_prefix_cache[MRV1]" &&
|
||||||
PYTHONPATH=/workspace/vllm pytest -v -s entrypoints/serve/dev/rpc'
|
PYTHONPATH=/workspace/vllm pytest -v -s entrypoints/serve/dev/rpc'
|
||||||
|
|
||||||
- label: ":intel: (BMG) Entrypoints Integration (API Server Scale Out)"
|
- label: ":intel: (BMG) Entrypoints Integration (API Server Scale Out)"
|
||||||
|
|||||||
@@ -1,8 +1,8 @@
|
|||||||
group: Expert Parallelism
|
group: Expert Parallelism Intel
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-xpu
|
- image-build-xpu
|
||||||
steps:
|
steps:
|
||||||
- label: EPLB Algorithm
|
- label: ":intel: (BMG) EPLB Algorithm"
|
||||||
key: eplb-algorithm
|
key: eplb-algorithm
|
||||||
timeout_in_minutes: 45
|
timeout_in_minutes: 45
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
|
|||||||
@@ -2,7 +2,7 @@ group: Kernels Intel
|
|||||||
depends_on:
|
depends_on:
|
||||||
- image-build-xpu
|
- image-build-xpu
|
||||||
steps:
|
steps:
|
||||||
- label: vLLM IR Tests
|
- label: ":intel: (BMG) vLLM IR Tests"
|
||||||
key: vllm-ir-tests
|
key: vllm-ir-tests
|
||||||
timeout_in_minutes: 30
|
timeout_in_minutes: 30
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
@@ -26,7 +26,7 @@ steps:
|
|||||||
pytest -v -s ir &&
|
pytest -v -s ir &&
|
||||||
pytest -v -s kernels/ir'
|
pytest -v -s kernels/ir'
|
||||||
|
|
||||||
- label: UVA Kernel Tests
|
- label: ":intel: (BMG) UVA Kernel Tests"
|
||||||
key: uva-kernel-tests
|
key: uva-kernel-tests
|
||||||
timeout_in_minutes: 20
|
timeout_in_minutes: 20
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
|
|||||||
@@ -1,8 +1,8 @@
|
|||||||
group: LM Eval
|
group: LM Eval Intel
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-xpu
|
- image-build-xpu
|
||||||
steps:
|
steps:
|
||||||
- label: "XPU GPQA Eval (GPT-OSS)"
|
- label: ":intel: (BMG) GPQA Eval (GPT-OSS)"
|
||||||
key: xpu-gpqa-eval-gpt-oss
|
key: xpu-gpqa-eval-gpt-oss
|
||||||
timeout_in_minutes: 60
|
timeout_in_minutes: 60
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
@@ -25,7 +25,7 @@ steps:
|
|||||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
'cd tests &&
|
'cd tests &&
|
||||||
pytest -s -v evals/gpt_oss/test_gpqa_correctness.py --config-list-file=configs/models-xpu.txt'
|
pytest -s -v evals/gpt_oss/test_gpqa_correctness.py --config-list-file=configs/models-xpu.txt'
|
||||||
- label: LM Eval Large Models(2 GPUs)
|
- label: ":intel: (BMG) LM Eval Large Models(2 GPUs)"
|
||||||
key: lm-eval-large-models-2-gpus
|
key: lm-eval-large-models-2-gpus
|
||||||
timeout_in_minutes: 45
|
timeout_in_minutes: 45
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
|
|||||||
@@ -2,14 +2,14 @@ group: LoRA Intel
|
|||||||
depends_on:
|
depends_on:
|
||||||
- image-build-xpu
|
- image-build-xpu
|
||||||
steps:
|
steps:
|
||||||
- label: LoRA Runtime + Utils
|
- label: ":intel: (BMG) LoRA Runtime + Utils"
|
||||||
key: lora-runtime-utils
|
key: lora-runtime-utils
|
||||||
timeout_in_minutes: 45
|
timeout_in_minutes: 45
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
agent_tags:
|
agent_tags:
|
||||||
label: production
|
label: production
|
||||||
gpu: 1+
|
gpu: 1+
|
||||||
mem: 24+
|
mem: 16+
|
||||||
no_plugin: true
|
no_plugin: true
|
||||||
working_dir: "."
|
working_dir: "."
|
||||||
env:
|
env:
|
||||||
@@ -33,10 +33,9 @@ steps:
|
|||||||
pytest -v -s lora/test_peft_helper.py &&
|
pytest -v -s lora/test_peft_helper.py &&
|
||||||
pytest -v -s lora/test_resolver.py &&
|
pytest -v -s lora/test_resolver.py &&
|
||||||
pytest -v -s lora/test_utils.py &&
|
pytest -v -s lora/test_utils.py &&
|
||||||
pytest -v -s lora/test_add_lora.py &&
|
|
||||||
pytest -v -s lora/test_worker.py'
|
pytest -v -s lora/test_worker.py'
|
||||||
|
|
||||||
- label: LoRA Fused/MoE Kernels
|
- label: ":intel: (BMG) LoRA Fused/MoE Kernels"
|
||||||
key: lora-fused-moe-kernels
|
key: lora-fused-moe-kernels
|
||||||
timeout_in_minutes: 45
|
timeout_in_minutes: 45
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
@@ -61,7 +60,7 @@ steps:
|
|||||||
pytest -v -s lora/test_fused_moe_lora_kernel.py &&
|
pytest -v -s lora/test_fused_moe_lora_kernel.py &&
|
||||||
pytest -v -s lora/test_moe_lora_align_sum.py --deselect="tests/lora/test_moe_lora_align_sum.py::test_moe_lora_align_block_size_mixed_base_and_lora[1]"'
|
pytest -v -s lora/test_moe_lora_align_sum.py --deselect="tests/lora/test_moe_lora_align_sum.py::test_moe_lora_align_block_size_mixed_base_and_lora[1]"'
|
||||||
|
|
||||||
- label: LoRA Punica Kernels
|
- label: ":intel: (BMG) LoRA Punica Kernels"
|
||||||
key: lora-punica-kernels
|
key: lora-punica-kernels
|
||||||
timeout_in_minutes: 45
|
timeout_in_minutes: 45
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
@@ -88,7 +87,7 @@ steps:
|
|||||||
pytest -v -s lora/test_punica_ops.py::test_kernels_hidden_size &&
|
pytest -v -s lora/test_punica_ops.py::test_kernels_hidden_size &&
|
||||||
pytest -v -s lora/test_punica_ops.py::test_add_lora_fused_moe_early_exit'
|
pytest -v -s lora/test_punica_ops.py::test_add_lora_fused_moe_early_exit'
|
||||||
|
|
||||||
- label: LoRA Punica FP8/XPU Ops
|
- label: ":intel: (BMG) LoRA Punica FP8/XPU Ops"
|
||||||
key: lora-punica-fp8-xpu-ops
|
key: lora-punica-fp8-xpu-ops
|
||||||
timeout_in_minutes: 60
|
timeout_in_minutes: 60
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
@@ -113,10 +112,61 @@ steps:
|
|||||||
pytest -v -s lora/test_punica_ops_fp8.py &&
|
pytest -v -s lora/test_punica_ops_fp8.py &&
|
||||||
pytest -v -s lora/test_punica_xpu_ops.py'
|
pytest -v -s lora/test_punica_xpu_ops.py'
|
||||||
|
|
||||||
- label: LoRA Models
|
- label: ":intel: (BMG) LoRA Models"
|
||||||
key: lora-models
|
key: lora-models
|
||||||
timeout_in_minutes: 45
|
timeout_in_minutes: 45
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
|
agent_tags:
|
||||||
|
label: production
|
||||||
|
gpu: 2+
|
||||||
|
mem: 16+
|
||||||
|
no_plugin: true
|
||||||
|
working_dir: "."
|
||||||
|
env:
|
||||||
|
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||||
|
REPO: "vllm-ci-test-repo"
|
||||||
|
VLLM_TEST_DEVICE: "xpu"
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/lora
|
||||||
|
- tests/lora
|
||||||
|
commands:
|
||||||
|
- >-
|
||||||
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
|
'cd tests &&
|
||||||
|
export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
|
||||||
|
pytest -v -s lora/test_quant_model.py --deselect="tests/lora/test_quant_model.py::test_quant_model_lora[model0]" --deselect="tests/lora/test_quant_model.py::test_quant_model_lora[model1]" --deselect="tests/lora/test_quant_model.py::test_quant_model_tp_equality[model0]" &&
|
||||||
|
pytest -v -s lora/test_transformers_model.py &&
|
||||||
|
pytest -v -s lora/test_chatglm3_tp.py &&
|
||||||
|
pytest -v -s lora/test_llama_tp.py::test_llama_lora'
|
||||||
|
|
||||||
|
- label: ":intel: (BMG) LoRA Multimodal"
|
||||||
|
key: lora-multimodal
|
||||||
|
timeout_in_minutes: 45
|
||||||
|
device: intel_gpu
|
||||||
|
agent_tags:
|
||||||
|
label: production
|
||||||
|
gpu: 1+
|
||||||
|
mem: 16+
|
||||||
|
no_plugin: true
|
||||||
|
working_dir: "."
|
||||||
|
env:
|
||||||
|
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||||
|
REPO: "vllm-ci-test-repo"
|
||||||
|
VLLM_TEST_DEVICE: "xpu"
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/lora
|
||||||
|
- tests/lora
|
||||||
|
commands:
|
||||||
|
- >-
|
||||||
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
|
'cd tests &&
|
||||||
|
export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
|
||||||
|
pytest -v -s lora/test_whisper.py'
|
||||||
|
|
||||||
|
- label: ":intel: (BMG) LoRA Add + Multimodal"
|
||||||
|
key: lora-add-multimodal
|
||||||
|
timeout_in_minutes: 45
|
||||||
|
device: intel_gpu
|
||||||
agent_tags:
|
agent_tags:
|
||||||
label: production
|
label: production
|
||||||
gpu: 2+
|
gpu: 2+
|
||||||
@@ -135,33 +185,6 @@ steps:
|
|||||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
'cd tests &&
|
'cd tests &&
|
||||||
export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
|
export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
|
||||||
pytest -v -s lora/test_quant_model.py --deselect="tests/lora/test_quant_model.py::test_quant_model_lora[model0]" --deselect="tests/lora/test_quant_model.py::test_quant_model_lora[model1]" --deselect="tests/lora/test_quant_model.py::test_quant_model_tp_equality[model0]" &&
|
pytest -v -s lora/test_add_lora.py &&
|
||||||
pytest -v -s lora/test_transformers_model.py &&
|
|
||||||
pytest -v -s lora/test_chatglm3_tp.py &&
|
|
||||||
pytest -v -s lora/test_llama_tp.py::test_llama_lora &&
|
|
||||||
pytest -s -v lora/test_minicpmv_tp.py'
|
|
||||||
|
|
||||||
- label: LoRA Multimodal
|
|
||||||
key: lora-multimodal
|
|
||||||
timeout_in_minutes: 45
|
|
||||||
device: intel_gpu
|
|
||||||
agent_tags:
|
|
||||||
label: production
|
|
||||||
gpu: 1+
|
|
||||||
mem: 24+
|
|
||||||
no_plugin: true
|
|
||||||
working_dir: "."
|
|
||||||
env:
|
|
||||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
|
||||||
REPO: "vllm-ci-test-repo"
|
|
||||||
VLLM_TEST_DEVICE: "xpu"
|
|
||||||
source_file_dependencies:
|
|
||||||
- vllm/lora
|
|
||||||
- tests/lora
|
|
||||||
commands:
|
|
||||||
- >-
|
|
||||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
|
||||||
'cd tests &&
|
|
||||||
export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
|
|
||||||
pytest -v -s lora/test_default_mm_loras.py &&
|
pytest -v -s lora/test_default_mm_loras.py &&
|
||||||
pytest -v -s lora/test_whisper.py'
|
pytest -s -v lora/test_minicpmv_tp.py'
|
||||||
|
|||||||
@@ -2,7 +2,7 @@ group: Miscellaneous Intel
|
|||||||
depends_on:
|
depends_on:
|
||||||
- image-build-xpu
|
- image-build-xpu
|
||||||
steps:
|
steps:
|
||||||
- label: XPU Batch Invariance
|
- label: ":intel: (BMG) Batch Invariance"
|
||||||
key: xpu-batch-invariance
|
key: xpu-batch-invariance
|
||||||
timeout_in_minutes: 60
|
timeout_in_minutes: 60
|
||||||
num_devices: 2
|
num_devices: 2
|
||||||
@@ -10,7 +10,7 @@ steps:
|
|||||||
agent_tags:
|
agent_tags:
|
||||||
label: production
|
label: production
|
||||||
gpu: 2+
|
gpu: 2+
|
||||||
mem: 24+
|
mem: 16+
|
||||||
no_plugin: true
|
no_plugin: true
|
||||||
working_dir: "."
|
working_dir: "."
|
||||||
env:
|
env:
|
||||||
@@ -30,10 +30,44 @@ steps:
|
|||||||
pytest -v -s v1/determinism/test_xpu_batch_invariant_ut.py &&
|
pytest -v -s v1/determinism/test_xpu_batch_invariant_ut.py &&
|
||||||
bash ../.buildkite/scripts/hardware_ci/run-xpu-batch-invariance.sh'
|
bash ../.buildkite/scripts/hardware_ci/run-xpu-batch-invariance.sh'
|
||||||
|
|
||||||
- label: V1 Core + KV + Metrics
|
- label: ":intel: (BMG) V1 Core + KV + Metrics"
|
||||||
key: v1-core-kv-metrics-intel
|
key: v1-core-kv-metrics-intel
|
||||||
timeout_in_minutes: 45
|
timeout_in_minutes: 45
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
|
agent_tags:
|
||||||
|
label: production
|
||||||
|
gpu: 1+
|
||||||
|
mem: 16+
|
||||||
|
no_plugin: true
|
||||||
|
working_dir: "."
|
||||||
|
env:
|
||||||
|
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||||
|
REPO: "vllm-ci-test-repo"
|
||||||
|
VLLM_TEST_DEVICE: "xpu"
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/
|
||||||
|
- tests/v1/core
|
||||||
|
- tests/v1/executor
|
||||||
|
- tests/v1/kv_offload
|
||||||
|
- tests/v1/worker
|
||||||
|
- tests/v1/kv_connector/unit
|
||||||
|
- tests/v1/ec_connector/unit
|
||||||
|
- tests/v1/metrics
|
||||||
|
- tests/entrypoints/openai/correctness/test_lmeval.py
|
||||||
|
commands:
|
||||||
|
- >-
|
||||||
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
|
'pip install -r requirements/kv_connectors.txt &&
|
||||||
|
export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
|
||||||
|
cd tests &&
|
||||||
|
pytest -v -s v1/executor &&
|
||||||
|
VLLM_BATCH_INVARIANT=1 pytest -v -s -m "not cpu_test" v1/ec_connector/unit
|
||||||
|
--ignore=v1/ec_connector/unit/test_ec_cpu_connector.py'
|
||||||
|
|
||||||
|
- label: ":intel: (BMG) EC CPU Connector (XPU)"
|
||||||
|
key: ec-cpu-connector-xpu
|
||||||
|
timeout_in_minutes: 45
|
||||||
|
device: intel_gpu
|
||||||
agent_tags:
|
agent_tags:
|
||||||
label: production
|
label: production
|
||||||
gpu: 1+
|
gpu: 1+
|
||||||
@@ -60,17 +94,16 @@ steps:
|
|||||||
'pip install -r requirements/kv_connectors.txt &&
|
'pip install -r requirements/kv_connectors.txt &&
|
||||||
export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
|
export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
|
||||||
cd tests &&
|
cd tests &&
|
||||||
pytest -v -s v1/executor &&
|
pytest -v -s v1/ec_connector/unit/test_ec_cpu_connector.py'
|
||||||
VLLM_BATCH_INVARIANT=1 pytest -v -s -m "not cpu_test" v1/ec_connector/unit'
|
|
||||||
|
|
||||||
- label: V1 Sample + Logits
|
- label: ":intel: (BMG) V1 Sample + Logits"
|
||||||
key: v1-sample-logits-intel
|
key: v1-sample-logits-intel
|
||||||
timeout_in_minutes: 90
|
timeout_in_minutes: 90
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
agent_tags:
|
agent_tags:
|
||||||
label: production
|
label: production
|
||||||
gpu: 1+
|
gpu: 1+
|
||||||
mem: 24+
|
mem: 16+
|
||||||
no_plugin: true
|
no_plugin: true
|
||||||
working_dir: "."
|
working_dir: "."
|
||||||
env:
|
env:
|
||||||
@@ -108,7 +141,7 @@ steps:
|
|||||||
limit: 1
|
limit: 1
|
||||||
parallelism: 4
|
parallelism: 4
|
||||||
|
|
||||||
- label: Basic Models Tests (Initialization)
|
- label: ":intel: (BMG) Basic Models Tests (Initialization)"
|
||||||
key: basic-models-tests-initialization
|
key: basic-models-tests-initialization
|
||||||
timeout_in_minutes: 60
|
timeout_in_minutes: 60
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
@@ -133,7 +166,7 @@ steps:
|
|||||||
cd tests &&
|
cd tests &&
|
||||||
pytest -v -s models/test_initialization.py::test_can_initialize_large_subset[Eagle3MiniMaxM2ForCausalLM]'
|
pytest -v -s models/test_initialization.py::test_can_initialize_large_subset[Eagle3MiniMaxM2ForCausalLM]'
|
||||||
|
|
||||||
- label: XPU CPU Offload
|
- label: ":intel: (BMG) CPU Offload"
|
||||||
key: xpu-cpu-offload
|
key: xpu-cpu-offload
|
||||||
timeout_in_minutes: 60
|
timeout_in_minutes: 60
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
@@ -161,7 +194,7 @@ steps:
|
|||||||
pytest -v -s v1/kv_offload &&
|
pytest -v -s v1/kv_offload &&
|
||||||
pytest -v -s v1/kv_connector/unit/test_offloading_connector.py'
|
pytest -v -s v1/kv_connector/unit/test_offloading_connector.py'
|
||||||
|
|
||||||
- label: NixlConnector PD accuracy (4 GPUs)
|
- label: ":intel: (BMG) NixlConnector PD accuracy (4 GPUs)"
|
||||||
key: nixlconnector-pd-accuracy-4-gpus
|
key: nixlconnector-pd-accuracy-4-gpus
|
||||||
timeout_in_minutes: 60
|
timeout_in_minutes: 60
|
||||||
num_devices: 4
|
num_devices: 4
|
||||||
@@ -190,7 +223,7 @@ steps:
|
|||||||
PREFILLER_TP_SIZE=1 DECODER_TP_SIZE=2 bash v1/kv_connector/nixl_integration/run_xpu_disagg_accuracy_test.sh &&
|
PREFILLER_TP_SIZE=1 DECODER_TP_SIZE=2 bash v1/kv_connector/nixl_integration/run_xpu_disagg_accuracy_test.sh &&
|
||||||
PREFILLER_TP_SIZE=2 DECODER_TP_SIZE=2 bash v1/kv_connector/nixl_integration/run_xpu_disagg_accuracy_test.sh'
|
PREFILLER_TP_SIZE=2 DECODER_TP_SIZE=2 bash v1/kv_connector/nixl_integration/run_xpu_disagg_accuracy_test.sh'
|
||||||
|
|
||||||
- label: Regression
|
- label: ":intel: (BMG) Regression"
|
||||||
key: regression
|
key: regression
|
||||||
timeout_in_minutes: 50
|
timeout_in_minutes: 50
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
@@ -223,7 +256,7 @@ steps:
|
|||||||
'cd tests &&
|
'cd tests &&
|
||||||
pytest -v -s test_regression.py'
|
pytest -v -s test_regression.py'
|
||||||
|
|
||||||
- label: Metrics, Tracing (2 GPUs)
|
- label: ":intel: (BMG) Metrics, Tracing (2 GPUs)"
|
||||||
key: metrics-tracing-2-gpus
|
key: metrics-tracing-2-gpus
|
||||||
timeout_in_minutes: 45
|
timeout_in_minutes: 45
|
||||||
num_devices: 2
|
num_devices: 2
|
||||||
@@ -258,10 +291,49 @@ steps:
|
|||||||
'cd tests &&
|
'cd tests &&
|
||||||
pytest -v -s v1/tracing'
|
pytest -v -s v1/tracing'
|
||||||
|
|
||||||
- label: Async Engine, Inputs, Utils, Worker
|
- label: ":intel: (BMG) Async Engine, Inputs, Utils, Worker"
|
||||||
key: async-engine-inputs-utils-worker
|
key: async-engine-inputs-utils-worker
|
||||||
timeout_in_minutes: 55
|
timeout_in_minutes: 55
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
|
agent_tags:
|
||||||
|
label: production
|
||||||
|
gpu: 1+
|
||||||
|
mem: 16+
|
||||||
|
no_plugin: true
|
||||||
|
working_dir: "."
|
||||||
|
env:
|
||||||
|
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||||
|
REPO: "vllm-ci-test-repo"
|
||||||
|
VLLM_TEST_DEVICE: "xpu"
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/assets/
|
||||||
|
- vllm/config/
|
||||||
|
- vllm/distributed/
|
||||||
|
- vllm/engine/
|
||||||
|
- vllm/inputs/
|
||||||
|
- vllm/model_executor/
|
||||||
|
- vllm/multimodal/
|
||||||
|
- vllm/platforms/
|
||||||
|
- vllm/sampling_params.py
|
||||||
|
- vllm/tokenizers/
|
||||||
|
- vllm/transformers_utils/
|
||||||
|
- vllm/utils/
|
||||||
|
- vllm/v1/
|
||||||
|
- tests/detokenizer
|
||||||
|
- tests/multimodal
|
||||||
|
- tests/utils_
|
||||||
|
commands:
|
||||||
|
- >-
|
||||||
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
|
'cd tests &&
|
||||||
|
pytest -v -s detokenizer --ignore=detokenizer/test_stop_strings.py &&
|
||||||
|
pytest -v -s -m "not cpu_test" ./multimodal &&
|
||||||
|
pytest -v -s utils_ --ignore=utils_/test_mem_utils.py'
|
||||||
|
|
||||||
|
- label: ":intel: (BMG) Detokenizer Stop Strings (XPU)"
|
||||||
|
key: detokenizer-stop-strings-xpu
|
||||||
|
timeout_in_minutes: 45
|
||||||
|
device: intel_gpu
|
||||||
agent_tags:
|
agent_tags:
|
||||||
label: production
|
label: production
|
||||||
gpu: 1+
|
gpu: 1+
|
||||||
@@ -290,14 +362,12 @@ steps:
|
|||||||
- tests/multimodal
|
- tests/multimodal
|
||||||
- tests/utils_
|
- tests/utils_
|
||||||
commands:
|
commands:
|
||||||
- >-
|
- >-
|
||||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
'cd tests &&
|
'cd tests &&
|
||||||
pytest -v -s detokenizer &&
|
pytest -v -s detokenizer/test_stop_strings.py'
|
||||||
pytest -v -s -m "not cpu_test" ./multimodal &&
|
|
||||||
pytest -v -s utils_ --ignore=utils_/test_mem_utils.py'
|
|
||||||
|
|
||||||
- label: Fusion Unit Tests
|
- label: ":intel: (BMG) Fusion Unit Tests"
|
||||||
key: fusion-unit-tests
|
key: fusion-unit-tests
|
||||||
timeout_in_minutes: 30
|
timeout_in_minutes: 30
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
|
|||||||
@@ -2,10 +2,38 @@ group: Model Executor Intel
|
|||||||
depends_on:
|
depends_on:
|
||||||
- image-build-xpu
|
- image-build-xpu
|
||||||
steps:
|
steps:
|
||||||
- label: Model Executor (Intel)
|
- label: ":intel: (BMG) Model Executor"
|
||||||
key: model-executor-intel
|
key: model-executor-intel
|
||||||
timeout_in_minutes: 45
|
timeout_in_minutes: 45
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
|
agent_tags:
|
||||||
|
label: production
|
||||||
|
gpu: 1+
|
||||||
|
mem: 16+
|
||||||
|
no_plugin: true
|
||||||
|
working_dir: "."
|
||||||
|
env:
|
||||||
|
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||||
|
REPO: "vllm-ci-test-repo"
|
||||||
|
VLLM_TEST_DEVICE: "xpu"
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/engine/arg_utils.py
|
||||||
|
- vllm/config/model.py
|
||||||
|
- vllm/model_executor
|
||||||
|
- tests/model_executor
|
||||||
|
commands:
|
||||||
|
- >-
|
||||||
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
|
'apt-get update && apt-get install -y curl libsodium23 &&
|
||||||
|
export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
|
||||||
|
export PYTHONFAULTHANDLER=1 &&
|
||||||
|
cd tests &&
|
||||||
|
pytest -v -s model_executor -m "not slow_test" --ignore="model_executor/layers/test_rocm_unquantized_gemm.py" --ignore="model_executor/model_loader/tensorizer_loader/test_tensorizer.py" --ignore="model_executor/model_loader/test_reload.py" --deselect="tests/model_executor/test_enabled_custom_ops.py::test_topk_gating_enabled_by_cdna"'
|
||||||
|
|
||||||
|
- label: ":intel: (BMG) Tensorizer Model Loader Tests (XPU)"
|
||||||
|
key: tensorizer-model-loader-tests-xpu
|
||||||
|
timeout_in_minutes: 45
|
||||||
|
device: intel_gpu
|
||||||
agent_tags:
|
agent_tags:
|
||||||
label: production
|
label: production
|
||||||
gpu: 1+
|
gpu: 1+
|
||||||
@@ -28,13 +56,4 @@ steps:
|
|||||||
export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
|
export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
|
||||||
export PYTHONFAULTHANDLER=1 &&
|
export PYTHONFAULTHANDLER=1 &&
|
||||||
cd tests &&
|
cd tests &&
|
||||||
pytest -v -s model_executor -m "not slow_test" --ignore="model_executor/layers/test_rocm_unquantized_gemm.py" --deselect="tests/model_executor/model_loader/test_reload.py::test_kv_scale_reload"
|
pytest -v -s model_executor/model_loader/tensorizer_loader/test_tensorizer.py -m "not slow_test"'
|
||||||
--deselect="tests/model_executor/layers/test_mm_input_norm.py::TestFusedMMInputNormModule::test_matches_reference_above_cudnn_grid_limit"
|
|
||||||
--deselect="tests/model_executor/layers/test_mm_input_norm.py::TestFusedMMInputNormDtypes::test_dtype_combinations[in_dtype0-out_dtype0]"
|
|
||||||
--deselect="tests/model_executor/layers/test_mm_input_norm.py::TestFusedMMInputNormDtypes::test_dtype_combinations[in_dtype1-out_dtype1]"
|
|
||||||
--deselect="tests/model_executor/layers/test_mm_input_norm.py::TestFusedMMInputNormDtypes::test_dtype_combinations[in_dtype2-out_dtype2]"
|
|
||||||
--deselect="tests/model_executor/layers/test_mm_input_norm.py::TestFusedMMInputNormDtypes::test_dtype_combinations[in_dtype3-out_dtype3]"
|
|
||||||
--deselect="tests/model_executor/layers/test_mm_input_norm.py::TestFusedMMInputNormDtypes::test_dtype_combinations[in_dtype4-out_dtype4]"
|
|
||||||
--deselect="tests/model_executor/layers/test_mm_input_norm.py::TestFusedMMInputNormDtypes::test_dtype_combinations[in_dtype5-out_dtype5]"
|
|
||||||
--deselect="tests/model_executor/layers/test_mm_input_norm.py::TestFusedMMInputNormShapes"
|
|
||||||
--deselect="tests/model_executor/layers/test_mm_input_norm.py::TestFusedMMInputNormInputHandling"'
|
|
||||||
|
|||||||
@@ -1,8 +1,8 @@
|
|||||||
group: Models - Distributed
|
group: Models - Distributed Intel
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-xpu
|
- image-build-xpu
|
||||||
steps:
|
steps:
|
||||||
- label: Distributed Model Tests (2 GPUs)
|
- label: ":intel: (BMG) Distributed Model Tests"
|
||||||
key: distributed-model-tests-2-gpus
|
key: distributed-model-tests-2-gpus
|
||||||
timeout_in_minutes: 65
|
timeout_in_minutes: 65
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
|
|||||||
@@ -1,15 +1,15 @@
|
|||||||
group: Models - Multimodal
|
group: Models - Multimodal Intel
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-xpu
|
- image-build-xpu
|
||||||
steps:
|
steps:
|
||||||
- label: "Multi-Modal Models (Standard) 1: qwen2"
|
- label: ":intel: (BMG) Multi-Modal Models (Standard) 1: qwen2"
|
||||||
key: multi-modal-models-standard-1-qwen2
|
key: multi-modal-models-standard-1-qwen2
|
||||||
timeout_in_minutes: 70
|
timeout_in_minutes: 70
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
agent_tags:
|
agent_tags:
|
||||||
label: production
|
label: production
|
||||||
gpu: 1+
|
gpu: 1+
|
||||||
mem: 24+
|
mem: 16+
|
||||||
no_plugin: true
|
no_plugin: true
|
||||||
working_dir: "."
|
working_dir: "."
|
||||||
env:
|
env:
|
||||||
@@ -26,14 +26,14 @@ steps:
|
|||||||
pytest -v -s models/multimodal/generation/test_common.py -m core_model -k "qwen2" &&
|
pytest -v -s models/multimodal/generation/test_common.py -m core_model -k "qwen2" &&
|
||||||
pytest -v -s models/multimodal/generation/test_ultravox.py -m core_model'
|
pytest -v -s models/multimodal/generation/test_ultravox.py -m core_model'
|
||||||
|
|
||||||
- label: "Multi-Modal Models (Standard) 2: qwen3 + gemma"
|
- label: ":intel: (BMG) Multi-Modal Models (Standard) 2: qwen3 + gemma"
|
||||||
key: multi-modal-models-standard-2-qwen3-gemma
|
key: multi-modal-models-standard-2-qwen3-gemma
|
||||||
timeout_in_minutes: 90
|
timeout_in_minutes: 90
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
agent_tags:
|
agent_tags:
|
||||||
label: production
|
label: production
|
||||||
gpu: 1+
|
gpu: 1+
|
||||||
mem: 24+
|
mem: 16+
|
||||||
no_plugin: true
|
no_plugin: true
|
||||||
working_dir: "."
|
working_dir: "."
|
||||||
env:
|
env:
|
||||||
@@ -51,7 +51,7 @@ steps:
|
|||||||
pytest -v -s models/multimodal/generation/test_mm_prefix_lm.py -m core_model &&
|
pytest -v -s models/multimodal/generation/test_mm_prefix_lm.py -m core_model &&
|
||||||
pytest -v -s models/multimodal/generation/test_qwen2_5_vl.py -m core_model'
|
pytest -v -s models/multimodal/generation/test_qwen2_5_vl.py -m core_model'
|
||||||
|
|
||||||
- label: "Multi-Modal Models (Standard) 3: llava + qwen2_vl"
|
- label: ":intel: (BMG) Multi-Modal Models (Standard) 3: llava + qwen2_vl"
|
||||||
key: multi-modal-models-standard-3-llava-qwen2-vl
|
key: multi-modal-models-standard-3-llava-qwen2-vl
|
||||||
timeout_in_minutes: 65
|
timeout_in_minutes: 65
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
@@ -72,16 +72,18 @@ steps:
|
|||||||
- >-
|
- >-
|
||||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
'cd tests &&
|
'cd tests &&
|
||||||
pytest -v -s models/multimodal/generation/test_common.py -m core_model -k "not qwen2 and not qwen3 and not gemma"'
|
pytest -v -s models/multimodal/generation/test_common.py -m core_model -k "not qwen2 and not qwen3 and not gemma" &&
|
||||||
|
pytest -v -s models/multimodal/generation/test_gemma_ragged_audio.py -m core_model
|
||||||
|
pytest -v -s models/multimodal/generation/test_qwen2_vl.py -m core_model'
|
||||||
|
|
||||||
- label: "Multi-Modal Models (Standard) 4: other + whisper"
|
- label: ":intel: (BMG) Multi-Modal Models (Standard) 4: other + whisper"
|
||||||
key: multi-modal-models-standard-4-other-whisper
|
key: multi-modal-models-standard-4-other-whisper
|
||||||
timeout_in_minutes: 45
|
timeout_in_minutes: 45
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
agent_tags:
|
agent_tags:
|
||||||
label: production
|
label: production
|
||||||
gpu: 1+
|
gpu: 1+
|
||||||
mem: 24+
|
mem: 16+
|
||||||
no_plugin: true
|
no_plugin: true
|
||||||
working_dir: "."
|
working_dir: "."
|
||||||
env:
|
env:
|
||||||
@@ -95,9 +97,9 @@ steps:
|
|||||||
- >-
|
- >-
|
||||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
'cd tests &&
|
'cd tests &&
|
||||||
pytest -v -s models/multimodal -m core_model --ignore models/multimodal/generation/test_common.py --ignore models/multimodal/generation/test_ultravox.py --ignore models/multimodal/generation/test_qwen2_5_vl.py --ignore models/multimodal/generation/test_qwen2_vl.py --ignore models/multimodal/generation/test_whisper.py --ignore models/multimodal/generation/test_memory_leak.py --ignore models/multimodal/processing'
|
pytest -v -s models/multimodal -m core_model --ignore models/multimodal/generation/test_common.py --ignore models/multimodal/generation/test_ultravox.py --ignore models/multimodal/generation/test_qwen2_5_vl.py --ignore models/multimodal/generation/test_qwen2_vl.py --ignore models/multimodal/generation/test_whisper.py --ignore models/multimodal/generation/test_gemma_ragged_audio.py --ignore models/multimodal/generation/test_memory_leak.py --ignore models/multimodal/processing'
|
||||||
|
|
||||||
- label: Multi-Modal Processor # 44min
|
- label: ":intel: (BMG) Multi-Modal Processor" # 44min
|
||||||
key: multi-modal-processor
|
key: multi-modal-processor
|
||||||
timeout_in_minutes: 60
|
timeout_in_minutes: 60
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
@@ -124,14 +126,14 @@ steps:
|
|||||||
--num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB'
|
--num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB'
|
||||||
parallelism: 4
|
parallelism: 4
|
||||||
|
|
||||||
- label: Multi-Modal Models (Extended Generation 1)
|
- label: ":intel: (BMG) Multi-Modal Models (Extended Generation 1)"
|
||||||
key: multi-modal-models-extended-generation-1
|
key: multi-modal-models-extended-generation-1
|
||||||
timeout_in_minutes: 60
|
timeout_in_minutes: 60
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
agent_tags:
|
agent_tags:
|
||||||
label: production
|
label: production
|
||||||
gpu: 1+
|
gpu: 1+
|
||||||
mem: 24+
|
mem: 16+
|
||||||
no_plugin: true
|
no_plugin: true
|
||||||
working_dir: "."
|
working_dir: "."
|
||||||
env:
|
env:
|
||||||
|
|||||||
+5
-3
@@ -1,8 +1,8 @@
|
|||||||
group: Quantization
|
group: Quantization Intel
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-xpu
|
- image-build-xpu
|
||||||
steps:
|
steps:
|
||||||
- label: Quantization
|
- label: ":intel: (BMG) Quantization"
|
||||||
key: quantization
|
key: quantization
|
||||||
timeout_in_minutes: 30
|
timeout_in_minutes: 30
|
||||||
env:
|
env:
|
||||||
@@ -25,5 +25,7 @@ steps:
|
|||||||
- >-
|
- >-
|
||||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
'VLLM_TEST_FORCE_LOAD_FORMAT=auto pytest -v -s tests/quantization/test_per_token_kv_cache.py --deselect="tests/quantization/test_per_token_kv_cache.py::test_triton_unified_attention_per_token_head_scale[int4-16-128-num_heads0-seq_lens1]"
|
'VLLM_TEST_FORCE_LOAD_FORMAT=auto pytest -v -s tests/quantization/test_per_token_kv_cache.py --deselect="tests/quantization/test_per_token_kv_cache.py::test_triton_unified_attention_per_token_head_scale[int4-16-128-num_heads0-seq_lens1]"
|
||||||
&& VLLM_TEST_FORCE_LOAD_FORMAT=auto pytest -v -s tests/quantization/test_auto_awq.py'
|
&& VLLM_TEST_FORCE_LOAD_FORMAT=auto pytest -v -s tests/quantization/test_auto_awq.py
|
||||||
|
&& VLLM_TEST_FORCE_LOAD_FORMAT=auto pytest -v -s tests/quantization/test_fp8_per_channel.py
|
||||||
|
&& VLLM_TEST_FORCE_LOAD_FORMAT=auto pytest -v -s tests/models/quantization/test_fp8_per_channel.py --deselect="tests/models/quantization/test_fp8_per_channel.py::test_fp8_per_channel_logprobs[moe]"'
|
||||||
|
|
||||||
@@ -2,10 +2,37 @@ group: Samplers Intel
|
|||||||
depends_on:
|
depends_on:
|
||||||
- image-build-xpu
|
- image-build-xpu
|
||||||
steps:
|
steps:
|
||||||
- label: Samplers Test (XPU Kernel)
|
- label: ":intel: (BMG) Samplers Test (XPU Kernel)"
|
||||||
key: samplers-test-xpu-kernel-intel
|
key: samplers-test-xpu-kernel-intel
|
||||||
timeout_in_minutes: 40
|
timeout_in_minutes: 40
|
||||||
device: intel_gpu
|
device: intel_gpu
|
||||||
|
agent_tags:
|
||||||
|
label: production
|
||||||
|
gpu: 1+
|
||||||
|
mem: 16+
|
||||||
|
no_plugin: true
|
||||||
|
working_dir: "."
|
||||||
|
env:
|
||||||
|
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||||
|
REPO: "vllm-ci-test-repo"
|
||||||
|
VLLM_TEST_DEVICE: "xpu"
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/model_executor/layers
|
||||||
|
- vllm/sampling_metadata.py
|
||||||
|
- tests/samplers
|
||||||
|
- tests/conftest.py
|
||||||
|
- vllm/entrypoints/generate/beam_search
|
||||||
|
commands:
|
||||||
|
- >-
|
||||||
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
|
'cd tests &&
|
||||||
|
VLLM_XPU_USE_SAMPLER_KERNEL=1 pytest -v -s samplers
|
||||||
|
--ignore=samplers/test_beam_search.py'
|
||||||
|
|
||||||
|
- label: ":intel: (BMG) Samplers Beam Search Test (XPU Kernel)"
|
||||||
|
key: samplers-beam-search-test-xpu-kernel-intel
|
||||||
|
timeout_in_minutes: 40
|
||||||
|
device: intel_gpu
|
||||||
agent_tags:
|
agent_tags:
|
||||||
label: production
|
label: production
|
||||||
gpu: 1+
|
gpu: 1+
|
||||||
@@ -26,4 +53,4 @@ steps:
|
|||||||
- >-
|
- >-
|
||||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
'cd tests &&
|
'cd tests &&
|
||||||
VLLM_XPU_USE_SAMPLER_KERNEL=1 pytest -v -s samplers'
|
VLLM_XPU_USE_SAMPLER_KERNEL=1 pytest -v -s samplers/test_beam_search.py'
|
||||||
|
|||||||
@@ -14,7 +14,7 @@ steps:
|
|||||||
limit: 2
|
limit: 2
|
||||||
- exit_status: -10 # Agent was lost
|
- exit_status: -10 # Agent was lost
|
||||||
limit: 2
|
limit: 2
|
||||||
- label: "XPU example Test"
|
- label: ":intel: (BMG) Example Test"
|
||||||
key: xpu-example-test
|
key: xpu-example-test
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-xpu
|
- image-build-xpu
|
||||||
@@ -23,7 +23,7 @@ steps:
|
|||||||
agent_tags:
|
agent_tags:
|
||||||
label: production
|
label: production
|
||||||
gpu: 2+
|
gpu: 2+
|
||||||
mem: 24+
|
mem: 16+
|
||||||
no_plugin: true
|
no_plugin: true
|
||||||
env:
|
env:
|
||||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||||
@@ -46,10 +46,9 @@ steps:
|
|||||||
python3 examples/basic/offline_inference/generate.py --model ibm-research/PowerMoE-3b --block-size 64 --enforce-eager -tp 2 &&
|
python3 examples/basic/offline_inference/generate.py --model ibm-research/PowerMoE-3b --block-size 64 --enforce-eager -tp 2 &&
|
||||||
python3 examples/basic/offline_inference/generate.py --model ibm-research/PowerMoE-3b --block-size 64 --enforce-eager -tp 2 --enable-expert-parallel &&
|
python3 examples/basic/offline_inference/generate.py --model ibm-research/PowerMoE-3b --block-size 64 --enforce-eager -tp 2 --enable-expert-parallel &&
|
||||||
python3 examples/basic/offline_inference/generate.py --model superjob/Qwen3-4B-Instruct-2507-GPTQ-Int4 --max-model-len 8192 &&
|
python3 examples/basic/offline_inference/generate.py --model superjob/Qwen3-4B-Instruct-2507-GPTQ-Int4 --max-model-len 8192 &&
|
||||||
VLLM_XPU_FUSED_MOE_USE_REF=1 python3 examples/basic/offline_inference/generate.py --model Qwen/Qwen3-30B-A3B-Instruct-2507-FP8 --enforce-eager -tp 2 --max-model-len 8192 &&
|
|
||||||
python3 examples/basic/offline_inference/generate.py --model INCModel/Qwen3-30B-A3B-Instruct-2507-MXFP4-LLMC -tp 2 --max-model-len 8192
|
python3 examples/basic/offline_inference/generate.py --model INCModel/Qwen3-30B-A3B-Instruct-2507-MXFP4-LLMC -tp 2 --max-model-len 8192
|
||||||
'
|
'
|
||||||
- label: "XPU W8A8 FP8 Linear Examples"
|
- label: ":intel: (BMG) W8A8 FP8 Linear Examples"
|
||||||
key: xpu-w8a8-fp8-linear-examples
|
key: xpu-w8a8-fp8-linear-examples
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-xpu
|
- image-build-xpu
|
||||||
@@ -58,7 +57,7 @@ steps:
|
|||||||
agent_tags:
|
agent_tags:
|
||||||
label: production
|
label: production
|
||||||
gpu: 1+
|
gpu: 1+
|
||||||
mem: 24+
|
mem: 16+
|
||||||
no_plugin: true
|
no_plugin: true
|
||||||
env:
|
env:
|
||||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||||
@@ -77,7 +76,7 @@ steps:
|
|||||||
python3 examples/basic/offline_inference/generate.py --linear-backend xpu --model meta-llama/Llama-3.2-1B-Instruct --quantization fp8_per_tensor --enforce-eager --max-model-len 4096 &&
|
python3 examples/basic/offline_inference/generate.py --linear-backend xpu --model meta-llama/Llama-3.2-1B-Instruct --quantization fp8_per_tensor --enforce-eager --max-model-len 4096 &&
|
||||||
python3 examples/basic/offline_inference/generate.py --linear-backend torch --model meta-llama/Llama-3.2-1B-Instruct --quantization fp8_per_tensor --enforce-eager --max-model-len 4096
|
python3 examples/basic/offline_inference/generate.py --linear-backend torch --model meta-llama/Llama-3.2-1B-Instruct --quantization fp8_per_tensor --enforce-eager --max-model-len 4096
|
||||||
'
|
'
|
||||||
- label: "XPU V1 test"
|
- label: ":intel: (BMG) V1 test"
|
||||||
key: xpu-v1-test
|
key: xpu-v1-test
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-xpu
|
- image-build-xpu
|
||||||
@@ -86,7 +85,7 @@ steps:
|
|||||||
agent_tags:
|
agent_tags:
|
||||||
label: production
|
label: production
|
||||||
gpu: 1+
|
gpu: 1+
|
||||||
mem: 24+
|
mem: 16+
|
||||||
no_plugin: true
|
no_plugin: true
|
||||||
env:
|
env:
|
||||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||||
@@ -106,9 +105,35 @@ steps:
|
|||||||
pytest -v -s v1/test_serial_utils.py &&
|
pytest -v -s v1/test_serial_utils.py &&
|
||||||
pytest -v -s v1/e2e/general/test_correctness_sliding_window.py &&
|
pytest -v -s v1/e2e/general/test_correctness_sliding_window.py &&
|
||||||
pytest -v -s v1/spec_decode --ignore=v1/spec_decode/test_max_len.py --ignore=v1/spec_decode/test_speculators_eagle3.py --ignore=v1/spec_decode/test_acceptance_length.py --ignore=v1/spec_decode/test_speculators_correctness.py --deselect=tests/v1/spec_decode/test_mtp.py::test_glm_mtp_defers_lm_head &&
|
pytest -v -s v1/spec_decode --ignore=v1/spec_decode/test_max_len.py --ignore=v1/spec_decode/test_speculators_eagle3.py --ignore=v1/spec_decode/test_acceptance_length.py --ignore=v1/spec_decode/test_speculators_correctness.py --deselect=tests/v1/spec_decode/test_mtp.py::test_glm_mtp_defers_lm_head &&
|
||||||
pytest -v -s v1/kv_connector/unit --ignore=v1/kv_connector/unit/test_lmcache_integration.py --ignore=v1/kv_connector/unit/test_hf3fs_client.py --ignore=v1/kv_connector/unit/test_hf3fs_connector.py --ignore=v1/kv_connector/unit/test_hf3fs_metadata_server.py --ignore=v1/kv_connector/unit/test_offloading_connector.py --ignore=v1/kv_connector/unit/test_nixl_connector_hma.py --deselect=tests/v1/kv_connector/unit/test_nixl_connector.py::test_abort_timeout_on_prefiller[ray]'
|
pytest -v -s v1/kv_connector/unit --ignore=v1/kv_connector/unit/test_lmcache_integration.py --ignore=v1/kv_connector/unit/test_hf3fs_client.py --ignore=v1/kv_connector/unit/test_hf3fs_connector.py --ignore=v1/kv_connector/unit/test_hf3fs_metadata_server.py --ignore=v1/kv_connector/unit/test_offloading_connector.py --ignore=v1/kv_connector/unit/test_multi_connector.py --ignore=v1/kv_connector/unit/test_example_connector.py --deselect=tests/v1/kv_connector/unit/test_nixl_connector.py::test_abort_timeout_on_prefiller[ray]'
|
||||||
parallelism: 2
|
parallelism: 2
|
||||||
- label: "XPU server test"
|
- label: ":intel: (BMG) Qwen3-30B + V1 KV Connector"
|
||||||
|
key: xpu-qwen3-30b-v1-kv-connector
|
||||||
|
depends_on:
|
||||||
|
- image-build-xpu
|
||||||
|
timeout_in_minutes: 90
|
||||||
|
device: intel_gpu
|
||||||
|
agent_tags:
|
||||||
|
label: production
|
||||||
|
gpu: 2+
|
||||||
|
mem: 24+
|
||||||
|
no_plugin: true
|
||||||
|
env:
|
||||||
|
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||||
|
REPO: "vllm-ci-test-repo"
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/
|
||||||
|
- .buildkite/intel_jobs/test-intel.yaml
|
||||||
|
commands:
|
||||||
|
- >-
|
||||||
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
|
'cd tests &&
|
||||||
|
pip install dpctl &&
|
||||||
|
pytest -v -s v1/kv_connector/unit/test_multi_connector.py &&
|
||||||
|
pytest -v -s v1/kv_connector/unit/test_example_connector.py &&
|
||||||
|
cd .. &&
|
||||||
|
VLLM_XPU_FUSED_MOE_USE_REF=1 python3 examples/basic/offline_inference/generate.py --model Qwen/Qwen3-30B-A3B-Instruct-2507-FP8 --enforce-eager -tp 2 --max-model-len 8192'
|
||||||
|
- label: ":intel: (BMG) Server test"
|
||||||
key: xpu-server-test
|
key: xpu-server-test
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-xpu
|
- image-build-xpu
|
||||||
@@ -131,7 +156,7 @@ steps:
|
|||||||
'cd tests &&
|
'cd tests &&
|
||||||
pytest -v -s entrypoints/multimodal/openai/chat_completion/test_audio_in_video.py &&
|
pytest -v -s entrypoints/multimodal/openai/chat_completion/test_audio_in_video.py &&
|
||||||
pytest -v -s benchmarks/test_serve_cli.py'
|
pytest -v -s benchmarks/test_serve_cli.py'
|
||||||
- label: "XPU quantization test"
|
- label: ":intel: (BMG) Quantization test"
|
||||||
key: xpu-quantization-test
|
key: xpu-quantization-test
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-xpu
|
- image-build-xpu
|
||||||
@@ -153,8 +178,8 @@ steps:
|
|||||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
'cd tests &&
|
'cd tests &&
|
||||||
pytest -v -s quantization/test_auto_round.py &&
|
pytest -v -s quantization/test_auto_round.py &&
|
||||||
pytest -v -s quantization/test_online.py --deselect=tests/quantization/test_online.py::test_online_quantization_loads_real_weights'
|
pytest -v -s quantization/test_online.py --deselect=tests/quantization/test_online.py::test_online_quantization_loads_real_weights --deselect="tests/quantization/test_online.py::test_online_quantization[False-requantization_mxfp8_ptcp_fp8]"'
|
||||||
- label: "XPU compressed tensors FP8 test"
|
- label: ":intel: (BMG) Compressed tensors FP8 test"
|
||||||
key: xpu-compressed-tensors-fp8-test
|
key: xpu-compressed-tensors-fp8-test
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-xpu
|
- image-build-xpu
|
||||||
@@ -179,7 +204,7 @@ steps:
|
|||||||
'cd tests &&
|
'cd tests &&
|
||||||
pytest -v -s quantization/test_compressed_tensors.py::test_compressed_tensors_fp8 &&
|
pytest -v -s quantization/test_compressed_tensors.py::test_compressed_tensors_fp8 &&
|
||||||
pytest -v -s quantization/test_compressed_tensors.py::test_compressed_tensors_fp8_block_enabled'
|
pytest -v -s quantization/test_compressed_tensors.py::test_compressed_tensors_fp8_block_enabled'
|
||||||
- label: "XPU Graph"
|
- label: ":intel: (BMG) Graph"
|
||||||
key: xpu-graph
|
key: xpu-graph
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-xpu
|
- image-build-xpu
|
||||||
|
|||||||
@@ -8,16 +8,28 @@ pytest -s -v test_lm_eval_correctness.py \
|
|||||||
--tp-size=1
|
--tp-size=1
|
||||||
"""
|
"""
|
||||||
|
|
||||||
|
import gc
|
||||||
import os
|
import os
|
||||||
|
import time
|
||||||
from contextlib import contextmanager
|
from contextlib import contextmanager
|
||||||
|
|
||||||
import lm_eval
|
import lm_eval
|
||||||
import pytest
|
import pytest
|
||||||
|
import torch
|
||||||
import yaml
|
import yaml
|
||||||
|
from lm_eval.api.registry import get_model
|
||||||
|
from lm_eval.utils import simple_parse_args_string
|
||||||
|
|
||||||
|
from vllm import LLM
|
||||||
|
from vllm.distributed import cleanup_dist_env_and_memory
|
||||||
|
from vllm.logger import init_logger
|
||||||
from vllm.platforms import current_platform
|
from vllm.platforms import current_platform
|
||||||
|
|
||||||
|
logger = init_logger(__name__)
|
||||||
|
|
||||||
DEFAULT_RTOL = 0.08
|
DEFAULT_RTOL = 0.08
|
||||||
|
ROCM_ENGINE_SHUTDOWN_TIMEOUT_S = 60.0
|
||||||
|
MEMORY_RELEASE_TIMEOUT_S = 240.0
|
||||||
|
|
||||||
|
|
||||||
@contextmanager
|
@contextmanager
|
||||||
@@ -46,6 +58,48 @@ def scoped_env_vars(new_env: dict[str, str]):
|
|||||||
os.environ.pop(key, None)
|
os.environ.pop(key, None)
|
||||||
|
|
||||||
|
|
||||||
|
def _wait_for_memory_release(gpu_memory_utilization: float) -> None:
|
||||||
|
devices = range(torch.accelerator.device_count())
|
||||||
|
deadline = time.monotonic() + MEMORY_RELEASE_TIMEOUT_S
|
||||||
|
while True:
|
||||||
|
memory = [torch.accelerator.get_memory_info(d) for d in devices]
|
||||||
|
if all(free >= total * gpu_memory_utilization for free, total in memory):
|
||||||
|
return
|
||||||
|
if time.monotonic() >= deadline:
|
||||||
|
usage = ", ".join(
|
||||||
|
f"{d}: {free / 2**30:.2f}/{total / 2**30:.2f} GiB free"
|
||||||
|
for d, (free, total) in zip(devices, memory)
|
||||||
|
)
|
||||||
|
logger.warning(
|
||||||
|
"GPU memory not released after %ss (%s); the next model needs %.2f",
|
||||||
|
MEMORY_RELEASE_TIMEOUT_S,
|
||||||
|
usage,
|
||||||
|
gpu_memory_utilization,
|
||||||
|
)
|
||||||
|
return
|
||||||
|
time.sleep(1)
|
||||||
|
|
||||||
|
|
||||||
|
def _shutdown_lm(lm) -> None:
|
||||||
|
if not current_platform.is_rocm():
|
||||||
|
return
|
||||||
|
llm = getattr(lm, "model", None)
|
||||||
|
if not isinstance(llm, LLM):
|
||||||
|
return
|
||||||
|
gpu_memory_utilization = (
|
||||||
|
llm.llm_engine.vllm_config.cache_config.gpu_memory_utilization
|
||||||
|
)
|
||||||
|
try:
|
||||||
|
llm.llm_engine.engine_core.shutdown(timeout=ROCM_ENGINE_SHUTDOWN_TIMEOUT_S)
|
||||||
|
except Exception:
|
||||||
|
logger.exception("Engine core shutdown raised; GPU memory may leak")
|
||||||
|
del llm
|
||||||
|
lm.model = None
|
||||||
|
gc.collect()
|
||||||
|
cleanup_dist_env_and_memory()
|
||||||
|
_wait_for_memory_release(gpu_memory_utilization)
|
||||||
|
|
||||||
|
|
||||||
def launch_lm_eval(eval_config, tp_size):
|
def launch_lm_eval(eval_config, tp_size):
|
||||||
trust_remote_code = eval_config.get("trust_remote_code", False)
|
trust_remote_code = eval_config.get("trust_remote_code", False)
|
||||||
max_model_len = eval_config.get("max_model_len", 4096)
|
max_model_len = eval_config.get("max_model_len", 4096)
|
||||||
@@ -82,9 +136,17 @@ def launch_lm_eval(eval_config, tp_size):
|
|||||||
|
|
||||||
env_vars = eval_config.get("env_vars", None)
|
env_vars = eval_config.get("env_vars", None)
|
||||||
with scoped_env_vars(env_vars):
|
with scoped_env_vars(env_vars):
|
||||||
|
if current_platform.is_rocm():
|
||||||
|
model = get_model(backend).create_from_arg_string(
|
||||||
|
model_args,
|
||||||
|
{"batch_size": batch_size, "max_batch_size": None, "device": None},
|
||||||
|
)
|
||||||
|
model_kwargs = {"metadata": simple_parse_args_string(model_args)}
|
||||||
|
else:
|
||||||
|
model = backend
|
||||||
|
model_kwargs = {"model_args": model_args}
|
||||||
results = lm_eval.simple_evaluate(
|
results = lm_eval.simple_evaluate(
|
||||||
model=backend,
|
model=model,
|
||||||
model_args=model_args,
|
|
||||||
tasks=[task["name"] for task in eval_config["tasks"]],
|
tasks=[task["name"] for task in eval_config["tasks"]],
|
||||||
num_fewshot=eval_config["num_fewshot"],
|
num_fewshot=eval_config["num_fewshot"],
|
||||||
limit=eval_config["limit"],
|
limit=eval_config["limit"],
|
||||||
@@ -98,7 +160,9 @@ def launch_lm_eval(eval_config, tp_size):
|
|||||||
# Forward decoding and early-stop controls (e.g., max_gen_toks, until=...)
|
# Forward decoding and early-stop controls (e.g., max_gen_toks, until=...)
|
||||||
gen_kwargs=eval_config.get("gen_kwargs"),
|
gen_kwargs=eval_config.get("gen_kwargs"),
|
||||||
batch_size=batch_size,
|
batch_size=batch_size,
|
||||||
|
**model_kwargs,
|
||||||
)
|
)
|
||||||
|
_shutdown_lm(model)
|
||||||
return results
|
return results
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
+220
-448
@@ -355,6 +355,10 @@ steps:
|
|||||||
queue: arm64_cpu_queue_release
|
queue: arm64_cpu_queue_release
|
||||||
commands:
|
commands:
|
||||||
- "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
|
- "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
|
||||||
|
# TODO(arpera):
|
||||||
|
# Remove BUILD_NIXL=true once NIXL has a wheel built against torch 2.15
|
||||||
|
# For details: https://github.com/vllm-project/vllm/pull/60090
|
||||||
|
# Tracking issue report: https://github.com/ai-dynamo/nixl/issues/2297
|
||||||
- |
|
- |
|
||||||
DOCKER_BUILDKIT=1 docker buildx build --load \
|
DOCKER_BUILDKIT=1 docker buildx build --load \
|
||||||
$(bash .buildkite/scripts/docker-build-metadata-args.sh cu134) \
|
$(bash .buildkite/scripts/docker-build-metadata-args.sh cu134) \
|
||||||
@@ -366,6 +370,7 @@ steps:
|
|||||||
--build-arg torch_cuda_arch_list="${CUDA_ARCH_AARCH64}" \
|
--build-arg torch_cuda_arch_list="${CUDA_ARCH_AARCH64}" \
|
||||||
--build-arg INSTALL_KV_CONNECTORS=true \
|
--build-arg INSTALL_KV_CONNECTORS=true \
|
||||||
--build-arg INSTALL_RUBIN_PRERELEASE=true \
|
--build-arg INSTALL_RUBIN_PRERELEASE=true \
|
||||||
|
--build-arg BUILD_NIXL=true \
|
||||||
--build-arg TRITON_INSTALL_FROM_SOURCE_REPO=https://github.com/triton-lang/triton.git \
|
--build-arg TRITON_INSTALL_FROM_SOURCE_REPO=https://github.com/triton-lang/triton.git \
|
||||||
--build-arg TRITON_INSTALL_FROM_SOURCE_REVISION=3f6e41132b5edf639bfb872ad73d4688765e08b8 \
|
--build-arg TRITON_INSTALL_FROM_SOURCE_REVISION=3f6e41132b5edf639bfb872ad73d4688765e08b8 \
|
||||||
--build-arg RUN_WHEEL_CHECK=false \
|
--build-arg RUN_WHEEL_CHECK=false \
|
||||||
@@ -698,348 +703,270 @@ steps:
|
|||||||
DOCKER_BUILDKIT: "1"
|
DOCKER_BUILDKIT: "1"
|
||||||
DOCKERHUB_USERNAME: "vllmbot"
|
DOCKERHUB_USERNAME: "vllmbot"
|
||||||
|
|
||||||
|
- trigger: "perf-eval"
|
||||||
|
label: "Trigger perf-eval (CUDA)"
|
||||||
|
key: trigger-perf-eval-cuda
|
||||||
|
if: build.env("NIGHTLY") == "1" || build.env("RUN_PERF_EVAL") == "1"
|
||||||
|
depends_on:
|
||||||
|
- build-release-image-x86
|
||||||
|
async: true
|
||||||
|
soft_fail: true
|
||||||
|
build:
|
||||||
|
branch: "main"
|
||||||
|
message: "(NIGHTLY=${NIGHTLY:-0}) Evaluate vLLM $BUILDKITE_COMMIT (CUDA)"
|
||||||
|
env:
|
||||||
|
NIGHTLY: 1 # run all perf-eval workloads
|
||||||
|
VLLM_COMMIT: "$BUILDKITE_COMMIT"
|
||||||
|
VLLM_IMAGE_CUDA: "public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-x86_64"
|
||||||
|
|
||||||
|
- trigger: "perf-eval"
|
||||||
|
label: "Trigger perf-eval (ROCm)"
|
||||||
|
key: trigger-perf-eval-rocm
|
||||||
|
if: build.env("NIGHTLY") == "1" || build.env("RUN_PERF_EVAL") == "1"
|
||||||
|
depends_on:
|
||||||
|
- build-rocm100-release-image
|
||||||
|
async: true
|
||||||
|
soft_fail: true
|
||||||
|
build:
|
||||||
|
branch: "main"
|
||||||
|
message: "(NIGHTLY=${NIGHTLY:-0}) Evaluate vLLM $BUILDKITE_COMMIT (ROCm)"
|
||||||
|
env:
|
||||||
|
NIGHTLY: 1 # run all perf-eval workloads
|
||||||
|
VLLM_COMMIT: "$BUILDKITE_COMMIT"
|
||||||
|
VLLM_IMAGE_ROCM: "public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-rocm100"
|
||||||
|
|
||||||
# =============================================================================
|
# =============================================================================
|
||||||
# ROCm Release Pipeline (x86_64 only)
|
# ROCm Release Pipelines (x86_64 only)
|
||||||
# =============================================================================
|
# =============================================================================
|
||||||
#
|
#
|
||||||
# vLLM version is determined by the Buildkite checkout (like CUDA pipeline).
|
# One group per ROCm stack, identified by its base Dockerfile (ROCM_BASE_DOCKERFILE).
|
||||||
# To build a specific version, trigger the build from that branch/tag.
|
# The scripts derive the ROCm version, wheel variant, cache keys and image tags from
|
||||||
|
# it (.buildkite/scripts/rocm/stack.sh), so both groups share one set of step
|
||||||
|
# definitions, anchored on the ROCm 10.0 group.
|
||||||
#
|
#
|
||||||
# Environment variables for ROCm builds (set via Buildkite UI or schedule):
|
# - ROCm 10.0 (TheRock, docker/Dockerfile.rocm{,_base}) is the default: it owns the
|
||||||
#
|
# :nightly / :latest images and the root wheel index.
|
||||||
# Note: ROCm version is determined by BASE_IMAGE in docker/Dockerfile.rocm_base
|
# - ROCm 7.2 (docker/Dockerfile.rocm_72{,_base}) is kept for a transition period as
|
||||||
|
# rocm72 images and wheels.
|
||||||
#
|
#
|
||||||
|
# vLLM version is determined by the Buildkite checkout (like the CUDA pipeline).
|
||||||
# =============================================================================
|
# =============================================================================
|
||||||
|
|
||||||
- group: "Build ROCm Wheel / Image "
|
- group: "Build ROCm 10.0 Wheel / Image"
|
||||||
key: "build-rocm-wheel-image"
|
key: "build-rocm100"
|
||||||
depends_on: ~
|
depends_on: ~
|
||||||
steps:
|
steps:
|
||||||
# ROCm Job 1: Build ROCm Base Wheels (with S3 caching)
|
- label: ":rocm: Build ROCm 10.0 Base Image & Wheels"
|
||||||
- label: ":rocm: Build ROCm Base Image & Wheels"
|
id: build-rocm100-base
|
||||||
id: build-rocm-base-wheels
|
|
||||||
depends_on: ~
|
depends_on: ~
|
||||||
agents:
|
agents: &rocm_build_agents
|
||||||
queue: cpu_queue_release
|
queue: cpu_queue_release
|
||||||
commands:
|
timeout_in_minutes: 360
|
||||||
- |
|
env: &rocm100_env
|
||||||
set -euo pipefail
|
ROCM_BASE_DOCKERFILE: "docker/Dockerfile.rocm_base"
|
||||||
|
ROCM_DEFAULT_ARG: "--default"
|
||||||
# Generate cache key
|
|
||||||
CACHE_KEY=$$(.buildkite/scripts/cache-rocm-base-wheels.sh key)
|
|
||||||
ECR_CACHE_TAG="public.ecr.aws/q9t5s3a7/vllm-release-repo:$${CACHE_KEY}-rocm-base"
|
|
||||||
|
|
||||||
echo "========================================"
|
|
||||||
echo "ROCm Base Build Configuration"
|
|
||||||
echo "========================================"
|
|
||||||
echo " CACHE_KEY: $${CACHE_KEY}"
|
|
||||||
echo " ECR_CACHE_TAG: $${ECR_CACHE_TAG}"
|
|
||||||
echo "========================================"
|
|
||||||
|
|
||||||
# Login to ECR
|
|
||||||
aws ecr-public get-login-password --region us-east-1 | \
|
|
||||||
docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7
|
|
||||||
|
|
||||||
IMAGE_EXISTS=false
|
|
||||||
WHEELS_EXIST=false
|
|
||||||
|
|
||||||
# Check ECR for Docker image
|
|
||||||
|
|
||||||
if docker manifest inspect "$${ECR_CACHE_TAG}" > /dev/null 2>&1; then
|
|
||||||
IMAGE_EXISTS=true
|
|
||||||
echo "ECR image cache HIT"
|
|
||||||
fi
|
|
||||||
|
|
||||||
# Check S3 for wheels
|
|
||||||
WHEEL_CACHE_STATUS=$(.buildkite/scripts/cache-rocm-base-wheels.sh check)
|
|
||||||
if [ "$${WHEEL_CACHE_STATUS}" = "hit" ]; then
|
|
||||||
WHEELS_EXIST=true
|
|
||||||
echo "S3 wheels cache HIT"
|
|
||||||
fi
|
|
||||||
|
|
||||||
|
|
||||||
# Scenario 1: Both cached (best case)
|
|
||||||
if [ "$${IMAGE_EXISTS}" = "true" ] && [ "$${WHEELS_EXIST}" = "true" ]; then
|
|
||||||
echo ""
|
|
||||||
echo "FULL CACHE HIT - Reusing both image and wheels"
|
|
||||||
echo ""
|
|
||||||
|
|
||||||
# Download wheels
|
|
||||||
.buildkite/scripts/cache-rocm-base-wheels.sh download
|
|
||||||
|
|
||||||
# Save ECR tag for downstream jobs
|
|
||||||
buildkite-agent meta-data set "rocm-base-image-tag" "$${ECR_CACHE_TAG}"
|
|
||||||
|
|
||||||
# Scenario 2: Full rebuild needed
|
|
||||||
else
|
|
||||||
echo ""
|
|
||||||
echo " CACHE MISS - Building from scratch..."
|
|
||||||
echo ""
|
|
||||||
|
|
||||||
# Build full base image and push to ECR
|
|
||||||
DOCKER_BUILDKIT=1 docker buildx build \
|
|
||||||
--file docker/Dockerfile.rocm_base \
|
|
||||||
--tag "$${ECR_CACHE_TAG}" \
|
|
||||||
--build-arg USE_SCCACHE=1 \
|
|
||||||
--build-arg SCCACHE_BUCKET_NAME=vllm-build-sccache \
|
|
||||||
--build-arg SCCACHE_REGION_NAME=us-west-2 \
|
|
||||||
--build-arg SCCACHE_S3_NO_CREDENTIALS=0 \
|
|
||||||
--push \
|
|
||||||
.
|
|
||||||
|
|
||||||
# Build wheel extraction stage
|
|
||||||
DOCKER_BUILDKIT=1 docker buildx build \
|
|
||||||
--file docker/Dockerfile.rocm_base \
|
|
||||||
--tag rocm-base-debs:$${BUILDKITE_BUILD_NUMBER} \
|
|
||||||
--target debs_wheel_release \
|
|
||||||
--build-arg USE_SCCACHE=1 \
|
|
||||||
--build-arg SCCACHE_BUCKET_NAME=vllm-build-sccache \
|
|
||||||
--build-arg SCCACHE_REGION_NAME=us-west-2 \
|
|
||||||
--build-arg SCCACHE_S3_NO_CREDENTIALS=0 \
|
|
||||||
--load \
|
|
||||||
.
|
|
||||||
|
|
||||||
# Extract and upload wheels
|
|
||||||
mkdir -p artifacts/rocm-base-wheels
|
|
||||||
cid=$(docker create rocm-base-debs:$${BUILDKITE_BUILD_NUMBER})
|
|
||||||
docker cp $${cid}:/app/debs/. artifacts/rocm-base-wheels/
|
|
||||||
docker rm $${cid}
|
|
||||||
|
|
||||||
.buildkite/scripts/cache-rocm-base-wheels.sh upload
|
|
||||||
|
|
||||||
# Cache base docker image to ECR
|
|
||||||
docker push "$${ECR_CACHE_TAG}"
|
|
||||||
|
|
||||||
buildkite-agent meta-data set "rocm-base-image-tag" "$${ECR_CACHE_TAG}"
|
|
||||||
|
|
||||||
echo ""
|
|
||||||
echo " Build complete - Image and wheels cached"
|
|
||||||
fi
|
|
||||||
|
|
||||||
artifact_paths:
|
|
||||||
- "artifacts/rocm-base-wheels/*.whl"
|
|
||||||
env:
|
|
||||||
DOCKER_BUILDKIT: "1"
|
DOCKER_BUILDKIT: "1"
|
||||||
S3_BUCKET: "vllm-wheels"
|
S3_BUCKET: "vllm-wheels"
|
||||||
|
DOCKERHUB_USERNAME: "vllmbot"
|
||||||
# ROCm Job 2: Build vLLM ROCm Wheel
|
commands: &rocm_base_commands
|
||||||
- label: ":python: Build vLLM ROCm Wheel - x86_64"
|
|
||||||
id: build-rocm-vllm-wheel
|
|
||||||
depends_on:
|
|
||||||
- step: build-rocm-base-wheels
|
|
||||||
allow_failure: false
|
|
||||||
agents:
|
|
||||||
queue: cpu_queue_release
|
|
||||||
timeout_in_minutes: 180
|
|
||||||
commands:
|
|
||||||
# Download artifacts and prepare Docker image
|
|
||||||
- |
|
- |
|
||||||
set -euo pipefail
|
set -euo pipefail
|
||||||
|
source .buildkite/scripts/rocm/stack.sh "$${ROCM_BASE_DOCKERFILE}"
|
||||||
# Ensure git tags are up-to-date (Buildkite's default fetch doesn't update tags)
|
SCCACHE_ARGS=(--build-arg USE_SCCACHE=1 --build-arg SCCACHE_BUCKET_NAME=vllm-build-sccache
|
||||||
# This fixes version detection when tags are moved/force-pushed
|
--build-arg SCCACHE_REGION_NAME=us-west-2 --build-arg SCCACHE_S3_NO_CREDENTIALS=0)
|
||||||
echo "Fetching latest tags from origin..."
|
|
||||||
git fetch --tags --force origin
|
|
||||||
|
|
||||||
# Log tag information for debugging version detection
|
|
||||||
echo "========================================"
|
|
||||||
echo "Git Tag Verification"
|
|
||||||
echo "========================================"
|
|
||||||
echo "Current HEAD: $(git rev-parse HEAD)"
|
|
||||||
echo "git describe --tags: $(git describe --tags 2>/dev/null || echo 'No tags found')"
|
|
||||||
echo ""
|
|
||||||
echo "Recent tags (pointing to commits near HEAD):"
|
|
||||||
git tag -l --sort=-creatordate | head -5
|
|
||||||
echo "setuptools_scm version detection:"
|
|
||||||
pip install -q setuptools_scm 2>/dev/null || true
|
|
||||||
python3 -c "import setuptools_scm; print(' Detected version:', setuptools_scm.get_version())" 2>/dev/null || echo " (setuptools_scm not available in this environment)"
|
|
||||||
echo "========================================"
|
|
||||||
|
|
||||||
# Download wheel artifacts from current build
|
|
||||||
echo "Downloading wheel artifacts from current build"
|
|
||||||
buildkite-agent artifact download "artifacts/rocm-base-wheels/*.whl" .
|
|
||||||
|
|
||||||
# Get ECR image tag from metadata (set by build-rocm-base-wheels)
|
|
||||||
ECR_IMAGE_TAG="$$(buildkite-agent meta-data get rocm-base-image-tag 2>/dev/null || echo '')"
|
|
||||||
if [ -z "$${ECR_IMAGE_TAG}" ]; then
|
|
||||||
echo "ERROR: rocm-base-image-tag metadata not found"
|
|
||||||
echo "This should have been set by the build-rocm-base-wheels job"
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
echo "Pulling base Docker image from ECR: $${ECR_IMAGE_TAG}"
|
|
||||||
|
|
||||||
# Login to ECR
|
|
||||||
aws ecr-public get-login-password --region us-east-1 | \
|
aws ecr-public get-login-password --region us-east-1 | \
|
||||||
docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7
|
docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7
|
||||||
|
|
||||||
# Pull base Docker image from ECR
|
# Base image, cached in ECR by the base Dockerfile's hash
|
||||||
docker pull "$${ECR_IMAGE_TAG}"
|
if docker manifest inspect "$${ROCM_STACK_ECR_BASE}" > /dev/null 2>&1; then
|
||||||
|
echo "ECR image cache HIT: $${ROCM_STACK_ECR_BASE}"
|
||||||
|
else
|
||||||
|
docker buildx build --file "$${ROCM_BASE_DOCKERFILE}" --tag "$${ROCM_STACK_ECR_BASE}" \
|
||||||
|
"$${SCCACHE_ARGS[@]}" --push .
|
||||||
|
fi
|
||||||
|
|
||||||
echo "Loaded base image: $${ECR_IMAGE_TAG}"
|
# Base wheels, cached in S3 (see cache-rocm-base-wheels.sh)
|
||||||
|
CACHE=.buildkite/scripts/cache-rocm-base-wheels.sh
|
||||||
|
if [ "$$($${CACHE} "$${ROCM_BASE_DOCKERFILE}" check)" = "hit" ]; then
|
||||||
|
$${CACHE} "$${ROCM_BASE_DOCKERFILE}" download
|
||||||
|
else
|
||||||
|
DEBS="rocm-base-debs:$${BUILDKITE_BUILD_NUMBER}-$${ROCM_STACK_VARIANT}"
|
||||||
|
docker buildx build --file "$${ROCM_BASE_DOCKERFILE}" --tag "$${DEBS}" \
|
||||||
|
--target debs_wheel_release "$${SCCACHE_ARGS[@]}" --load .
|
||||||
|
mkdir -p "$${ROCM_STACK_BASE_WHEELS_DIR}"
|
||||||
|
cid=$$(docker create "$${DEBS}")
|
||||||
|
docker cp "$${cid}":/app/debs/. "$${ROCM_STACK_BASE_WHEELS_DIR}/"
|
||||||
|
docker rm "$${cid}"
|
||||||
|
$${CACHE} "$${ROCM_BASE_DOCKERFILE}" upload
|
||||||
|
fi
|
||||||
|
buildkite-agent artifact upload "$${ROCM_STACK_BASE_WHEELS_DIR}/*.whl"
|
||||||
|
|
||||||
# Prepare base wheels for Docker build context
|
- label: ":python: Build vLLM ROCm 10.0 Wheel - x86_64"
|
||||||
|
id: build-rocm100-vllm-wheel
|
||||||
|
depends_on: build-rocm100-base
|
||||||
|
agents: *rocm_build_agents
|
||||||
|
timeout_in_minutes: 180
|
||||||
|
env: *rocm100_env
|
||||||
|
commands: &rocm_vllm_wheel_commands
|
||||||
|
- |
|
||||||
|
set -euo pipefail
|
||||||
|
source .buildkite/scripts/rocm/stack.sh "$${ROCM_BASE_DOCKERFILE}"
|
||||||
|
# Buildkite's default fetch doesn't update moved tags; version detection needs them
|
||||||
|
git fetch --tags --force origin
|
||||||
|
buildkite-agent artifact download "$${ROCM_STACK_BASE_WHEELS_DIR}/*.whl" .
|
||||||
|
aws ecr-public get-login-password --region us-east-1 | \
|
||||||
|
docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7
|
||||||
|
docker pull "$${ROCM_STACK_ECR_BASE}"
|
||||||
mkdir -p docker/context/base-wheels
|
mkdir -p docker/context/base-wheels
|
||||||
touch docker/context/base-wheels/.keep
|
touch docker/context/base-wheels/.keep
|
||||||
cp artifacts/rocm-base-wheels/*.whl docker/context/base-wheels/
|
cp "$${ROCM_STACK_BASE_WHEELS_DIR}"/*.whl docker/context/base-wheels/
|
||||||
echo "Base wheels for vLLM build:"
|
docker build --file "$${ROCM_STACK_DOCKERFILE}" --target export_vllm_wheel_release \
|
||||||
ls -lh docker/context/base-wheels/
|
|
||||||
|
|
||||||
echo "========================================"
|
|
||||||
echo "Building vLLM wheel with:"
|
|
||||||
echo " BUILDKITE_COMMIT: $${BUILDKITE_COMMIT}"
|
|
||||||
echo " BUILDKITE_BRANCH: $${BUILDKITE_BRANCH}"
|
|
||||||
echo " BASE_IMAGE: $${ECR_IMAGE_TAG}"
|
|
||||||
echo "========================================"
|
|
||||||
|
|
||||||
# Build vLLM wheel using local checkout (REMOTE_VLLM=0)
|
|
||||||
DOCKER_BUILDKIT=1 docker build \
|
|
||||||
--file docker/Dockerfile.rocm \
|
|
||||||
--target export_vllm_wheel_release \
|
|
||||||
--output type=local,dest=rocm-dist \
|
--output type=local,dest=rocm-dist \
|
||||||
--build-arg BASE_IMAGE="$${ECR_IMAGE_TAG}" \
|
--build-arg BASE_IMAGE="$${ROCM_STACK_ECR_BASE}" --build-arg REMOTE_VLLM=0 \
|
||||||
--build-arg REMOTE_VLLM=0 \
|
--build-arg GIT_REPO_CHECK=1 --build-arg USE_SCCACHE=1 \
|
||||||
--build-arg GIT_REPO_CHECK=1 \
|
|
||||||
--build-arg USE_SCCACHE=1 \
|
|
||||||
--build-arg SCCACHE_BUCKET_NAME=vllm-build-sccache \
|
--build-arg SCCACHE_BUCKET_NAME=vllm-build-sccache \
|
||||||
--build-arg SCCACHE_REGION_NAME=us-west-2 \
|
--build-arg SCCACHE_REGION_NAME=us-west-2 --build-arg SCCACHE_S3_NO_CREDENTIALS=0 .
|
||||||
--build-arg SCCACHE_S3_NO_CREDENTIALS=0 \
|
mkdir -p "$${ROCM_STACK_VLLM_WHEEL_DIR}"
|
||||||
.
|
cp rocm-dist/*.whl "$${ROCM_STACK_VLLM_WHEEL_DIR}/"
|
||||||
echo "Built vLLM wheel:"
|
buildkite-agent artifact upload "$${ROCM_STACK_VLLM_WHEEL_DIR}/*.whl"
|
||||||
ls -lh rocm-dist/*.whl
|
|
||||||
# Copy wheel to artifacts directory
|
|
||||||
mkdir -p artifacts/rocm-vllm-wheel
|
|
||||||
cp rocm-dist/*.whl artifacts/rocm-vllm-wheel/
|
|
||||||
echo "Final vLLM wheel:"
|
|
||||||
ls -lh artifacts/rocm-vllm-wheel/
|
|
||||||
artifact_paths:
|
|
||||||
- "artifacts/rocm-vllm-wheel/*.whl"
|
|
||||||
env:
|
|
||||||
DOCKER_BUILDKIT: "1"
|
|
||||||
S3_BUCKET: "vllm-wheels"
|
|
||||||
|
|
||||||
# ROCm Job 3: Upload Wheels to S3
|
- label: ":s3: Upload ROCm 10.0 Wheels to S3"
|
||||||
- label: ":s3: Upload ROCm Wheels to S3"
|
id: upload-rocm100-wheels
|
||||||
id: upload-rocm-wheels
|
depends_on: build-rocm100-vllm-wheel
|
||||||
depends_on:
|
agents: *rocm_build_agents
|
||||||
- step: build-rocm-vllm-wheel
|
|
||||||
allow_failure: false
|
|
||||||
agents:
|
|
||||||
queue: cpu_queue_release
|
|
||||||
timeout_in_minutes: 60
|
timeout_in_minutes: 60
|
||||||
commands:
|
env: *rocm100_env
|
||||||
# Download all wheel artifacts and run upload
|
commands: &rocm_upload_commands
|
||||||
- |
|
- |
|
||||||
set -euo pipefail
|
set -euo pipefail
|
||||||
|
source .buildkite/scripts/rocm/stack.sh "$${ROCM_BASE_DOCKERFILE}"
|
||||||
|
buildkite-agent artifact download "$${ROCM_STACK_BASE_WHEELS_DIR}/*.whl" .
|
||||||
|
buildkite-agent artifact download "$${ROCM_STACK_VLLM_WHEEL_DIR}/*.whl" .
|
||||||
|
bash .buildkite/scripts/upload-rocm-wheels.sh "$${ROCM_BASE_DOCKERFILE}"
|
||||||
|
|
||||||
# Download artifacts from current build
|
- label: ":memo: Annotate ROCm 10.0 wheel release"
|
||||||
echo "Downloading artifacts from current build"
|
id: annotate-rocm100-release
|
||||||
buildkite-agent artifact download "artifacts/rocm-base-wheels/*.whl" .
|
depends_on: upload-rocm100-wheels
|
||||||
buildkite-agent artifact download "artifacts/rocm-vllm-wheel/*.whl" .
|
agents: *rocm_build_agents
|
||||||
|
env: *rocm100_env
|
||||||
|
commands: &rocm_annotate_commands
|
||||||
|
- bash .buildkite/scripts/annotate-rocm-release.sh "$${ROCM_BASE_DOCKERFILE}" $${ROCM_DEFAULT_ARG}
|
||||||
|
|
||||||
# # Run upload script
|
# Generate https://wheels.vllm.ai/rocm/ (the default stack's variant), so users can
|
||||||
bash .buildkite/scripts/upload-rocm-wheels.sh
|
# `uv pip install vllm --extra-index-url https://wheels.vllm.ai/rocm/` (release only)
|
||||||
env:
|
|
||||||
DOCKER_BUILDKIT: "1"
|
|
||||||
S3_BUCKET: "vllm-wheels"
|
|
||||||
|
|
||||||
# ROCm Job 4: Annotate ROCm Wheel Release
|
|
||||||
- label: ":memo: Annotate ROCm wheel release"
|
|
||||||
id: annotate-rocm-release
|
|
||||||
depends_on:
|
|
||||||
- upload-rocm-wheels
|
|
||||||
agents:
|
|
||||||
queue: cpu_queue_release
|
|
||||||
commands:
|
|
||||||
- "bash .buildkite/scripts/annotate-rocm-release.sh"
|
|
||||||
env:
|
|
||||||
S3_BUCKET: "vllm-wheels"
|
|
||||||
|
|
||||||
# ROCm Job 5: Generate Root Index for ROCm Wheels (for release only)
|
|
||||||
# This is the job to create https://wheels.vllm.ai/rocm/ index allowing
|
|
||||||
# users to install with `uv pip install vllm --extra-index-url https://wheels.vllm.ai/rocm/`
|
|
||||||
- block: "Generate Root Index for ROCm Wheels for Release"
|
- block: "Generate Root Index for ROCm Wheels for Release"
|
||||||
key: block-generate-root-index-rocm-wheels
|
key: block-generate-root-index-rocm-wheels
|
||||||
depends_on: upload-rocm-wheels
|
depends_on:
|
||||||
|
- upload-rocm100-wheels
|
||||||
|
- upload-rocm72-wheels
|
||||||
|
|
||||||
- label: ":package: Generate Root Index for ROCm Wheels for Release"
|
- label: ":package: Generate Root Index for ROCm Wheels for Release"
|
||||||
depends_on: block-generate-root-index-rocm-wheels
|
depends_on: block-generate-root-index-rocm-wheels
|
||||||
id: generate-root-index-rocm-wheels
|
id: generate-root-index-rocm-wheels
|
||||||
agents:
|
agents: *rocm_build_agents
|
||||||
queue: cpu_queue_release
|
env: *rocm100_env
|
||||||
commands:
|
commands:
|
||||||
- "bash tools/vllm-rocm/generate-rocm-wheels-root-index.sh"
|
- "bash tools/vllm-rocm/generate-rocm-wheels-root-index.sh"
|
||||||
env:
|
|
||||||
S3_BUCKET: "vllm-wheels"
|
|
||||||
VARIANT: "rocm723"
|
|
||||||
|
|
||||||
# ROCm Job 6: Build ROCm Release Docker Image
|
- label: ":docker: Build release image - x86_64 - ROCm 10.0"
|
||||||
- label: ":docker: Build release image - x86_64 - ROCm"
|
id: build-rocm100-release-image
|
||||||
id: build-rocm-release-image
|
|
||||||
depends_on:
|
depends_on:
|
||||||
- step: block-build-release-images
|
- step: block-build-release-images
|
||||||
allow_failure: true
|
allow_failure: true
|
||||||
- step: build-rocm-base-wheels
|
- step: build-rocm100-base
|
||||||
allow_failure: false
|
allow_failure: false
|
||||||
agents:
|
agents: *rocm_build_agents
|
||||||
queue: cpu_queue_release
|
timeout_in_minutes: 180
|
||||||
timeout_in_minutes: 60
|
env: *rocm100_env
|
||||||
commands:
|
commands: &rocm_release_image_commands
|
||||||
- |
|
- |
|
||||||
set -euo pipefail
|
set -euo pipefail
|
||||||
|
source .buildkite/scripts/rocm/stack.sh "$${ROCM_BASE_DOCKERFILE}"
|
||||||
# Login to ECR
|
|
||||||
aws ecr-public get-login-password --region us-east-1 | \
|
aws ecr-public get-login-password --region us-east-1 | \
|
||||||
docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7
|
docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7
|
||||||
|
docker pull "$${ROCM_STACK_ECR_BASE}"
|
||||||
# Get ECR image tag from metadata (set by build-rocm-base-wheels)
|
docker build --file "$${ROCM_STACK_DOCKERFILE}" --target vllm-openai \
|
||||||
ECR_IMAGE_TAG="$$(buildkite-agent meta-data get rocm-base-image-tag 2>/dev/null || echo '')"
|
--tag "$${ROCM_STACK_ECR_IMAGE}" --progress plain \
|
||||||
if [ -z "$${ECR_IMAGE_TAG}" ]; then
|
--build-arg max_jobs=16 --build-arg BASE_IMAGE="$${ROCM_STACK_ECR_BASE}" \
|
||||||
echo "ERROR: rocm-base-image-tag metadata not found"
|
--build-arg INSTALL_LMCACHE=true --build-arg USE_SCCACHE=1 \
|
||||||
echo "This should have been set by the build-rocm-base-wheels job"
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
echo "Pulling base Docker image from ECR: $${ECR_IMAGE_TAG}"
|
|
||||||
|
|
||||||
# Pull base Docker image from ECR
|
|
||||||
docker pull "$${ECR_IMAGE_TAG}"
|
|
||||||
|
|
||||||
echo "Loaded base image: $${ECR_IMAGE_TAG}"
|
|
||||||
|
|
||||||
# Pass the base image ECR tag to downstream steps (nightly publish)
|
|
||||||
buildkite-agent meta-data set "rocm-base-ecr-tag" "$${ECR_IMAGE_TAG}"
|
|
||||||
|
|
||||||
echo "========================================"
|
|
||||||
echo "Building vLLM ROCm release image with:"
|
|
||||||
echo " BASE_IMAGE: $${ECR_IMAGE_TAG}"
|
|
||||||
echo " BUILDKITE_COMMIT: $${BUILDKITE_COMMIT}"
|
|
||||||
echo "========================================"
|
|
||||||
|
|
||||||
# Build vLLM ROCm release image using cached base
|
|
||||||
DOCKER_BUILDKIT=1 docker build \
|
|
||||||
--build-arg max_jobs=16 \
|
|
||||||
--build-arg BASE_IMAGE="$${ECR_IMAGE_TAG}" \
|
|
||||||
--build-arg USE_SCCACHE=1 \
|
|
||||||
--build-arg SCCACHE_BUCKET_NAME=vllm-build-sccache \
|
--build-arg SCCACHE_BUCKET_NAME=vllm-build-sccache \
|
||||||
--build-arg SCCACHE_REGION_NAME=us-west-2 \
|
--build-arg SCCACHE_REGION_NAME=us-west-2 --build-arg SCCACHE_S3_NO_CREDENTIALS=0 .
|
||||||
--build-arg SCCACHE_S3_NO_CREDENTIALS=0 \
|
docker push "$${ROCM_STACK_ECR_IMAGE}"
|
||||||
--build-arg INSTALL_LMCACHE=true \
|
|
||||||
--tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$${BUILDKITE_COMMIT}-rocm \
|
|
||||||
--target vllm-openai \
|
|
||||||
--progress plain \
|
|
||||||
-f docker/Dockerfile.rocm .
|
|
||||||
|
|
||||||
# Push to ECR
|
- label: "Publish nightly ROCm 10.0 image to DockerHub"
|
||||||
docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$${BUILDKITE_COMMIT}-rocm
|
id: publish-rocm100-nightly
|
||||||
|
depends_on: build-rocm100-release-image
|
||||||
|
if: build.env("NIGHTLY") == "1"
|
||||||
|
agents: &rocm_publish_agents
|
||||||
|
queue: small_cpu_queue_release
|
||||||
|
env: *rocm100_env
|
||||||
|
commands: &rocm_publish_nightly_commands
|
||||||
|
- bash .buildkite/scripts/push-nightly-builds-rocm.sh "$${ROCM_BASE_DOCKERFILE}" $${ROCM_DEFAULT_ARG}
|
||||||
|
plugins: &rocm_dockerhub_login
|
||||||
|
- docker-login#v3.0.0:
|
||||||
|
username: vllmbot
|
||||||
|
password-env: DOCKERHUB_TOKEN
|
||||||
|
|
||||||
echo ""
|
- group: "Build ROCm 7.2 Wheel / Image"
|
||||||
echo " Successfully built and pushed ROCm release image"
|
key: "build-rocm72"
|
||||||
echo " Image: public.ecr.aws/q9t5s3a7/vllm-release-repo:$${BUILDKITE_COMMIT}-rocm"
|
depends_on: ~
|
||||||
echo ""
|
steps:
|
||||||
env:
|
- label: ":rocm: Build ROCm 7.2 Base Image & Wheels"
|
||||||
|
id: build-rocm72-base
|
||||||
|
depends_on: ~
|
||||||
|
agents: *rocm_build_agents
|
||||||
|
timeout_in_minutes: 360
|
||||||
|
env: &rocm72_env
|
||||||
|
ROCM_BASE_DOCKERFILE: "docker/Dockerfile.rocm_72_base"
|
||||||
|
ROCM_DEFAULT_ARG: ""
|
||||||
DOCKER_BUILDKIT: "1"
|
DOCKER_BUILDKIT: "1"
|
||||||
S3_BUCKET: "vllm-wheels"
|
S3_BUCKET: "vllm-wheels"
|
||||||
|
DOCKERHUB_USERNAME: "vllmbot"
|
||||||
|
commands: *rocm_base_commands
|
||||||
|
|
||||||
|
- label: ":python: Build vLLM ROCm 7.2 Wheel - x86_64"
|
||||||
|
id: build-rocm72-vllm-wheel
|
||||||
|
depends_on: build-rocm72-base
|
||||||
|
agents: *rocm_build_agents
|
||||||
|
timeout_in_minutes: 180
|
||||||
|
env: *rocm72_env
|
||||||
|
commands: *rocm_vllm_wheel_commands
|
||||||
|
|
||||||
|
- label: ":s3: Upload ROCm 7.2 Wheels to S3"
|
||||||
|
id: upload-rocm72-wheels
|
||||||
|
depends_on: build-rocm72-vllm-wheel
|
||||||
|
agents: *rocm_build_agents
|
||||||
|
timeout_in_minutes: 60
|
||||||
|
env: *rocm72_env
|
||||||
|
commands: *rocm_upload_commands
|
||||||
|
|
||||||
|
- label: ":memo: Annotate ROCm 7.2 wheel release"
|
||||||
|
id: annotate-rocm72-release
|
||||||
|
depends_on: upload-rocm72-wheels
|
||||||
|
agents: *rocm_build_agents
|
||||||
|
env: *rocm72_env
|
||||||
|
commands: *rocm_annotate_commands
|
||||||
|
|
||||||
|
- label: ":docker: Build release image - x86_64 - ROCm 7.2"
|
||||||
|
id: build-rocm72-release-image
|
||||||
|
depends_on:
|
||||||
|
- step: block-build-release-images
|
||||||
|
allow_failure: true
|
||||||
|
- step: build-rocm72-base
|
||||||
|
allow_failure: false
|
||||||
|
agents: *rocm_build_agents
|
||||||
|
timeout_in_minutes: 180
|
||||||
|
env: *rocm72_env
|
||||||
|
commands: *rocm_release_image_commands
|
||||||
|
|
||||||
|
- label: "Publish nightly ROCm 7.2 image to DockerHub"
|
||||||
|
id: publish-rocm72-nightly
|
||||||
|
depends_on: build-rocm72-release-image
|
||||||
|
if: build.env("NIGHTLY") == "1"
|
||||||
|
agents: *rocm_publish_agents
|
||||||
|
env: *rocm72_env
|
||||||
|
commands: *rocm_publish_nightly_commands
|
||||||
|
plugins: *rocm_dockerhub_login
|
||||||
|
|
||||||
- label: "Publish nightly XPU image to DockerHub"
|
- label: "Publish nightly XPU image to DockerHub"
|
||||||
depends_on:
|
depends_on:
|
||||||
@@ -1058,163 +985,6 @@ steps:
|
|||||||
DOCKER_BUILDKIT: "1"
|
DOCKER_BUILDKIT: "1"
|
||||||
DOCKERHUB_USERNAME: "vllmbot"
|
DOCKERHUB_USERNAME: "vllmbot"
|
||||||
|
|
||||||
- label: "Publish nightly ROCm image to DockerHub"
|
|
||||||
depends_on:
|
|
||||||
- build-rocm-release-image
|
|
||||||
if: build.env("NIGHTLY") == "1"
|
|
||||||
agents:
|
|
||||||
queue: small_cpu_queue_release
|
|
||||||
commands:
|
|
||||||
- "bash .buildkite/scripts/push-nightly-builds-rocm.sh"
|
|
||||||
# Clean up old nightly builds (keep only last 14)
|
|
||||||
- "bash .buildkite/scripts/cleanup-nightly-builds.sh nightly- vllm/vllm-openai-rocm"
|
|
||||||
- "bash .buildkite/scripts/cleanup-nightly-builds.sh base-nightly- vllm/vllm-openai-rocm"
|
|
||||||
plugins:
|
|
||||||
- docker-login#v3.0.0:
|
|
||||||
username: vllmbot
|
|
||||||
password-env: DOCKERHUB_TOKEN
|
|
||||||
env:
|
|
||||||
DOCKER_BUILDKIT: "1"
|
|
||||||
DOCKERHUB_USERNAME: "vllmbot"
|
|
||||||
|
|
||||||
# =============================================================================
|
|
||||||
# ROCk Release Pipeline (x86_64 only)
|
|
||||||
# =============================================================================
|
|
||||||
#
|
|
||||||
# Same shape as the ROCm pipeline above (Jobs 1 and 6 only), but built from
|
|
||||||
# docker/Dockerfile.rock_base and docker/Dockerfile.rock, which install the
|
|
||||||
# ROCm SDK from TheRock wheels instead of the ROCm apt repos.
|
|
||||||
#
|
|
||||||
# Note: ROCm SDK version is determined by ROCM_SDK_VERSION in
|
|
||||||
# docker/Dockerfile.rock_base
|
|
||||||
#
|
|
||||||
# =============================================================================
|
|
||||||
|
|
||||||
- group: "Build ROCk Image"
|
|
||||||
key: "build-rock-image"
|
|
||||||
depends_on: ~
|
|
||||||
steps:
|
|
||||||
# ROCk Job 1: Build ROCk Base Image (with ECR caching)
|
|
||||||
- label: ":rocm: Build ROCk Base Image"
|
|
||||||
id: build-rock-base-image
|
|
||||||
depends_on: ~
|
|
||||||
agents:
|
|
||||||
queue: cpu_queue_release
|
|
||||||
timeout_in_minutes: 360
|
|
||||||
commands:
|
|
||||||
- |
|
|
||||||
set -euo pipefail
|
|
||||||
|
|
||||||
# The SDK version, torch wheels and component branches all live in
|
|
||||||
# the Dockerfile, so its hash is the cache key.
|
|
||||||
CACHE_KEY=$$(sha256sum docker/Dockerfile.rock_base | cut -c1-16)
|
|
||||||
ECR_CACHE_TAG="public.ecr.aws/q9t5s3a7/vllm-release-repo:$${CACHE_KEY}-rock-base"
|
|
||||||
|
|
||||||
echo "========================================"
|
|
||||||
echo "ROCk Base Build Configuration"
|
|
||||||
echo "========================================"
|
|
||||||
echo " CACHE_KEY: $${CACHE_KEY}"
|
|
||||||
echo " ECR_CACHE_TAG: $${ECR_CACHE_TAG}"
|
|
||||||
echo "========================================"
|
|
||||||
|
|
||||||
# Login to ECR
|
|
||||||
aws ecr-public get-login-password --region us-east-1 | \
|
|
||||||
docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7
|
|
||||||
|
|
||||||
if docker manifest inspect "$${ECR_CACHE_TAG}" > /dev/null 2>&1; then
|
|
||||||
echo "ECR image cache HIT"
|
|
||||||
else
|
|
||||||
echo "CACHE MISS - Building from scratch..."
|
|
||||||
|
|
||||||
DOCKER_BUILDKIT=1 docker buildx build \
|
|
||||||
--file docker/Dockerfile.rock_base \
|
|
||||||
--tag "$${ECR_CACHE_TAG}" \
|
|
||||||
--build-arg USE_SCCACHE=1 \
|
|
||||||
--build-arg SCCACHE_BUCKET_NAME=vllm-build-sccache \
|
|
||||||
--build-arg SCCACHE_REGION_NAME=us-west-2 \
|
|
||||||
--build-arg SCCACHE_S3_NO_CREDENTIALS=0 \
|
|
||||||
--push \
|
|
||||||
.
|
|
||||||
fi
|
|
||||||
|
|
||||||
# Save ECR tag for downstream jobs
|
|
||||||
buildkite-agent meta-data set "rock-base-image-tag" "$${ECR_CACHE_TAG}"
|
|
||||||
env:
|
|
||||||
DOCKER_BUILDKIT: "1"
|
|
||||||
|
|
||||||
# ROCk Job 2: Build ROCk Release Docker Image
|
|
||||||
- label: ":docker: Build release image - x86_64 - ROCk"
|
|
||||||
id: build-rock-release-image
|
|
||||||
depends_on:
|
|
||||||
- step: block-build-release-images
|
|
||||||
allow_failure: true
|
|
||||||
- step: build-rock-base-image
|
|
||||||
allow_failure: false
|
|
||||||
agents:
|
|
||||||
queue: cpu_queue_release
|
|
||||||
timeout_in_minutes: 180
|
|
||||||
commands:
|
|
||||||
- |
|
|
||||||
set -euo pipefail
|
|
||||||
|
|
||||||
# Login to ECR
|
|
||||||
aws ecr-public get-login-password --region us-east-1 | \
|
|
||||||
docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7
|
|
||||||
|
|
||||||
ECR_IMAGE_TAG="$$(buildkite-agent meta-data get rock-base-image-tag 2>/dev/null || echo '')"
|
|
||||||
if [ -z "$${ECR_IMAGE_TAG}" ]; then
|
|
||||||
echo "ERROR: rock-base-image-tag metadata not found"
|
|
||||||
echo "This should have been set by the build-rock-base-image job"
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
docker pull "$${ECR_IMAGE_TAG}"
|
|
||||||
|
|
||||||
# Pass the base image ECR tag to downstream steps (nightly publish)
|
|
||||||
buildkite-agent meta-data set "rock-base-ecr-tag" "$${ECR_IMAGE_TAG}"
|
|
||||||
|
|
||||||
echo "========================================"
|
|
||||||
echo "Building vLLM ROCk release image with:"
|
|
||||||
echo " BASE_IMAGE: $${ECR_IMAGE_TAG}"
|
|
||||||
echo " BUILDKITE_COMMIT: $${BUILDKITE_COMMIT}"
|
|
||||||
echo "========================================"
|
|
||||||
|
|
||||||
DOCKER_BUILDKIT=1 docker build \
|
|
||||||
--build-arg max_jobs=16 \
|
|
||||||
--build-arg BASE_IMAGE="$${ECR_IMAGE_TAG}" \
|
|
||||||
--build-arg USE_SCCACHE=1 \
|
|
||||||
--build-arg SCCACHE_BUCKET_NAME=vllm-build-sccache \
|
|
||||||
--build-arg SCCACHE_REGION_NAME=us-west-2 \
|
|
||||||
--build-arg SCCACHE_S3_NO_CREDENTIALS=0 \
|
|
||||||
--build-arg INSTALL_LMCACHE=true \
|
|
||||||
--tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$${BUILDKITE_COMMIT}-rock \
|
|
||||||
--target vllm-openai \
|
|
||||||
--progress plain \
|
|
||||||
-f docker/Dockerfile.rock .
|
|
||||||
|
|
||||||
docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$${BUILDKITE_COMMIT}-rock
|
|
||||||
env:
|
|
||||||
DOCKER_BUILDKIT: "1"
|
|
||||||
|
|
||||||
- label: "Publish nightly ROCk image to DockerHub"
|
|
||||||
depends_on:
|
|
||||||
- build-rock-release-image
|
|
||||||
if: build.env("NIGHTLY") == "1"
|
|
||||||
agents:
|
|
||||||
queue: small_cpu_queue_release
|
|
||||||
commands:
|
|
||||||
- "bash .buildkite/scripts/push-nightly-builds-rocm.sh rock rocm100"
|
|
||||||
# Clean up old nightly builds (keep only last 14)
|
|
||||||
- "bash .buildkite/scripts/cleanup-nightly-builds.sh nightly-rocm100- vllm/vllm-openai-rocm"
|
|
||||||
- "bash .buildkite/scripts/cleanup-nightly-builds.sh base-nightly-rocm100- vllm/vllm-openai-rocm"
|
|
||||||
plugins:
|
|
||||||
- docker-login#v3.0.0:
|
|
||||||
username: vllmbot
|
|
||||||
password-env: DOCKERHUB_TOKEN
|
|
||||||
env:
|
|
||||||
DOCKER_BUILDKIT: "1"
|
|
||||||
DOCKERHUB_USERNAME: "vllmbot"
|
|
||||||
|
|
||||||
# =============================================================================
|
# =============================================================================
|
||||||
# Publish to DockerHub and PyPI (at the end so all builds complete first)
|
# Publish to DockerHub and PyPI (at the end so all builds complete first)
|
||||||
# =============================================================================
|
# =============================================================================
|
||||||
@@ -1227,7 +997,8 @@ steps:
|
|||||||
- create-multi-arch-manifest-ubuntu2404
|
- create-multi-arch-manifest-ubuntu2404
|
||||||
- create-multi-arch-manifest-cuda-12-9-ubuntu2404
|
- create-multi-arch-manifest-cuda-12-9-ubuntu2404
|
||||||
- create-manifest-xpu
|
- create-manifest-xpu
|
||||||
- build-rocm-release-image
|
- build-rocm100-release-image
|
||||||
|
- build-rocm72-release-image
|
||||||
- input-release-version
|
- input-release-version
|
||||||
# Wait for CPU builds if their block steps were unblocked, so publish
|
# Wait for CPU builds if their block steps were unblocked, so publish
|
||||||
# doesn't race the in-progress CPU build. allow_failure lets publish
|
# doesn't race the in-progress CPU build. allow_failure lets publish
|
||||||
@@ -1252,6 +1023,7 @@ steps:
|
|||||||
- "cuda-13-0-ubuntu-24-04"
|
- "cuda-13-0-ubuntu-24-04"
|
||||||
- "cuda-12-9-ubuntu-24-04"
|
- "cuda-12-9-ubuntu-24-04"
|
||||||
- "rocm"
|
- "rocm"
|
||||||
|
- "rocm72"
|
||||||
- "xpu"
|
- "xpu"
|
||||||
- "cpu"
|
- "cpu"
|
||||||
plugins:
|
plugins:
|
||||||
|
|||||||
@@ -2,15 +2,23 @@
|
|||||||
# SPDX-License-Identifier: Apache-2.0
|
# SPDX-License-Identifier: Apache-2.0
|
||||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||||
#
|
#
|
||||||
# Generate Buildkite annotation for ROCm wheel release
|
# Generate Buildkite annotation for a ROCm stack's wheel release.
|
||||||
|
#
|
||||||
|
# Usage: annotate-rocm-release.sh <base-dockerfile> [--default]
|
||||||
|
# base-dockerfile e.g. docker/Dockerfile.rocm_base or docker/Dockerfile.rocm_72_base
|
||||||
|
# --default the stack also owns the plain :latest / :v<ver> Docker Hub tags
|
||||||
set -ex
|
set -ex
|
||||||
|
|
||||||
# Extract build configuration from Dockerfile.rocm_base (single source of truth)
|
# shellcheck source=.buildkite/scripts/rocm/stack.sh
|
||||||
# Extract ROCm version dynamically from Dockerfile.rocm_base
|
source "$(dirname "${BASH_SOURCE[0]}")/rocm/stack.sh" "${1:?Usage: $0 <base-dockerfile> [--default]}"
|
||||||
# BASE_IMAGE format: rocm/dev-ubuntu-22.04:7.0-complete -> extracts "7.0"
|
TAG_VARIANTS=("-${ROCM_STACK_VARIANT}")
|
||||||
ROCM_VERSION=$(grep -E '^ARG BASE_IMAGE=' docker/Dockerfile.rocm_base | sed -E 's/.*:([0-9]+\.[0-9]+).*/\1/' || echo "unknown")
|
if [[ "${2:-}" == "--default" ]]; then
|
||||||
PYTHON_VERSION=$(grep '^ARG PYTHON_VERSION=' docker/Dockerfile.rocm_base | sed 's/^ARG PYTHON_VERSION=//')
|
TAG_VARIANTS=("" "-${ROCM_STACK_VARIANT}")
|
||||||
PYTORCH_ROCM_ARCH=$(grep '^ARG PYTORCH_ROCM_ARCH=' docker/Dockerfile.rocm_base | sed 's/^ARG PYTORCH_ROCM_ARCH=//')
|
fi
|
||||||
|
ROCM_VERSION="$ROCM_STACK_VERSION"
|
||||||
|
VARIANT="$ROCM_STACK_VARIANT"
|
||||||
|
PYTHON_VERSION=$(sed -nE 's/^ARG PYTHON_VERSION="?([^" ]+)"?.*/\1/p' "$ROCM_STACK_BASE_DOCKERFILE")
|
||||||
|
PYTORCH_ROCM_ARCH=$(sed -nE 's/^ARG PYTORCH_ROCM_ARCH="?([^"]+)"?.*/\1/p' "$ROCM_STACK_BASE_DOCKERFILE")
|
||||||
|
|
||||||
# Get release version, default to 1.0.0.dev for nightly/per-commit builds
|
# Get release version, default to 1.0.0.dev for nightly/per-commit builds
|
||||||
RELEASE_VERSION=$(buildkite-agent meta-data get release-version 2>/dev/null || echo "")
|
RELEASE_VERSION=$(buildkite-agent meta-data get release-version 2>/dev/null || echo "")
|
||||||
@@ -18,22 +26,32 @@ if [ -z "${RELEASE_VERSION}" ]; then
|
|||||||
RELEASE_VERSION="1.0.0.dev"
|
RELEASE_VERSION="1.0.0.dev"
|
||||||
fi
|
fi
|
||||||
|
|
||||||
ROCM_BASE_CACHE_KEY=$(.buildkite/scripts/cache-rocm-base-wheels.sh key)
|
|
||||||
|
|
||||||
# S3 URLs
|
# S3 URLs
|
||||||
S3_BUCKET="${S3_BUCKET:-vllm-wheels}"
|
S3_BUCKET="${S3_BUCKET:-vllm-wheels}"
|
||||||
S3_REGION="${AWS_DEFAULT_REGION:-us-west-2}"
|
S3_REGION="${AWS_DEFAULT_REGION:-us-west-2}"
|
||||||
S3_URL="http://${S3_BUCKET}.s3-website-${S3_REGION}.amazonaws.com"
|
S3_HOST="${S3_BUCKET}.s3-website-${S3_REGION}.amazonaws.com"
|
||||||
|
S3_URL="http://${S3_HOST}"
|
||||||
|
WHEEL_PATH="rocm/${BUILDKITE_COMMIT}/${VARIANT}-wheels/"
|
||||||
|
|
||||||
# Format ROCm version for path (e.g., "7.1" -> "rocm710")
|
DOCKER_CMDS="docker pull ${ROCM_STACK_ECR_BASE}
|
||||||
ROCM_VERSION_PATH="rocm$(echo "${ROCM_VERSION}" | tr -d '.')"
|
docker pull ${ROCM_STACK_ECR_IMAGE}"
|
||||||
ROCM_PATH="rocm/${BUILDKITE_COMMIT}/${ROCM_VERSION_PATH}"
|
for suffix in "${TAG_VARIANTS[@]}"; do
|
||||||
buildkite-agent annotate --style 'success' --context 'rocm-release-workflow' << EOF
|
for tag in "latest${suffix}" "v${RELEASE_VERSION}${suffix}"; do
|
||||||
## ROCm Wheel and Docker Image Releases
|
DOCKER_CMDS+="
|
||||||
|
docker tag ${ROCM_STACK_ECR_BASE} vllm/vllm-openai-rocm:${tag}-base
|
||||||
|
docker tag ${ROCM_STACK_ECR_IMAGE} vllm/vllm-openai-rocm:${tag}
|
||||||
|
docker push vllm/vllm-openai-rocm:${tag}-base
|
||||||
|
docker push vllm/vllm-openai-rocm:${tag}"
|
||||||
|
done
|
||||||
|
done
|
||||||
|
|
||||||
|
buildkite-agent annotate --style 'success' --context "rocm-release-workflow-${VARIANT}" << EOF
|
||||||
|
## ROCm ${ROCM_VERSION} Wheel and Docker Image Releases
|
||||||
### Build Configuration
|
### Build Configuration
|
||||||
| Setting | Value |
|
| Setting | Value |
|
||||||
|---------|-------|
|
|---------|-------|
|
||||||
| **ROCm Version** | ${ROCM_VERSION} |
|
| **ROCm Version** | ${ROCM_VERSION} |
|
||||||
|
| **Index Variant** | ${VARIANT} |
|
||||||
| **Python Version** | ${PYTHON_VERSION} |
|
| **Python Version** | ${PYTHON_VERSION} |
|
||||||
| **GPU Architectures** | ${PYTORCH_ROCM_ARCH} |
|
| **GPU Architectures** | ${PYTORCH_ROCM_ARCH} |
|
||||||
| **Branch** | \`${BUILDKITE_BRANCH}\` |
|
| **Branch** | \`${BUILDKITE_BRANCH}\` |
|
||||||
@@ -41,49 +59,20 @@ buildkite-agent annotate --style 'success' --context 'rocm-release-workflow' <<
|
|||||||
|
|
||||||
### :package: Installation
|
### :package: Installation
|
||||||
|
|
||||||
**Install from this build (by commit):**
|
|
||||||
|
|
||||||
\`\`\`bash
|
\`\`\`bash
|
||||||
pip install vllm --extra-index-url ${S3_URL}/${ROCM_PATH}/ --trusted-host ${S3_BUCKET}.s3-website-${S3_REGION}.amazonaws.com
|
# This build (by commit)
|
||||||
|
pip install vllm --extra-index-url ${S3_URL}/rocm/${BUILDKITE_COMMIT}/${VARIANT}/ --trusted-host ${S3_HOST}
|
||||||
# Example for ROCm ${ROCM_VERSION}:
|
# Nightly (if published)
|
||||||
pip install vllm --extra-index-url ${S3_URL}/rocm/${BUILDKITE_COMMIT}/${ROCM_VERSION_PATH}/ --trusted-host ${S3_BUCKET}.s3-website-${S3_REGION}.amazonaws.com
|
pip install vllm --extra-index-url ${S3_URL}/rocm/nightly/${VARIANT}/ --trusted-host ${S3_HOST}
|
||||||
\`\`\`
|
|
||||||
|
|
||||||
**Install from nightly (if published):**
|
|
||||||
|
|
||||||
\`\`\`bash
|
|
||||||
pip install vllm --extra-index-url ${S3_URL}/rocm/nightly/ --trusted-host ${S3_BUCKET}.s3-website-${S3_REGION}.amazonaws.com
|
|
||||||
\`\`\`
|
\`\`\`
|
||||||
|
|
||||||
### :floppy_disk: Download Wheels Directly
|
### :floppy_disk: Download Wheels Directly
|
||||||
|
|
||||||
\`\`\`bash
|
\`\`\`bash
|
||||||
# List all ROCm wheels
|
aws s3 ls s3://${S3_BUCKET}/${WHEEL_PATH}
|
||||||
aws s3 ls s3://${S3_BUCKET}/rocm/${BUILDKITE_COMMIT}/${ROCM_VERSION_PATH}/
|
aws s3 cp --recursive --exclude "*" --include "*.whl" s3://${S3_BUCKET}/${WHEEL_PATH} .
|
||||||
# Download specific wheels
|
|
||||||
aws s3 cp s3://${S3_BUCKET}/rocm/${BUILDKITE_COMMIT}/${ROCM_VERSION_PATH}/vllm-*.whl .
|
|
||||||
aws s3 cp s3://${S3_BUCKET}/rocm/${BUILDKITE_COMMIT}/${ROCM_VERSION_PATH}/torch-*.whl .
|
|
||||||
aws s3 cp s3://${S3_BUCKET}/rocm/${BUILDKITE_COMMIT}/${ROCM_VERSION_PATH}/triton-*.whl .
|
|
||||||
aws s3 cp s3://${S3_BUCKET}/rocm/${BUILDKITE_COMMIT}/${ROCM_VERSION_PATH}/triton-kernels-*.whl .
|
|
||||||
aws s3 cp s3://${S3_BUCKET}/rocm/${BUILDKITE_COMMIT}/${ROCM_VERSION_PATH}/torchvision-*.whl .
|
|
||||||
aws s3 cp s3://${S3_BUCKET}/rocm/${BUILDKITE_COMMIT}/${ROCM_VERSION_PATH}/torchaudio-*.whl .
|
|
||||||
aws s3 cp s3://${S3_BUCKET}/rocm/${BUILDKITE_COMMIT}/${ROCM_VERSION_PATH}/amdsmi-*.whl .
|
|
||||||
aws s3 cp s3://${S3_BUCKET}/rocm/${BUILDKITE_COMMIT}/${ROCM_VERSION_PATH}/amd_aiter-*.whl .
|
|
||||||
aws s3 cp s3://${S3_BUCKET}/rocm/${BUILDKITE_COMMIT}/${ROCM_VERSION_PATH}/flash-attn-*.whl .
|
|
||||||
\`\`\`
|
\`\`\`
|
||||||
|
|
||||||
### :gear: Included Packages
|
|
||||||
- **vllm**: vLLM with ROCm support
|
|
||||||
- **torch**: PyTorch built for ROCm ${ROCM_VERSION}
|
|
||||||
- **triton**: Triton
|
|
||||||
- **triton-kernels**: Triton kernels
|
|
||||||
- **torchvision**: TorchVision for ROCm PyTorch
|
|
||||||
- **torchaudio**: Torchaudio for ROCm PyTorch
|
|
||||||
- **amdsmi**: AMD SMI Python bindings
|
|
||||||
- **amd_aiter**: Aiter for ROCm
|
|
||||||
- **flash-attn**: Flash Attention for ROCm
|
|
||||||
|
|
||||||
### :warning: Notes
|
### :warning: Notes
|
||||||
- These wheels are built for **ROCm ${ROCM_VERSION}** and will NOT work with CUDA GPUs
|
- These wheels are built for **ROCm ${ROCM_VERSION}** and will NOT work with CUDA GPUs
|
||||||
- Supported GPU architectures: ${PYTORCH_ROCM_ARCH}
|
- Supported GPU architectures: ${PYTORCH_ROCM_ARCH}
|
||||||
@@ -91,23 +80,8 @@ aws s3 cp s3://${S3_BUCKET}/rocm/${BUILDKITE_COMMIT}/${ROCM_VERSION_PATH}/flash-
|
|||||||
|
|
||||||
### :package: Docker Image Release
|
### :package: Docker Image Release
|
||||||
|
|
||||||
To download and upload the image:
|
|
||||||
|
|
||||||
\`\`\`
|
\`\`\`
|
||||||
docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${BUILDKITE_COMMIT}-rocm-base
|
${DOCKER_CMDS}
|
||||||
docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${BUILDKITE_COMMIT}-rocm
|
|
||||||
|
|
||||||
docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${ROCM_BASE_CACHE_KEY}-rocm-base vllm/vllm-openai-rocm:${BUILDKITE_COMMIT}-base
|
|
||||||
docker tag vllm/vllm-openai-rocm:${BUILDKITE_COMMIT}-base vllm/vllm-openai-rocm:latest-base
|
|
||||||
docker tag vllm/vllm-openai-rocm:${BUILDKITE_COMMIT}-base vllm/vllm-openai-rocm:v${RELEASE_VERSION}-base
|
|
||||||
docker push vllm/vllm-openai-rocm:latest-base
|
|
||||||
docker push vllm/vllm-openai-rocm:v${RELEASE_VERSION}-base
|
|
||||||
|
|
||||||
docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${BUILDKITE_COMMIT}-rocm vllm/vllm-openai-rocm:${BUILDKITE_COMMIT}
|
|
||||||
docker tag vllm/vllm-openai-rocm:${BUILDKITE_COMMIT} vllm/vllm-openai-rocm:latest
|
|
||||||
docker tag vllm/vllm-openai-rocm:${BUILDKITE_COMMIT} vllm/vllm-openai-rocm:v${RELEASE_VERSION}
|
|
||||||
docker push vllm/vllm-openai-rocm:latest
|
|
||||||
docker push vllm/vllm-openai-rocm:v${RELEASE_VERSION}
|
|
||||||
\`\`\`
|
\`\`\`
|
||||||
|
|
||||||
EOF
|
EOF
|
||||||
|
|||||||
@@ -25,6 +25,7 @@ export CMAKE_BUILD_PARALLEL_LEVEL="${CMAKE_BUILD_PARALLEL_LEVEL:-4}"
|
|||||||
|
|
||||||
uv venv --python 3.12
|
uv venv --python 3.12
|
||||||
uv pip install -r requirements/build/cpu.txt --index-strategy unsafe-best-match
|
uv pip install -r requirements/build/cpu.txt --index-strategy unsafe-best-match
|
||||||
uv build --wheel --no-build-isolation -o artifacts/dist
|
uv build --wheel --no-build-isolation -o artifacts/dist \
|
||||||
|
--config-setting=--build-option=--py-limited-api=cp38
|
||||||
|
|
||||||
ls -l artifacts/dist/*.whl
|
ls -l artifacts/dist/*.whl
|
||||||
|
|||||||
@@ -5,39 +5,33 @@
|
|||||||
# Cache helper for ROCm base wheels
|
# Cache helper for ROCm base wheels
|
||||||
#
|
#
|
||||||
# This script manages caching of pre-built ROCm base wheels (torch, triton, etc.)
|
# This script manages caching of pre-built ROCm base wheels (torch, triton, etc.)
|
||||||
# to avoid rebuilding them when Dockerfile.rocm_base hasn't changed.
|
# to avoid rebuilding them when the stack's base Dockerfile hasn't changed.
|
||||||
#
|
#
|
||||||
# Usage:
|
# Usage: cache-rocm-base-wheels.sh <base-dockerfile> <command>
|
||||||
# cache-rocm-base-wheels.sh check - Check if cache exists, outputs "hit" or "miss"
|
# base-dockerfile e.g. docker/Dockerfile.rocm_base or docker/Dockerfile.rocm_72_base
|
||||||
# cache-rocm-base-wheels.sh upload - Upload wheels to cache
|
# Commands:
|
||||||
# cache-rocm-base-wheels.sh download - Download wheels from cache
|
# check - Check if cache exists, outputs "hit" or "miss"
|
||||||
# cache-rocm-base-wheels.sh key - Output the cache key
|
# upload - Upload wheels to cache
|
||||||
|
# download - Download wheels from cache
|
||||||
|
# key - Output the cache key
|
||||||
|
# path - Output the full S3 cache path
|
||||||
#
|
#
|
||||||
# Environment variables:
|
# Environment variables:
|
||||||
# S3_BUCKET - S3 bucket name (default: vllm-wheels)
|
# S3_BUCKET - S3 bucket name (default: vllm-wheels)
|
||||||
#
|
#
|
||||||
# Note: ROCm version is determined by BASE_IMAGE in Dockerfile.rocm_base,
|
# The cache key hashes the base Dockerfile and the repo files it COPYs in, which
|
||||||
# so changes to ROCm version are captured by the Dockerfile hash.
|
# capture the ROCm version and every component pin (see rocm/stack.sh).
|
||||||
|
|
||||||
set -euo pipefail
|
set -euo pipefail
|
||||||
|
|
||||||
BUCKET="${S3_BUCKET:-vllm-wheels}"
|
BUCKET="${S3_BUCKET:-vllm-wheels}"
|
||||||
DOCKERFILE="docker/Dockerfile.rocm_base"
|
|
||||||
CACHE_PREFIX="rocm/cache"
|
CACHE_PREFIX="rocm/cache"
|
||||||
|
|
||||||
# Generate hash from Dockerfile content + build args
|
# shellcheck source=.buildkite/scripts/rocm/stack.sh
|
||||||
generate_cache_key() {
|
source "$(dirname "${BASH_SOURCE[0]}")/rocm/stack.sh" "${1:?Usage: $0 <base-dockerfile> <command>}"
|
||||||
# Include Dockerfile content
|
shift
|
||||||
if [[ ! -f "$DOCKERFILE" ]]; then
|
CACHE_KEY="$ROCM_STACK_WHEEL_KEY"
|
||||||
echo "ERROR: Dockerfile not found: $DOCKERFILE" >&2
|
WHEELS_DIR="$ROCM_STACK_BASE_WHEELS_DIR"
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
local dockerfile_hash=$(sha256sum "$DOCKERFILE" | cut -c1-16)
|
|
||||||
|
|
||||||
echo "${dockerfile_hash}"
|
|
||||||
}
|
|
||||||
|
|
||||||
CACHE_KEY=$(generate_cache_key)
|
|
||||||
CACHE_PATH="s3://${BUCKET}/${CACHE_PREFIX}/${CACHE_KEY}/"
|
CACHE_PATH="s3://${BUCKET}/${CACHE_PREFIX}/${CACHE_KEY}/"
|
||||||
|
|
||||||
case "${1:-}" in
|
case "${1:-}" in
|
||||||
@@ -67,19 +61,19 @@ case "${1:-}" in
|
|||||||
echo "Cache path: ${CACHE_PATH}"
|
echo "Cache path: ${CACHE_PATH}"
|
||||||
echo ""
|
echo ""
|
||||||
|
|
||||||
if [[ ! -d "artifacts/rocm-base-wheels" ]]; then
|
if [[ ! -d "${WHEELS_DIR}" ]]; then
|
||||||
echo "ERROR: artifacts/rocm-base-wheels directory not found" >&2
|
echo "ERROR: ${WHEELS_DIR} directory not found" >&2
|
||||||
exit 1
|
exit 1
|
||||||
fi
|
fi
|
||||||
|
|
||||||
WHEEL_COUNT=$(find artifacts/rocm-base-wheels -maxdepth 1 -name '*.whl' 2>/dev/null | wc -l)
|
WHEEL_COUNT=$(find "${WHEELS_DIR}" -maxdepth 1 -name '*.whl' 2>/dev/null | wc -l)
|
||||||
if [[ "$WHEEL_COUNT" -eq 0 ]]; then
|
if [[ "$WHEEL_COUNT" -eq 0 ]]; then
|
||||||
echo "ERROR: No wheels found in artifacts/rocm-base-wheels/" >&2
|
echo "ERROR: No wheels found in ${WHEELS_DIR}/" >&2
|
||||||
exit 1
|
exit 1
|
||||||
fi
|
fi
|
||||||
|
|
||||||
echo "Uploading $WHEEL_COUNT wheels..."
|
echo "Uploading $WHEEL_COUNT wheels..."
|
||||||
aws s3 cp --recursive artifacts/rocm-base-wheels/ "${CACHE_PATH}"
|
aws s3 cp --recursive "${WHEELS_DIR}/" "${CACHE_PATH}"
|
||||||
|
|
||||||
echo ""
|
echo ""
|
||||||
echo "Cache upload complete!"
|
echo "Cache upload complete!"
|
||||||
@@ -93,17 +87,17 @@ case "${1:-}" in
|
|||||||
echo "Cache key: ${CACHE_KEY}"
|
echo "Cache key: ${CACHE_KEY}"
|
||||||
echo "Cache path: ${CACHE_PATH}"
|
echo "Cache path: ${CACHE_PATH}"
|
||||||
echo ""
|
echo ""
|
||||||
mkdir -p artifacts/rocm-base-wheels
|
mkdir -p "${WHEELS_DIR}"
|
||||||
|
|
||||||
# Use sync with include/exclude to only download .whl files
|
# Use sync with include/exclude to only download .whl files
|
||||||
aws s3 sync "${CACHE_PATH}" artifacts/rocm-base-wheels/ \
|
aws s3 sync "${CACHE_PATH}" "${WHEELS_DIR}/" \
|
||||||
--exclude "*" \
|
--exclude "*" \
|
||||||
--include "*.whl"
|
--include "*.whl"
|
||||||
|
|
||||||
echo ""
|
echo ""
|
||||||
echo "Downloaded wheels:"
|
echo "Downloaded wheels:"
|
||||||
find artifacts/rocm-base-wheels -maxdepth 1 -name '*.whl' -exec ls -lh {} \;
|
find "${WHEELS_DIR}" -maxdepth 1 -name '*.whl' -exec ls -lh {} \;
|
||||||
WHEEL_COUNT=$(find artifacts/rocm-base-wheels -maxdepth 1 -name '*.whl' 2>/dev/null | wc -l)
|
WHEEL_COUNT=$(find "${WHEELS_DIR}" -maxdepth 1 -name '*.whl' 2>/dev/null | wc -l)
|
||||||
echo ""
|
echo ""
|
||||||
echo "Total: $WHEEL_COUNT wheels"
|
echo "Total: $WHEEL_COUNT wheels"
|
||||||
echo "========================================"
|
echo "========================================"
|
||||||
@@ -118,12 +112,12 @@ case "${1:-}" in
|
|||||||
;;
|
;;
|
||||||
|
|
||||||
*)
|
*)
|
||||||
echo "Usage: $0 {check|upload|download|key|path}" >&2
|
echo "Usage: $0 <base-dockerfile> {check|upload|download|key|path}" >&2
|
||||||
echo "" >&2
|
echo "" >&2
|
||||||
echo "Commands:" >&2
|
echo "Commands:" >&2
|
||||||
echo " check - Check if cache exists, outputs 'hit' or 'miss'" >&2
|
echo " check - Check if cache exists, outputs 'hit' or 'miss'" >&2
|
||||||
echo " upload - Upload wheels from artifacts/rocm-base-wheels/ to cache" >&2
|
echo " upload - Upload wheels from ${WHEELS_DIR}/ to cache" >&2
|
||||||
echo " download - Download wheels from cache to artifacts/rocm-base-wheels/" >&2
|
echo " download - Download wheels from cache to ${WHEELS_DIR}/" >&2
|
||||||
echo " key - Output the cache key" >&2
|
echo " key - Output the cache key" >&2
|
||||||
echo " path - Output the full S3 cache path" >&2
|
echo " path - Output the full S3 cache path" >&2
|
||||||
exit 1
|
exit 1
|
||||||
|
|||||||
@@ -17,7 +17,7 @@ DEFAULT_REPO_SLUG="vllm-project/vllm"
|
|||||||
DEFAULT_CI_HCL_SOURCE="docker/ci-rocm.hcl"
|
DEFAULT_CI_HCL_SOURCE="docker/ci-rocm.hcl"
|
||||||
DEFAULT_CI_BASE_CONTENT_FILES=".dockerignore requirements/common.txt requirements/rocm.txt requirements/test/rocm.txt tools/install_torchcodec_rocm.sh rust-toolchain.toml tests/vllm_test_utils"
|
DEFAULT_CI_BASE_CONTENT_FILES=".dockerignore requirements/common.txt requirements/rocm.txt requirements/test/rocm.txt tools/install_torchcodec_rocm.sh rust-toolchain.toml tests/vllm_test_utils"
|
||||||
DEFAULT_CI_BASE_DOCKERFILE="docker/Dockerfile.rocm"
|
DEFAULT_CI_BASE_DOCKERFILE="docker/Dockerfile.rocm"
|
||||||
DEFAULT_CI_BASE_DOCKERFILE_STAGES="base rust_toolchain_input_0 rust-toolchain-input rust-toolchain build_nixl lmcache_source build_lmcache build_rocshmem build_deepep mori_base ci_base"
|
DEFAULT_CI_BASE_DOCKERFILE_STAGES="base rust_toolchain_input_0 rust-toolchain-input rust-toolchain build_nixl lmcache_source build_lmcache build_deepep mori_base ci_base"
|
||||||
DEFAULT_CI_BASE_METADATA_VERSION="3"
|
DEFAULT_CI_BASE_METADATA_VERSION="3"
|
||||||
# ROCm CI forces REMOTE_VLLM=0, so content identity covers only the selected
|
# ROCm CI forces REMOTE_VLLM=0, so content identity covers only the selected
|
||||||
# local-source stages rather than unreachable remote-fetch alternatives.
|
# local-source stages rather than unreachable remote-fetch alternatives.
|
||||||
@@ -555,9 +555,6 @@ configure_custom_rocm_stages() {
|
|||||||
CI_BASE_DOCKERFILE_STAGES="${CI_BASE_DOCKERFILE_STAGES:-${stages}}"
|
CI_BASE_DOCKERFILE_STAGES="${CI_BASE_DOCKERFILE_STAGES:-${stages}}"
|
||||||
ROCM_CSRC_DOCKERFILE_STAGES="${ROCM_CSRC_DOCKERFILE_STAGES:-${stages}}"
|
ROCM_CSRC_DOCKERFILE_STAGES="${ROCM_CSRC_DOCKERFILE_STAGES:-${stages}}"
|
||||||
ROCM_RUST_DOCKERFILE_STAGES="${ROCM_RUST_DOCKERFILE_STAGES:-${stages}}"
|
ROCM_RUST_DOCKERFILE_STAGES="${ROCM_RUST_DOCKERFILE_STAGES:-${stages}}"
|
||||||
if [[ " ${stages} " != *" build_rocshmem "* ]]; then
|
|
||||||
unset ROCSHMEM_BRANCH ROCSHMEM_CACHE_KEY DEEPEP_CACHE_KEY
|
|
||||||
fi
|
|
||||||
}
|
}
|
||||||
|
|
||||||
compose_dependency_cache_key() {
|
compose_dependency_cache_key() {
|
||||||
@@ -1724,14 +1721,11 @@ ci_base_metadata_pairs() {
|
|||||||
metadata_pair "vllm.rocm.nixl_commit" "${NIXL_BRANCH:-$(resolve_dockerfile_arg_value "${dockerfile}" "NIXL_BRANCH")}"
|
metadata_pair "vllm.rocm.nixl_commit" "${NIXL_BRANCH:-$(resolve_dockerfile_arg_value "${dockerfile}" "NIXL_BRANCH")}"
|
||||||
metadata_pair "vllm.rocm.ucx_repo" "$(resolve_dockerfile_arg_value "${dockerfile}" "UCX_REPO")"
|
metadata_pair "vllm.rocm.ucx_repo" "$(resolve_dockerfile_arg_value "${dockerfile}" "UCX_REPO")"
|
||||||
metadata_pair "vllm.rocm.ucx_commit" "${UCX_BRANCH:-$(resolve_dockerfile_arg_value "${dockerfile}" "UCX_BRANCH")}"
|
metadata_pair "vllm.rocm.ucx_commit" "${UCX_BRANCH:-$(resolve_dockerfile_arg_value "${dockerfile}" "UCX_BRANCH")}"
|
||||||
metadata_pair "vllm.rocm.rocshmem_repo" "$(resolve_dockerfile_arg_value "${dockerfile}" "ROCSHMEM_REPO")"
|
|
||||||
metadata_pair "vllm.rocm.rocshmem_commit" "${ROCSHMEM_BRANCH:-$(resolve_dockerfile_arg_value "${dockerfile}" "ROCSHMEM_BRANCH")}"
|
|
||||||
metadata_pair "vllm.rocm.deepep_repo" "$(resolve_dockerfile_arg_value "${dockerfile}" "DEEPEP_REPO")"
|
metadata_pair "vllm.rocm.deepep_repo" "$(resolve_dockerfile_arg_value "${dockerfile}" "DEEPEP_REPO")"
|
||||||
metadata_pair "vllm.rocm.deepep_commit" "${DEEPEP_BRANCH:-$(resolve_dockerfile_arg_value "${dockerfile}" "DEEPEP_BRANCH")}"
|
metadata_pair "vllm.rocm.deepep_commit" "${DEEPEP_BRANCH:-$(resolve_dockerfile_arg_value "${dockerfile}" "DEEPEP_BRANCH")}"
|
||||||
metadata_pair "vllm.rocm.deepep_nic" "$(resolve_dockerfile_arg_value "${dockerfile}" "DEEPEP_NIC")"
|
metadata_pair "vllm.rocm.deepep_nic" "$(resolve_dockerfile_arg_value "${dockerfile}" "DEEPEP_NIC")"
|
||||||
metadata_pair "vllm.rocm.deepep_rocm_arch" "$(resolve_dockerfile_arg_value "${dockerfile}" "DEEPEP_ROCM_ARCH")"
|
metadata_pair "vllm.rocm.deepep_rocm_arch" "$(resolve_dockerfile_arg_value "${dockerfile}" "DEEPEP_ROCM_ARCH")"
|
||||||
metadata_pair "vllm.rocm.nixl_cache_key" "${NIXL_CACHE_KEY:-}"
|
metadata_pair "vllm.rocm.nixl_cache_key" "${NIXL_CACHE_KEY:-}"
|
||||||
metadata_pair "vllm.rocm.rocshmem_cache_key" "${ROCSHMEM_CACHE_KEY:-}"
|
|
||||||
metadata_pair "vllm.rocm.deepep_cache_key" "${DEEPEP_CACHE_KEY:-}"
|
metadata_pair "vllm.rocm.deepep_cache_key" "${DEEPEP_CACHE_KEY:-}"
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -2314,7 +2308,7 @@ extract_dependency_pins() {
|
|||||||
return 0
|
return 0
|
||||||
fi
|
fi
|
||||||
|
|
||||||
for var in NIXL_BRANCH UCX_BRANCH ROCSHMEM_BRANCH DEEPEP_BRANCH; do
|
for var in NIXL_BRANCH UCX_BRANCH DEEPEP_BRANCH; do
|
||||||
if [[ -n "${!var:-}" ]]; then
|
if [[ -n "${!var:-}" ]]; then
|
||||||
echo "Using provided ${var}: ${!var}"
|
echo "Using provided ${var}: ${!var}"
|
||||||
continue
|
continue
|
||||||
@@ -2336,17 +2330,14 @@ compute_dependency_cache_keys() {
|
|||||||
local dockerfile_rocm=""
|
local dockerfile_rocm=""
|
||||||
local nixl_branch=""
|
local nixl_branch=""
|
||||||
local ucx_branch=""
|
local ucx_branch=""
|
||||||
local rocshmem_branch=""
|
|
||||||
local deepep_branch=""
|
local deepep_branch=""
|
||||||
local nixl_material=""
|
local nixl_material=""
|
||||||
local rocshmem_material=""
|
|
||||||
local deepep_material=""
|
local deepep_material=""
|
||||||
|
|
||||||
bake_dir=$(dirname "${VLLM_BAKE_FILE}")
|
bake_dir=$(dirname "${VLLM_BAKE_FILE}")
|
||||||
dockerfile_rocm="${CI_BASE_DOCKERFILE:-${bake_dir}/Dockerfile.rocm}"
|
dockerfile_rocm="${CI_BASE_DOCKERFILE:-${bake_dir}/Dockerfile.rocm}"
|
||||||
nixl_branch=$(resolve_dockerfile_arg_value "${dockerfile_rocm}" "NIXL_BRANCH")
|
nixl_branch=$(resolve_dockerfile_arg_value "${dockerfile_rocm}" "NIXL_BRANCH")
|
||||||
ucx_branch=$(resolve_dockerfile_arg_value "${dockerfile_rocm}" "UCX_BRANCH")
|
ucx_branch=$(resolve_dockerfile_arg_value "${dockerfile_rocm}" "UCX_BRANCH")
|
||||||
rocshmem_branch=$(resolve_dockerfile_arg_value "${dockerfile_rocm}" "ROCSHMEM_BRANCH")
|
|
||||||
deepep_branch=$(resolve_dockerfile_arg_value "${dockerfile_rocm}" "DEEPEP_BRANCH")
|
deepep_branch=$(resolve_dockerfile_arg_value "${dockerfile_rocm}" "DEEPEP_BRANCH")
|
||||||
|
|
||||||
if [[ -n "${nixl_branch}" && -n "${ucx_branch}" ]]; then
|
if [[ -n "${nixl_branch}" && -n "${ucx_branch}" ]]; then
|
||||||
@@ -2360,22 +2351,11 @@ compute_dependency_cache_keys() {
|
|||||||
echo "NIXL dependency cache key: ${NIXL_CACHE_KEY}"
|
echo "NIXL dependency cache key: ${NIXL_CACHE_KEY}"
|
||||||
fi
|
fi
|
||||||
|
|
||||||
if [[ -n "${rocshmem_branch}" ]]; then
|
if [[ -n "${deepep_branch}" ]]; then
|
||||||
rocshmem_material=$(compose_stage_cache_material "${dockerfile_rocm}" "base build_rocshmem")
|
deepep_material=$(compose_stage_cache_material "${dockerfile_rocm}" "base build_deepep")
|
||||||
ROCSHMEM_CACHE_KEY=$(
|
|
||||||
compose_dependency_cache_key \
|
|
||||||
"${rocshmem_branch}" \
|
|
||||||
"${rocshmem_material}"
|
|
||||||
)
|
|
||||||
export ROCSHMEM_CACHE_KEY
|
|
||||||
echo "ROCShmem dependency cache key: ${ROCSHMEM_CACHE_KEY}"
|
|
||||||
fi
|
|
||||||
|
|
||||||
if [[ -n "${deepep_branch}" && -n "${rocshmem_branch}" ]]; then
|
|
||||||
deepep_material=$(compose_stage_cache_material "${dockerfile_rocm}" "base build_rocshmem build_deepep")
|
|
||||||
DEEPEP_CACHE_KEY=$(
|
DEEPEP_CACHE_KEY=$(
|
||||||
compose_dependency_cache_key \
|
compose_dependency_cache_key \
|
||||||
"${deepep_branch}-rocshmem-${rocshmem_branch}" \
|
"${deepep_branch}" \
|
||||||
"${deepep_material}"
|
"${deepep_material}"
|
||||||
)
|
)
|
||||||
export DEEPEP_CACHE_KEY
|
export DEEPEP_CACHE_KEY
|
||||||
@@ -2415,18 +2395,11 @@ dependency_cache_ref_for_target() {
|
|||||||
printf '%s\n' "${cache_repo}:nixl-rocm-${NIXL_BRANCH}-ucx-${UCX_BRANCH:-}"
|
printf '%s\n' "${cache_repo}:nixl-rocm-${NIXL_BRANCH}-ucx-${UCX_BRANCH:-}"
|
||||||
fi
|
fi
|
||||||
;;
|
;;
|
||||||
rocshmem-rocm-ci)
|
|
||||||
if [[ -n "${ROCSHMEM_CACHE_KEY:-}" ]]; then
|
|
||||||
printf '%s\n' "${cache_repo}:rocshmem-rocm-${ROCSHMEM_CACHE_KEY}"
|
|
||||||
elif [[ -n "${ROCSHMEM_BRANCH:-}" ]]; then
|
|
||||||
printf '%s\n' "${cache_repo}:rocshmem-rocm-${ROCSHMEM_BRANCH}"
|
|
||||||
fi
|
|
||||||
;;
|
|
||||||
deepep-rocm-ci)
|
deepep-rocm-ci)
|
||||||
if [[ -n "${DEEPEP_CACHE_KEY:-}" ]]; then
|
if [[ -n "${DEEPEP_CACHE_KEY:-}" ]]; then
|
||||||
printf '%s\n' "${cache_repo}:deepep-rocm-${DEEPEP_CACHE_KEY}"
|
printf '%s\n' "${cache_repo}:deepep-rocm-${DEEPEP_CACHE_KEY}"
|
||||||
elif [[ -n "${DEEPEP_BRANCH:-}" ]]; then
|
elif [[ -n "${DEEPEP_BRANCH:-}" ]]; then
|
||||||
printf '%s\n' "${cache_repo}:deepep-rocm-${DEEPEP_BRANCH}-rocshmem-${ROCSHMEM_BRANCH:-}"
|
printf '%s\n' "${cache_repo}:deepep-rocm-${DEEPEP_BRANCH}"
|
||||||
fi
|
fi
|
||||||
;;
|
;;
|
||||||
esac
|
esac
|
||||||
@@ -2444,7 +2417,6 @@ add_dependency_cache_target() {
|
|||||||
resolve_ci_base_dependency_targets() {
|
resolve_ci_base_dependency_targets() {
|
||||||
local mode="${ROCM_DEP_CACHE_EXPORT_MODE:-missing}"
|
local mode="${ROCM_DEP_CACHE_EXPORT_MODE:-missing}"
|
||||||
local nixl_ref=""
|
local nixl_ref=""
|
||||||
local rocshmem_ref=""
|
|
||||||
local deepep_ref=""
|
local deepep_ref=""
|
||||||
|
|
||||||
[[ "${TARGET}" == "ci-base-rocm-ci-with-deps" ]] || return 0
|
[[ "${TARGET}" == "ci-base-rocm-ci-with-deps" ]] || return 0
|
||||||
@@ -2452,7 +2424,7 @@ resolve_ci_base_dependency_targets() {
|
|||||||
case "${mode}" in
|
case "${mode}" in
|
||||||
always)
|
always)
|
||||||
echo "ROCM_DEP_CACHE_EXPORT_MODE=always; exporting all dependency caches serially"
|
echo "ROCM_DEP_CACHE_EXPORT_MODE=always; exporting all dependency caches serially"
|
||||||
for target in nixl-rocm-ci rocshmem-rocm-ci deepep-rocm-ci; do
|
for target in nixl-rocm-ci deepep-rocm-ci; do
|
||||||
if [[ -n "$(dependency_cache_ref_for_target "${target}")" ]]; then
|
if [[ -n "$(dependency_cache_ref_for_target "${target}")" ]]; then
|
||||||
add_dependency_cache_target "${target}"
|
add_dependency_cache_target "${target}"
|
||||||
fi
|
fi
|
||||||
@@ -2482,16 +2454,6 @@ resolve_ci_base_dependency_targets() {
|
|||||||
fi
|
fi
|
||||||
fi
|
fi
|
||||||
|
|
||||||
if [[ "${mode}" != "always" && -n "${ROCSHMEM_CACHE_KEY:-}" ]]; then
|
|
||||||
rocshmem_ref=$(dependency_cache_ref_for_target "rocshmem-rocm-ci")
|
|
||||||
if dependency_cache_ref_exists "${rocshmem_ref}"; then
|
|
||||||
echo "ROCShmem dependency cache exists: ${rocshmem_ref}"
|
|
||||||
else
|
|
||||||
echo "ROCShmem dependency cache missing; will seed: ${rocshmem_ref}"
|
|
||||||
add_dependency_cache_target "rocshmem-rocm-ci"
|
|
||||||
fi
|
|
||||||
fi
|
|
||||||
|
|
||||||
if [[ "${mode}" != "always" && -n "${DEEPEP_CACHE_KEY:-}" ]]; then
|
if [[ "${mode}" != "always" && -n "${DEEPEP_CACHE_KEY:-}" ]]; then
|
||||||
deepep_ref=$(dependency_cache_ref_for_target "deepep-rocm-ci")
|
deepep_ref=$(dependency_cache_ref_for_target "deepep-rocm-ci")
|
||||||
if dependency_cache_ref_exists "${deepep_ref}"; then
|
if dependency_cache_ref_exists "${deepep_ref}"; then
|
||||||
@@ -2502,15 +2464,6 @@ resolve_ci_base_dependency_targets() {
|
|||||||
fi
|
fi
|
||||||
fi
|
fi
|
||||||
|
|
||||||
# DeepEP inherits from ROCShmem. If ROCShmem is being seeded, seed DeepEP too
|
|
||||||
# so the pair stays consistent for future ci_base rebuilds.
|
|
||||||
if printf '%s\n' "${DEPENDENCY_CACHE_TARGETS[@]}" | grep -qx "rocshmem-rocm-ci" \
|
|
||||||
&& ! printf '%s\n' "${DEPENDENCY_CACHE_TARGETS[@]}" | grep -qx "deepep-rocm-ci" \
|
|
||||||
&& [[ -n "${DEEPEP_BRANCH:-}" ]]; then
|
|
||||||
echo "ROCShmem cache is missing; also seeding DeepEP cache"
|
|
||||||
add_dependency_cache_target "deepep-rocm-ci"
|
|
||||||
fi
|
|
||||||
|
|
||||||
BAKE_TARGETS=("ci-base-rocm-ci")
|
BAKE_TARGETS=("ci-base-rocm-ci")
|
||||||
if [[ ${#DEPENDENCY_CACHE_TARGETS[@]} -eq 0 ]]; then
|
if [[ ${#DEPENDENCY_CACHE_TARGETS[@]} -eq 0 ]]; then
|
||||||
echo "All dependency caches exist; building ci_base without dependency cache exports"
|
echo "All dependency caches exist; building ci_base without dependency cache exports"
|
||||||
|
|||||||
@@ -5,14 +5,17 @@ set -ex
|
|||||||
# Clean up old nightly builds from DockerHub, keeping only the last 14 builds
|
# Clean up old nightly builds from DockerHub, keeping only the last 14 builds
|
||||||
# This script uses DockerHub API to list and delete old tags with specified prefix
|
# This script uses DockerHub API to list and delete old tags with specified prefix
|
||||||
# Tags starting with "nightly-dev" are always excluded from deletion
|
# Tags starting with "nightly-dev" are always excluded from deletion
|
||||||
# Usage: cleanup-nightly-builds.sh [TAG_PREFIX] [REPO]
|
# Usage: cleanup-nightly-builds.sh [TAG_PREFIX] [REPO] [EXCLUDE_PREFIX]
|
||||||
# Example: cleanup-nightly-builds.sh "nightly-"
|
# Example: cleanup-nightly-builds.sh "nightly-"
|
||||||
# Example: cleanup-nightly-builds.sh "cu130-nightly-"
|
# Example: cleanup-nightly-builds.sh "cu130-nightly-"
|
||||||
# Example: cleanup-nightly-builds.sh "nightly-" "vllm/vllm-openai-rocm"
|
# Example: cleanup-nightly-builds.sh "nightly-" "vllm/vllm-openai-rocm"
|
||||||
|
# Example: cleanup-nightly-builds.sh "nightly-" "vllm/vllm-openai-rocm" "nightly-rocm"
|
||||||
|
# (EXCLUDE_PREFIX skips tags owned by another variant sharing TAG_PREFIX)
|
||||||
|
|
||||||
# Get tag prefix and repo from arguments
|
# Get tag prefix and repo from arguments
|
||||||
TAG_PREFIX="${1:-nightly-}"
|
TAG_PREFIX="${1:-nightly-}"
|
||||||
REPO="${2:-vllm/vllm-openai}"
|
REPO="${2:-vllm/vllm-openai}"
|
||||||
|
EXCLUDE_PREFIX="${3:-}"
|
||||||
|
|
||||||
echo "Cleaning up tags with prefix: $TAG_PREFIX in repository: $REPO"
|
echo "Cleaning up tags with prefix: $TAG_PREFIX in repository: $REPO"
|
||||||
|
|
||||||
@@ -57,7 +60,7 @@ get_all_tags() {
|
|||||||
|
|
||||||
# Get both last_updated timestamp and tag name, separated by |
|
# Get both last_updated timestamp and tag name, separated by |
|
||||||
# Exclude mutable architecture tags and nightly-dev tags from cleanup
|
# Exclude mutable architecture tags and nightly-dev tags from cleanup
|
||||||
local tags=$(echo "$response" | jq -r --arg prefix "$TAG_PREFIX" '.results[] | select(.name | startswith($prefix)) | select(.name != ($prefix + "x86_64") and .name != ($prefix + "aarch64")) | select(.name | startswith("nightly-dev") | not) | "\(.last_updated)|\(.name)"')
|
local tags=$(echo "$response" | jq -r --arg prefix "$TAG_PREFIX" --arg exclude "$EXCLUDE_PREFIX" '.results[] | select(.name | startswith($prefix)) | select($exclude == "" or (.name | startswith($exclude) | not)) | select(.name != ($prefix + "x86_64") and .name != ($prefix + "aarch64")) | select(.name | startswith("nightly-dev") | not) | "\(.last_updated)|\(.name)"')
|
||||||
|
|
||||||
if [ -z "$tags" ]; then
|
if [ -z "$tags" ]; then
|
||||||
break
|
break
|
||||||
|
|||||||
@@ -227,7 +227,12 @@ SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
|||||||
# five-minute lifetime and the loop above can run to the build-age deadline.
|
# five-minute lifetime and the loop above can run to the build-age deadline.
|
||||||
# Build 91827 waited 6h48m and then took a 401 on all 360 callbacks from a
|
# Build 91827 waited 6h48m and then took a 401 on all 360 callbacks from a
|
||||||
# token that had expired hours earlier.
|
# token that had expired hours earlier.
|
||||||
OIDC_TOKEN="$(buildkite-agent oidc request-token --skip-redaction --audience "${AUDIENCE}" 2>/dev/null)"
|
# Posting is paced under the relay's rate limit, which takes several minutes
|
||||||
|
# for a full nightly, so ask for a longer lifetime than the default. Fall back
|
||||||
|
# to the default if this agent rejects --lifetime.
|
||||||
|
OIDC_TOKEN="$(buildkite-agent oidc request-token --skip-redaction --audience "${AUDIENCE}" \
|
||||||
|
--lifetime 1800 2>/dev/null \
|
||||||
|
|| buildkite-agent oidc request-token --skip-redaction --audience "${AUDIENCE}" 2>/dev/null)"
|
||||||
if [[ -z "${OIDC_TOKEN}" ]]; then
|
if [[ -z "${OIDC_TOKEN}" ]]; then
|
||||||
echo "could not mint a Buildkite OIDC token after the wait -- skipping report"
|
echo "could not mint a Buildkite OIDC token after the wait -- skipping report"
|
||||||
exit 0
|
exit 0
|
||||||
|
|||||||
@@ -24,7 +24,9 @@ from __future__ import annotations
|
|||||||
|
|
||||||
import argparse
|
import argparse
|
||||||
import json
|
import json
|
||||||
|
import os
|
||||||
import sys
|
import sys
|
||||||
|
import time
|
||||||
import urllib.error
|
import urllib.error
|
||||||
import urllib.request
|
import urllib.request
|
||||||
|
|
||||||
@@ -43,6 +45,14 @@ _CONCLUSION = {
|
|||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
|
# The relay rate-limits callbacks per repo over a sliding 60 s window
|
||||||
|
# (RATE_LIMIT_PER_MIN in pytorch/test-infra), and a nightly has far more jobs
|
||||||
|
# than that. Pace below the limit, and back off on a 429 for about a minute in
|
||||||
|
# total so the last retry lands in a new window.
|
||||||
|
_POST_INTERVAL_S = float(os.environ.get("CRCR_POST_INTERVAL_S", "0.65"))
|
||||||
|
_RATE_LIMIT_BACKOFF_S = (2, 4, 8, 16, 32)
|
||||||
|
|
||||||
|
|
||||||
def post(url: str, token: str, body: dict, timeout: int = 30) -> tuple[int, str]:
|
def post(url: str, token: str, body: dict, timeout: int = 30) -> tuple[int, str]:
|
||||||
req = urllib.request.Request(
|
req = urllib.request.Request(
|
||||||
url,
|
url,
|
||||||
@@ -113,6 +123,12 @@ def main() -> int:
|
|||||||
ok += 1
|
ok += 1
|
||||||
continue
|
continue
|
||||||
status, detail = post(args.callback_url, args.oidc_token, body)
|
status, detail = post(args.callback_url, args.oidc_token, body)
|
||||||
|
for delay in _RATE_LIMIT_BACKOFF_S:
|
||||||
|
if status != 429:
|
||||||
|
break
|
||||||
|
time.sleep(delay)
|
||||||
|
status, detail = post(args.callback_url, args.oidc_token, body)
|
||||||
|
time.sleep(_POST_INTERVAL_S)
|
||||||
if 200 <= status < 300:
|
if 200 <= status < 300:
|
||||||
ok += 1
|
ok += 1
|
||||||
else:
|
else:
|
||||||
|
|||||||
@@ -12,7 +12,7 @@ from dataclasses import asdict, dataclass
|
|||||||
from datetime import datetime
|
from datetime import datetime
|
||||||
from pathlib import Path
|
from pathlib import Path
|
||||||
from typing import Any
|
from typing import Any
|
||||||
from urllib.parse import quote
|
from urllib.parse import quote, unquote, urlparse
|
||||||
|
|
||||||
import regex as re
|
import regex as re
|
||||||
|
|
||||||
@@ -51,6 +51,8 @@ class WheelFileInfo:
|
|||||||
platform_tag: str
|
platform_tag: str
|
||||||
variant: str | None
|
variant: str | None
|
||||||
filename: str
|
filename: str
|
||||||
|
# Absolute URL for files hosted elsewhere (see --external-links)
|
||||||
|
url: str | None = None
|
||||||
|
|
||||||
|
|
||||||
def parse_from_filename(file: str) -> WheelFileInfo:
|
def parse_from_filename(file: str) -> WheelFileInfo:
|
||||||
@@ -110,6 +112,29 @@ def parse_from_filename(file: str) -> WheelFileInfo:
|
|||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
|
def parse_external_url(url: str) -> WheelFileInfo:
|
||||||
|
"""Parse an absolute wheel or sdist URL hosted on another index."""
|
||||||
|
filename = unquote(urlparse(url).path.rsplit("/", 1)[-1])
|
||||||
|
if filename.endswith(".whl"):
|
||||||
|
info = parse_from_filename(filename)
|
||||||
|
else:
|
||||||
|
match = re.match(r"^(?P<name>.+)-(?P<version>[^-]+)\.(tar\.gz|zip)$", filename)
|
||||||
|
if not match:
|
||||||
|
raise ValueError(f"Unsupported external file: {filename}")
|
||||||
|
info = WheelFileInfo(
|
||||||
|
package_name=match.group("name"),
|
||||||
|
version=match.group("version"),
|
||||||
|
build_tag=None,
|
||||||
|
python_tag="source",
|
||||||
|
abi_tag="none",
|
||||||
|
platform_tag="any",
|
||||||
|
variant=None,
|
||||||
|
filename=filename,
|
||||||
|
)
|
||||||
|
info.url = url
|
||||||
|
return info
|
||||||
|
|
||||||
|
|
||||||
def generate_project_list(subdir_names: list[str], comment: str = "") -> str:
|
def generate_project_list(subdir_names: list[str], comment: str = "") -> str:
|
||||||
"""Generate project list HTML content linking to each project & variant subdirectory."""
|
"""Generate project list HTML content linking to each project & variant subdirectory."""
|
||||||
href_tags = []
|
href_tags = []
|
||||||
@@ -129,14 +154,19 @@ def generate_package_index_and_metadata(
|
|||||||
href_tags = []
|
href_tags = []
|
||||||
metadata = []
|
metadata = []
|
||||||
for file in sorted(wheel_files, key=lambda x: x.filename):
|
for file in sorted(wheel_files, key=lambda x: x.filename):
|
||||||
relative_path = (
|
if file.url:
|
||||||
wheel_base_dir.relative_to(index_base_dir, walk_up=True) / file.filename
|
file_path_quoted = file.url
|
||||||
)
|
else:
|
||||||
# handle with '+' in URL, and avoid double-encoding '/' and already-encoded '%2B'
|
relative_path = (
|
||||||
# NOTE: this is AWS S3 specific behavior!
|
wheel_base_dir.relative_to(index_base_dir, walk_up=True) / file.filename
|
||||||
file_path_quoted = quote(relative_path.as_posix(), safe=":%/")
|
)
|
||||||
|
# handle with '+' in URL, and avoid double-encoding '/' and already-encoded '%2B'
|
||||||
|
# NOTE: this is AWS S3 specific behavior!
|
||||||
|
file_path_quoted = quote(relative_path.as_posix(), safe=":%/")
|
||||||
href_tags.append(f' <a href="{file_path_quoted}">{file.filename}</a><br/>')
|
href_tags.append(f' <a href="{file_path_quoted}">{file.filename}</a><br/>')
|
||||||
file_meta = asdict(file)
|
file_meta = asdict(file)
|
||||||
|
if file_meta["url"] is None:
|
||||||
|
del file_meta["url"]
|
||||||
file_meta["path"] = file_path_quoted
|
file_meta["path"] = file_path_quoted
|
||||||
metadata.append(file_meta)
|
metadata.append(file_meta)
|
||||||
index_str = INDEX_HTML_TEMPLATE.format(items="\n".join(href_tags), comment=comment)
|
index_str = INDEX_HTML_TEMPLATE.format(items="\n".join(href_tags), comment=comment)
|
||||||
@@ -151,6 +181,7 @@ def generate_index_and_metadata(
|
|||||||
default_variant: str | None = None,
|
default_variant: str | None = None,
|
||||||
alias_to_default: str | None = None,
|
alias_to_default: str | None = None,
|
||||||
comment: str = "",
|
comment: str = "",
|
||||||
|
external_urls: list[str] | None = None,
|
||||||
):
|
):
|
||||||
"""Generate index for all wheel files.
|
"""Generate index for all wheel files.
|
||||||
|
|
||||||
@@ -160,6 +191,8 @@ def generate_index_and_metadata(
|
|||||||
index_base_dir (Path): Base directory to store index files.
|
index_base_dir (Path): Base directory to store index files.
|
||||||
default_variant (str | None): The default variant name, if any.
|
default_variant (str | None): The default variant name, if any.
|
||||||
alias_to_default (str | None): Alias variant name for the default variant, if any.
|
alias_to_default (str | None): Alias variant name for the default variant, if any.
|
||||||
|
external_urls (list[str] | None): Absolute URLs of files hosted on another index,
|
||||||
|
listed in the generated indices without being copied.
|
||||||
comment (str | None): Optional comment to include in the generated HTML files.
|
comment (str | None): Optional comment to include in the generated HTML files.
|
||||||
|
|
||||||
First, parse all wheel files to extract metadata.
|
First, parse all wheel files to extract metadata.
|
||||||
@@ -214,6 +247,7 @@ def generate_index_and_metadata(
|
|||||||
|
|
||||||
"""
|
"""
|
||||||
parsed_files = [parse_from_filename(f) for f in whl_files]
|
parsed_files = [parse_from_filename(f) for f in whl_files]
|
||||||
|
parsed_files += [parse_external_url(u) for u in external_urls or []]
|
||||||
|
|
||||||
if not parsed_files:
|
if not parsed_files:
|
||||||
print("No wheel files found, skipping index generation.")
|
print("No wheel files found, skipping index generation.")
|
||||||
@@ -232,10 +266,14 @@ def generate_index_and_metadata(
|
|||||||
print(f"Detected ROCm variant from vllm: {rocm_variant}")
|
print(f"Detected ROCm variant from vllm: {rocm_variant}")
|
||||||
break
|
break
|
||||||
|
|
||||||
# Apply ROCm variant to all wheels without a variant
|
# Apply ROCm variant to all wheels without a variant. Dependencies with their
|
||||||
|
# own ROCm local version (e.g. TheRock's torch-2.12.0+rocm10.0.0) belong to
|
||||||
|
# the same variant rather than one of their own.
|
||||||
if rocm_variant:
|
if rocm_variant:
|
||||||
for file in parsed_files:
|
for file in parsed_files:
|
||||||
if file.variant is None:
|
if file.variant is None or (
|
||||||
|
file.variant.startswith("rocm") and file.variant != rocm_variant
|
||||||
|
):
|
||||||
file.variant = rocm_variant
|
file.variant = rocm_variant
|
||||||
print(f"Inherited variant '{rocm_variant}' for {file.filename}")
|
print(f"Inherited variant '{rocm_variant}' for {file.filename}")
|
||||||
|
|
||||||
@@ -366,6 +404,13 @@ if __name__ == "__main__":
|
|||||||
default=None,
|
default=None,
|
||||||
help="Alias variant name for the default variant",
|
help="Alias variant name for the default variant",
|
||||||
)
|
)
|
||||||
|
parser.add_argument(
|
||||||
|
"--external-links",
|
||||||
|
type=str,
|
||||||
|
default=None,
|
||||||
|
help="Optional file with one absolute URL per line for packages hosted on "
|
||||||
|
"another index (listed alongside, but not copied into, this index)",
|
||||||
|
)
|
||||||
parser.add_argument(
|
parser.add_argument(
|
||||||
"--comment",
|
"--comment",
|
||||||
type=str,
|
type=str,
|
||||||
@@ -463,5 +508,14 @@ if __name__ == "__main__":
|
|||||||
default_variant=None,
|
default_variant=None,
|
||||||
alias_to_default=args.alias_to_default,
|
alias_to_default=args.alias_to_default,
|
||||||
comment=args.comment.strip(),
|
comment=args.comment.strip(),
|
||||||
|
external_urls=(
|
||||||
|
[
|
||||||
|
line.strip()
|
||||||
|
for line in Path(args.external_links).read_text().splitlines()
|
||||||
|
if line.strip() and not line.startswith("#")
|
||||||
|
]
|
||||||
|
if args.external_links
|
||||||
|
else None
|
||||||
|
),
|
||||||
)
|
)
|
||||||
print(f"Successfully generated index and metadata in {output_dir}")
|
print(f"Successfully generated index and metadata in {output_dir}")
|
||||||
|
|||||||
@@ -43,6 +43,7 @@ kernel_tests() {
|
|||||||
docker exec "$CONTAINER_NAME" bash -c "
|
docker exec "$CONTAINER_NAME" bash -c "
|
||||||
set -e
|
set -e
|
||||||
pytest -x -v -s tests/kernels/test_onednn.py
|
pytest -x -v -s tests/kernels/test_onednn.py
|
||||||
|
pytest -x -v -s tests/kernels/test_cpu_fused_sampling.py
|
||||||
pytest -x -v -s tests/kernels/attention/test_cpu_attn.py
|
pytest -x -v -s tests/kernels/attention/test_cpu_attn.py
|
||||||
pytest -x -v -s tests/kernels/core/test_cpu_activation.py
|
pytest -x -v -s tests/kernels/core/test_cpu_activation.py
|
||||||
pytest -x -v -s tests/kernels/moe/test_cpu_fused_moe.py
|
pytest -x -v -s tests/kernels/moe/test_cpu_fused_moe.py
|
||||||
|
|||||||
@@ -19,10 +19,9 @@ DISK_USAGE_THRESHOLD=${DISK_USAGE_THRESHOLD:-80}
|
|||||||
CACHE_MAX_AGE=${CACHE_MAX_AGE:-24h}
|
CACHE_MAX_AGE=${CACHE_MAX_AGE:-24h}
|
||||||
|
|
||||||
# Reclaim disk only when the host is under pressure, aging out anything unused
|
# Reclaim disk only when the host is under pressure, aging out anything unused
|
||||||
# for less than CACHE_MAX_AGE so hot layers survive -- same `--filter
|
# for less than CACHE_MAX_AGE so hot layers survive (`--filter until=<N>h`).
|
||||||
# until=<N>h` pattern the TPU CI scripts already rely on. `docker buildx
|
# `docker buildx prune --max-used-space` is a no-op on this host's `docker`
|
||||||
# prune --max-used-space` is a no-op on this host's `docker` driver (BuildKit
|
# driver (BuildKit embedded in dockerd never enforces the size cap), so we don't use it.
|
||||||
# embedded in dockerd never enforces the size cap), so we don't use it.
|
|
||||||
prune_if_disk_pressure() {
|
prune_if_disk_pressure() {
|
||||||
local docker_root disk_usage
|
local docker_root disk_usage
|
||||||
docker_root=$(docker info -f '{{.DockerRootDir}}' 2>/dev/null || true)
|
docker_root=$(docker info -f '{{.DockerRootDir}}' 2>/dev/null || true)
|
||||||
|
|||||||
@@ -1,29 +0,0 @@
|
|||||||
#!/bin/bash
|
|
||||||
|
|
||||||
# This script build the GH200 docker image and run the offline inference inside the container.
|
|
||||||
# It serves a sanity check for compilation and basic model usage.
|
|
||||||
set -ex
|
|
||||||
|
|
||||||
# Skip the new torch installation during build since we are using the specified version for arm64 in the Dockerfile
|
|
||||||
python3 tools/use_existing_torch.py
|
|
||||||
|
|
||||||
# Try building the docker image
|
|
||||||
DOCKER_BUILDKIT=1 docker build . \
|
|
||||||
--file docker/Dockerfile \
|
|
||||||
--target vllm-openai \
|
|
||||||
--platform "linux/arm64" \
|
|
||||||
-t gh200-test \
|
|
||||||
--build-arg max_jobs=66 \
|
|
||||||
--build-arg nvcc_threads=2 \
|
|
||||||
--build-arg BUILD_BASE_IMAGE=pytorch/manylinuxaarch64-builder:cuda13.0-b8b5f17a7d9ccfc25bbc5cf17b3fcea12964a042 \
|
|
||||||
--build-arg torch_cuda_arch_list="9.0+PTX"
|
|
||||||
|
|
||||||
# Setup cleanup
|
|
||||||
remove_docker_container() { docker rm -f gh200-test || true; }
|
|
||||||
trap remove_docker_container EXIT
|
|
||||||
remove_docker_container
|
|
||||||
|
|
||||||
# Run the image and test offline inference
|
|
||||||
docker run -e HF_TOKEN -e VLLM_WORKER_MULTIPROC_METHOD=spawn -v /root/.cache/huggingface:/root/.cache/huggingface --name gh200-test --gpus=all --entrypoint="" gh200-test bash -c '
|
|
||||||
python3 examples/basic/offline_inference/generate.py --model meta-llama/Llama-3.2-1B
|
|
||||||
'
|
|
||||||
@@ -57,7 +57,7 @@ case "${test_suite}" in
|
|||||||
cd tests
|
cd tests
|
||||||
|
|
||||||
pytest -v -s quantization/test_auto_round.py
|
pytest -v -s quantization/test_auto_round.py
|
||||||
pytest -v -s quantization/test_online.py --deselect=tests/quantization/test_online.py::test_online_quantization_loads_real_weights
|
pytest -v -s quantization/test_online.py --deselect=tests/quantization/test_online.py::test_online_quantization_loads_real_weights --deselect="tests/quantization/test_online.py::test_online_quantization[False-requantization_mxfp8_ptcp_fp8]"
|
||||||
;;
|
;;
|
||||||
compressed-tensors-fp8)
|
compressed-tensors-fp8)
|
||||||
cd tests
|
cd tests
|
||||||
|
|||||||
@@ -1,166 +0,0 @@
|
|||||||
#!/bin/bash
|
|
||||||
|
|
||||||
set -xu
|
|
||||||
|
|
||||||
|
|
||||||
remove_docker_container() {
|
|
||||||
docker rm -f tpu-test || true;
|
|
||||||
}
|
|
||||||
|
|
||||||
trap remove_docker_container EXIT
|
|
||||||
|
|
||||||
# Remove the container that might not be cleaned up in the previous run.
|
|
||||||
remove_docker_container
|
|
||||||
|
|
||||||
# Build the docker image.
|
|
||||||
docker build -f docker/Dockerfile.tpu -t vllm-tpu .
|
|
||||||
|
|
||||||
# Set up cleanup.
|
|
||||||
cleanup_docker() {
|
|
||||||
# Get Docker's root directory
|
|
||||||
docker_root=$(docker info -f '{{.DockerRootDir}}')
|
|
||||||
if [ -z "$docker_root" ]; then
|
|
||||||
echo "Failed to determine Docker root directory."
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
echo "Docker root directory: $docker_root"
|
|
||||||
# Check disk usage of the filesystem where Docker's root directory is located
|
|
||||||
disk_usage=$(df "$docker_root" | tail -1 | awk '{print $5}' | sed 's/%//')
|
|
||||||
# Define the threshold
|
|
||||||
threshold=70
|
|
||||||
if [ "$disk_usage" -gt "$threshold" ]; then
|
|
||||||
echo "Disk usage is above $threshold%. Cleaning up Docker images and volumes..."
|
|
||||||
# Remove dangling images (those that are not tagged and not used by any container)
|
|
||||||
docker image prune -f
|
|
||||||
# Remove unused volumes / force the system prune for old images as well.
|
|
||||||
docker volume prune -f && docker system prune --force --filter "until=72h" --all
|
|
||||||
echo "Docker images and volumes cleanup completed."
|
|
||||||
else
|
|
||||||
echo "Disk usage is below $threshold%. No cleanup needed."
|
|
||||||
fi
|
|
||||||
}
|
|
||||||
cleanup_docker
|
|
||||||
|
|
||||||
# For HF_TOKEN.
|
|
||||||
source /etc/environment
|
|
||||||
|
|
||||||
docker run --privileged --net host --shm-size=16G -it \
|
|
||||||
-e "HF_TOKEN=$HF_TOKEN" --name tpu-test \
|
|
||||||
vllm-tpu /bin/bash -c '
|
|
||||||
set -e # Exit immediately if a command exits with a non-zero status.
|
|
||||||
set -u # Treat unset variables as an error.
|
|
||||||
|
|
||||||
echo "--- Starting script inside Docker container ---"
|
|
||||||
|
|
||||||
# Create results directory
|
|
||||||
RESULTS_DIR=$(mktemp -d)
|
|
||||||
# If mktemp fails, set -e will cause the script to exit.
|
|
||||||
echo "Results will be stored in: $RESULTS_DIR"
|
|
||||||
|
|
||||||
# Install dependencies
|
|
||||||
echo "--- Installing Python dependencies ---"
|
|
||||||
python3 -m pip install --progress-bar off git+https://github.com/thuml/depyf.git \
|
|
||||||
&& python3 -m pip install --progress-bar off pytest pytest-asyncio tpu-info \
|
|
||||||
&& python3 -m pip install --progress-bar off "lm-eval[api]>=0.4.12" \
|
|
||||||
&& python3 -m pip install --progress-bar off hf-transfer tblib==3.1.0
|
|
||||||
echo "--- Python dependencies installed ---"
|
|
||||||
|
|
||||||
export VLLM_XLA_CHECK_RECOMPILATION=1
|
|
||||||
export VLLM_XLA_CACHE_PATH=
|
|
||||||
|
|
||||||
echo "--- Hardware Information ---"
|
|
||||||
# tpu-info
|
|
||||||
echo "--- Starting Tests ---"
|
|
||||||
set +e
|
|
||||||
overall_script_exit_code=0
|
|
||||||
|
|
||||||
# --- Test Definitions ---
|
|
||||||
# If a test fails, this function will print logs and will not cause the main script to exit.
|
|
||||||
run_test() {
|
|
||||||
local test_num=$1
|
|
||||||
local test_name=$2
|
|
||||||
local test_command=$3
|
|
||||||
local log_file="$RESULTS_DIR/test_${test_num}.log"
|
|
||||||
local actual_exit_code
|
|
||||||
|
|
||||||
echo "--- TEST_$test_num: Running $test_name ---"
|
|
||||||
|
|
||||||
# Execute the test command.
|
|
||||||
eval "$test_command" > >(tee -a "$log_file") 2> >(tee -a "$log_file" >&2)
|
|
||||||
actual_exit_code=$?
|
|
||||||
|
|
||||||
echo "TEST_${test_num}_COMMAND_EXIT_CODE: $actual_exit_code" # This goes to main log
|
|
||||||
echo "TEST_${test_num}_COMMAND_EXIT_CODE: $actual_exit_code" >> "$log_file" # Also to per-test log
|
|
||||||
|
|
||||||
if [ "$actual_exit_code" -ne 0 ]; then
|
|
||||||
echo "TEST_$test_num ($test_name) FAILED with exit code $actual_exit_code." >&2
|
|
||||||
echo "--- Log for failed TEST_$test_num ($test_name) ---" >&2
|
|
||||||
if [ -f "$log_file" ]; then
|
|
||||||
cat "$log_file" >&2
|
|
||||||
else
|
|
||||||
echo "Log file $log_file not found for TEST_$test_num ($test_name)." >&2
|
|
||||||
fi
|
|
||||||
echo "--- End of log for TEST_$test_num ($test_name) ---" >&2
|
|
||||||
return "$actual_exit_code" # Return the failure code
|
|
||||||
else
|
|
||||||
echo "TEST_$test_num ($test_name) PASSED."
|
|
||||||
return 0 # Return success
|
|
||||||
fi
|
|
||||||
}
|
|
||||||
|
|
||||||
# Helper function to call run_test and update the overall script exit code
|
|
||||||
run_and_track_test() {
|
|
||||||
local test_num_arg="$1"
|
|
||||||
local test_name_arg="$2"
|
|
||||||
local test_command_arg="$3"
|
|
||||||
|
|
||||||
# Run the test
|
|
||||||
run_test "$test_num_arg" "$test_name_arg" "$test_command_arg"
|
|
||||||
local test_specific_exit_code=$?
|
|
||||||
|
|
||||||
# If the test failed, set the overall script exit code to 1
|
|
||||||
if [ "$test_specific_exit_code" -ne 0 ]; then
|
|
||||||
# No need for extra echo here, run_test already logged the failure.
|
|
||||||
overall_script_exit_code=1
|
|
||||||
fi
|
|
||||||
}
|
|
||||||
|
|
||||||
# --- Actual Test Execution ---
|
|
||||||
run_and_track_test 1 "test_struct_output_generate.py" \
|
|
||||||
"python3 -m pytest -s -v /workspace/vllm/tests/entrypoints/llm/test_struct_output_generate.py -k \"not test_structured_output_with_reasoning_matrices\""
|
|
||||||
run_and_track_test 2 "test_moe_pallas.py" \
|
|
||||||
"python3 -m pytest -s -v /workspace/vllm/tests/tpu/test_moe_pallas.py"
|
|
||||||
run_and_track_test 3 "test_lora.py" \
|
|
||||||
"VLLM_XLA_CHECK_RECOMPILATION=0 python3 -m pytest -s -v /workspace/vllm/tests/tpu/lora/test_lora.py"
|
|
||||||
run_and_track_test 4 "test_tpu_qkv_linear.py" \
|
|
||||||
"python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_tpu_qkv_linear.py"
|
|
||||||
run_and_track_test 5 "test_spmd_model_weight_loading.py" \
|
|
||||||
"python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_spmd_model_weight_loading.py"
|
|
||||||
run_and_track_test 6 "test_kv_cache_update_kernel.py" \
|
|
||||||
"python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_kv_cache_update_kernel.py"
|
|
||||||
run_and_track_test 7 "test_tpu_int8.py" \
|
|
||||||
"python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_tpu_int8.py"
|
|
||||||
|
|
||||||
# After all tests have been attempted, exit with the overall status.
|
|
||||||
if [ "$overall_script_exit_code" -ne 0 ]; then
|
|
||||||
echo "--- One or more tests FAILED. Overall script exiting with failure code 1. ---"
|
|
||||||
else
|
|
||||||
echo "--- All tests have completed and PASSED. Overall script exiting with success code 0. ---"
|
|
||||||
fi
|
|
||||||
exit "$overall_script_exit_code"
|
|
||||||
' # IMPORTANT: This is the closing single quote for the bash -c "..." command. Ensure it is present and correct.
|
|
||||||
|
|
||||||
# Capture the exit code of the docker run command
|
|
||||||
DOCKER_RUN_EXIT_CODE=$?
|
|
||||||
|
|
||||||
# The trap will run for cleanup.
|
|
||||||
# Exit the main script with the Docker run command's exit code.
|
|
||||||
if [ "$DOCKER_RUN_EXIT_CODE" -ne 0 ]; then
|
|
||||||
echo "Docker run command failed with exit code $DOCKER_RUN_EXIT_CODE."
|
|
||||||
exit "$DOCKER_RUN_EXIT_CODE"
|
|
||||||
else
|
|
||||||
echo "Docker run command completed successfully."
|
|
||||||
exit 0
|
|
||||||
fi
|
|
||||||
# TODO: This test fails because it uses RANDOM_SEED sampling
|
|
||||||
# pytest -v -s /workspace/vllm/tests/tpu/test_custom_dispatcher.py \
|
|
||||||
@@ -1,172 +0,0 @@
|
|||||||
#!/bin/bash
|
|
||||||
|
|
||||||
set -xu
|
|
||||||
|
|
||||||
|
|
||||||
remove_docker_container() {
|
|
||||||
docker rm -f tpu-test || true;
|
|
||||||
}
|
|
||||||
|
|
||||||
trap remove_docker_container EXIT
|
|
||||||
|
|
||||||
# Remove the container that might not be cleaned up in the previous run.
|
|
||||||
remove_docker_container
|
|
||||||
|
|
||||||
# Build the docker image.
|
|
||||||
docker build -f docker/Dockerfile.tpu -t vllm-tpu .
|
|
||||||
|
|
||||||
# Set up cleanup.
|
|
||||||
cleanup_docker() {
|
|
||||||
# Get Docker's root directory
|
|
||||||
docker_root=$(docker info -f '{{.DockerRootDir}}')
|
|
||||||
if [ -z "$docker_root" ]; then
|
|
||||||
echo "Failed to determine Docker root directory."
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
echo "Docker root directory: $docker_root"
|
|
||||||
# Check disk usage of the filesystem where Docker's root directory is located
|
|
||||||
disk_usage=$(df "$docker_root" | tail -1 | awk '{print $5}' | sed 's/%//')
|
|
||||||
# Define the threshold
|
|
||||||
threshold=70
|
|
||||||
if [ "$disk_usage" -gt "$threshold" ]; then
|
|
||||||
echo "Disk usage is above $threshold%. Cleaning up Docker images and volumes..."
|
|
||||||
# Remove dangling images (those that are not tagged and not used by any container)
|
|
||||||
docker image prune -f
|
|
||||||
# Remove unused volumes / force the system prune for old images as well.
|
|
||||||
docker volume prune -f && docker system prune --force --filter "until=72h" --all
|
|
||||||
echo "Docker images and volumes cleanup completed."
|
|
||||||
else
|
|
||||||
echo "Disk usage is below $threshold%. No cleanup needed."
|
|
||||||
fi
|
|
||||||
}
|
|
||||||
cleanup_docker
|
|
||||||
|
|
||||||
# For HF_TOKEN.
|
|
||||||
source /etc/environment
|
|
||||||
|
|
||||||
docker run --privileged --net host --shm-size=16G -it \
|
|
||||||
-e "HF_TOKEN=$HF_TOKEN" --name tpu-test \
|
|
||||||
vllm-tpu /bin/bash -c '
|
|
||||||
set -e # Exit immediately if a command exits with a non-zero status.
|
|
||||||
set -u # Treat unset variables as an error.
|
|
||||||
|
|
||||||
echo "--- Starting script inside Docker container ---"
|
|
||||||
|
|
||||||
# Create results directory
|
|
||||||
RESULTS_DIR=$(mktemp -d)
|
|
||||||
# If mktemp fails, set -e will cause the script to exit.
|
|
||||||
echo "Results will be stored in: $RESULTS_DIR"
|
|
||||||
|
|
||||||
# Install dependencies
|
|
||||||
echo "--- Installing Python dependencies ---"
|
|
||||||
python3 -m pip install --progress-bar off git+https://github.com/thuml/depyf.git \
|
|
||||||
&& python3 -m pip install --progress-bar off pytest pytest-asyncio tpu-info \
|
|
||||||
&& python3 -m pip install --progress-bar off "lm-eval[api]>=0.4.12" \
|
|
||||||
&& python3 -m pip install --progress-bar off hf-transfer tblib==3.1.0
|
|
||||||
echo "--- Python dependencies installed ---"
|
|
||||||
|
|
||||||
export VLLM_XLA_CHECK_RECOMPILATION=1
|
|
||||||
export VLLM_XLA_CACHE_PATH=
|
|
||||||
|
|
||||||
echo "--- Hardware Information ---"
|
|
||||||
# tpu-info
|
|
||||||
echo "--- Starting Tests ---"
|
|
||||||
set +e
|
|
||||||
overall_script_exit_code=0
|
|
||||||
|
|
||||||
# --- Test Definitions ---
|
|
||||||
# If a test fails, this function will print logs and will not cause the main script to exit.
|
|
||||||
run_test() {
|
|
||||||
local test_num=$1
|
|
||||||
local test_name=$2
|
|
||||||
local test_command=$3
|
|
||||||
local log_file="$RESULTS_DIR/test_${test_num}.log"
|
|
||||||
local actual_exit_code
|
|
||||||
|
|
||||||
echo "--- TEST_$test_num: Running $test_name ---"
|
|
||||||
|
|
||||||
# Execute the test command.
|
|
||||||
eval "$test_command" > >(tee -a "$log_file") 2> >(tee -a "$log_file" >&2)
|
|
||||||
actual_exit_code=$?
|
|
||||||
|
|
||||||
echo "TEST_${test_num}_COMMAND_EXIT_CODE: $actual_exit_code" # This goes to main log
|
|
||||||
echo "TEST_${test_num}_COMMAND_EXIT_CODE: $actual_exit_code" >> "$log_file" # Also to per-test log
|
|
||||||
|
|
||||||
if [ "$actual_exit_code" -ne 0 ]; then
|
|
||||||
echo "TEST_$test_num ($test_name) FAILED with exit code $actual_exit_code." >&2
|
|
||||||
echo "--- Log for failed TEST_$test_num ($test_name) ---" >&2
|
|
||||||
if [ -f "$log_file" ]; then
|
|
||||||
cat "$log_file" >&2
|
|
||||||
else
|
|
||||||
echo "Log file $log_file not found for TEST_$test_num ($test_name)." >&2
|
|
||||||
fi
|
|
||||||
echo "--- End of log for TEST_$test_num ($test_name) ---" >&2
|
|
||||||
return "$actual_exit_code" # Return the failure code
|
|
||||||
else
|
|
||||||
echo "TEST_$test_num ($test_name) PASSED."
|
|
||||||
return 0 # Return success
|
|
||||||
fi
|
|
||||||
}
|
|
||||||
|
|
||||||
# Helper function to call run_test and update the overall script exit code
|
|
||||||
run_and_track_test() {
|
|
||||||
local test_num_arg="$1"
|
|
||||||
local test_name_arg="$2"
|
|
||||||
local test_command_arg="$3"
|
|
||||||
|
|
||||||
# Run the test
|
|
||||||
run_test "$test_num_arg" "$test_name_arg" "$test_command_arg"
|
|
||||||
local test_specific_exit_code=$?
|
|
||||||
|
|
||||||
# If the test failed, set the overall script exit code to 1
|
|
||||||
if [ "$test_specific_exit_code" -ne 0 ]; then
|
|
||||||
# No need for extra echo here, run_test already logged the failure.
|
|
||||||
overall_script_exit_code=1
|
|
||||||
fi
|
|
||||||
}
|
|
||||||
|
|
||||||
# --- Actual Test Execution ---
|
|
||||||
run_and_track_test 0 "test_perf.py" \
|
|
||||||
"python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_perf.py"
|
|
||||||
run_and_track_test 1 "test_compilation.py" \
|
|
||||||
"python3 -m pytest -s -v /workspace/vllm/tests/tpu/test_compilation.py"
|
|
||||||
run_and_track_test 2 "test_basic.py" \
|
|
||||||
"python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_basic.py"
|
|
||||||
run_and_track_test 3 "test_accuracy.py::test_lm_eval_accuracy_v1_engine" \
|
|
||||||
"python3 -m pytest -s -v /workspace/vllm/tests/entrypoints/llm/test_accuracy.py::test_lm_eval_accuracy_v1_engine"
|
|
||||||
run_and_track_test 4 "test_quantization_accuracy.py" \
|
|
||||||
"python3 -m pytest -s -v /workspace/vllm/tests/tpu/test_quantization_accuracy.py"
|
|
||||||
run_and_track_test 6 "test_tpu_model_runner.py" \
|
|
||||||
"python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/worker/test_tpu_model_runner.py"
|
|
||||||
run_and_track_test 7 "test_sampler.py" \
|
|
||||||
"python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_sampler.py"
|
|
||||||
run_and_track_test 8 "test_topk_topp_sampler.py" \
|
|
||||||
"python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_topk_topp_sampler.py"
|
|
||||||
run_and_track_test 9 "test_multimodal.py" \
|
|
||||||
"python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_multimodal.py"
|
|
||||||
run_and_track_test 10 "test_pallas.py" \
|
|
||||||
"python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_pallas.py"
|
|
||||||
|
|
||||||
# After all tests have been attempted, exit with the overall status.
|
|
||||||
if [ "$overall_script_exit_code" -ne 0 ]; then
|
|
||||||
echo "--- One or more tests FAILED. Overall script exiting with failure code 1. ---"
|
|
||||||
else
|
|
||||||
echo "--- All tests have completed and PASSED. Overall script exiting with success code 0. ---"
|
|
||||||
fi
|
|
||||||
exit "$overall_script_exit_code"
|
|
||||||
' # IMPORTANT: This is the closing single quote for the bash -c "..." command. Ensure it is present and correct.
|
|
||||||
|
|
||||||
# Capture the exit code of the docker run command
|
|
||||||
DOCKER_RUN_EXIT_CODE=$?
|
|
||||||
|
|
||||||
# The trap will run for cleanup.
|
|
||||||
# Exit the main script with the Docker run command's exit code.
|
|
||||||
if [ "$DOCKER_RUN_EXIT_CODE" -ne 0 ]; then
|
|
||||||
echo "Docker run command failed with exit code $DOCKER_RUN_EXIT_CODE."
|
|
||||||
exit "$DOCKER_RUN_EXIT_CODE"
|
|
||||||
else
|
|
||||||
echo "Docker run command completed successfully."
|
|
||||||
exit 0
|
|
||||||
fi
|
|
||||||
# TODO: This test fails because it uses RANDOM_SEED sampling
|
|
||||||
# pytest -v -s /workspace/vllm/tests/tpu/test_custom_dispatcher.py \
|
|
||||||
@@ -10,7 +10,7 @@ fi
|
|||||||
|
|
||||||
# TODO: Use the PyPI wheel once it is published.
|
# TODO: Use the PyPI wheel once it is published.
|
||||||
uv pip install --system \
|
uv pip install --system \
|
||||||
"kvcr @ git+https://github.com/ai-dynamo/kvcr.git@v0.1.0"
|
"kvcr @ git+https://github.com/ai-dynamo/kvcr.git@v0.1.1"
|
||||||
|
|
||||||
# Keep only the NIXL wheel matching the CI image's CUDA runtime.
|
# Keep only the NIXL wheel matching the CI image's CUDA runtime.
|
||||||
NIXL_VERSION=$(uv pip show --system nixl | sed -n 's/^Version: //p')
|
NIXL_VERSION=$(uv pip show --system nixl | sed -n 's/^Version: //p')
|
||||||
|
|||||||
@@ -11,9 +11,9 @@ set -euo pipefail
|
|||||||
TARGET="${1:-all}"
|
TARGET="${1:-all}"
|
||||||
case "${TARGET}" in
|
case "${TARGET}" in
|
||||||
cuda-13-0 | cuda-12-9 | cuda-13-0-ubuntu-24-04 | \
|
cuda-13-0 | cuda-12-9 | cuda-13-0-ubuntu-24-04 | \
|
||||||
cuda-12-9-ubuntu-24-04 | rocm | xpu | cpu | all) ;;
|
cuda-12-9-ubuntu-24-04 | rocm | rocm72 | xpu | cpu | all) ;;
|
||||||
*)
|
*)
|
||||||
echo "Usage: $0 {cuda-13-0|cuda-12-9|cuda-13-0-ubuntu-24-04|cuda-12-9-ubuntu-24-04|rocm|xpu|cpu|all}"
|
echo "Usage: $0 {cuda-13-0|cuda-12-9|cuda-13-0-ubuntu-24-04|cuda-12-9-ubuntu-24-04|rocm|rocm72|xpu|cpu|all}"
|
||||||
exit 2
|
exit 2
|
||||||
;;
|
;;
|
||||||
esac
|
esac
|
||||||
@@ -143,23 +143,35 @@ if target_enabled cuda-12-9-ubuntu-24-04; then
|
|||||||
fi
|
fi
|
||||||
|
|
||||||
# ---- ROCm ----
|
# ---- ROCm ----
|
||||||
|
# Each ROCm stack is identified by its base Dockerfile (see rocm/stack.sh). The
|
||||||
|
# default stack also owns the plain :latest / :v<ver> tags.
|
||||||
|
|
||||||
|
publish_rocm_stack() {
|
||||||
|
local base_dockerfile="$1" default="$2" suffix
|
||||||
|
(
|
||||||
|
# shellcheck source=.buildkite/scripts/rocm/stack.sh
|
||||||
|
source .buildkite/scripts/rocm/stack.sh "$base_dockerfile"
|
||||||
|
local suffixes=("-${ROCM_STACK_VARIANT}")
|
||||||
|
[[ "$default" == "1" ]] && suffixes=("" "-${ROCM_STACK_VARIANT}")
|
||||||
|
docker pull "$ROCM_STACK_ECR_IMAGE"
|
||||||
|
docker pull "$ROCM_STACK_ECR_BASE"
|
||||||
|
for suffix in "${suffixes[@]}"; do
|
||||||
|
for tag in "latest${suffix}" "v${RELEASE_VERSION}${suffix}"; do
|
||||||
|
docker tag "$ROCM_STACK_ECR_IMAGE" "vllm/vllm-openai-rocm:${tag}"
|
||||||
|
docker tag "$ROCM_STACK_ECR_BASE" "vllm/vllm-openai-rocm:${tag}-base"
|
||||||
|
docker push "vllm/vllm-openai-rocm:${tag}"
|
||||||
|
docker push "vllm/vllm-openai-rocm:${tag}-base"
|
||||||
|
done
|
||||||
|
done
|
||||||
|
)
|
||||||
|
}
|
||||||
|
|
||||||
if target_enabled rocm; then
|
if target_enabled rocm; then
|
||||||
ROCM_BASE_CACHE_KEY=$(.buildkite/scripts/cache-rocm-base-wheels.sh key)
|
publish_rocm_stack docker/Dockerfile.rocm_base 1
|
||||||
echo "ROCm base cache key: ${ROCM_BASE_CACHE_KEY}"
|
fi
|
||||||
|
|
||||||
docker pull "public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-rocm"
|
if target_enabled rocm72; then
|
||||||
docker pull "public.ecr.aws/q9t5s3a7/vllm-release-repo:${ROCM_BASE_CACHE_KEY}-rocm-base"
|
publish_rocm_stack docker/Dockerfile.rocm_72_base 0
|
||||||
|
|
||||||
docker tag "public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-rocm" vllm/vllm-openai-rocm:latest
|
|
||||||
docker tag "public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-rocm" "vllm/vllm-openai-rocm:v${RELEASE_VERSION}"
|
|
||||||
docker push vllm/vllm-openai-rocm:latest
|
|
||||||
docker push "vllm/vllm-openai-rocm:v${RELEASE_VERSION}"
|
|
||||||
|
|
||||||
docker tag "public.ecr.aws/q9t5s3a7/vllm-release-repo:${ROCM_BASE_CACHE_KEY}-rocm-base" vllm/vllm-openai-rocm:latest-base
|
|
||||||
docker tag "public.ecr.aws/q9t5s3a7/vllm-release-repo:${ROCM_BASE_CACHE_KEY}-rocm-base" "vllm/vllm-openai-rocm:v${RELEASE_VERSION}-base"
|
|
||||||
docker push vllm/vllm-openai-rocm:latest-base
|
|
||||||
docker push "vllm/vllm-openai-rocm:v${RELEASE_VERSION}-base"
|
|
||||||
fi
|
fi
|
||||||
|
|
||||||
# ---- XPU ----
|
# ---- XPU ----
|
||||||
|
|||||||
@@ -2,42 +2,36 @@
|
|||||||
# SPDX-License-Identifier: Apache-2.0
|
# SPDX-License-Identifier: Apache-2.0
|
||||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||||
#
|
#
|
||||||
# Push a ROCm-family nightly base image and nightly image from ECR to Docker Hub
|
# Push a ROCm stack's nightly base image and nightly image from ECR to Docker Hub
|
||||||
# under vllm/vllm-openai-rocm, as base-nightly[-<variant>], nightly[-<variant>]
|
# under vllm/vllm-openai-rocm, as base-nightly-<variant>, nightly-<variant> and their
|
||||||
# and their -<commit> forms.
|
# -<commit> forms, then prune old nightly tags. With --default, also push the plain
|
||||||
# Run when NIGHTLY=1 after the matching build-*-release-image step has pushed to ECR.
|
# base-nightly and nightly tags for the same images.
|
||||||
|
# Run when NIGHTLY=1 after the stack's release image has been pushed to ECR.
|
||||||
#
|
#
|
||||||
# Usage: push-nightly-builds-rocm.sh [ECR_TAG_SUFFIX TAG_VARIANT]
|
# Usage: push-nightly-builds-rocm.sh <base-dockerfile> [--default]
|
||||||
# Pass both arguments or neither. With none, the default ROCm apt build is
|
# e.g. "docker/Dockerfile.rocm_base --default" (ROCm 10.0, also :nightly)
|
||||||
# published as :nightly. The TheRock build passes "rock" (the source ECR tag
|
# and "docker/Dockerfile.rocm_72_base" (ROCm 7.2, :nightly-rocm72).
|
||||||
# suffix) and "rocm714" (the Docker Hub tag flavor), giving :nightly-rocm714.
|
|
||||||
#
|
#
|
||||||
# Local testing (no push to Docker Hub):
|
# Local testing (no push to Docker Hub):
|
||||||
# BASE_ECR_IMAGE=<full-base-image-reference> \
|
# BUILDKITE_COMMIT=<commit-with-image-in-ecr> DRY_RUN=1 \
|
||||||
# BUILDKITE_COMMIT=<commit-with-image-in-ecr> DRY_RUN=1 \
|
# bash .buildkite/scripts/push-nightly-builds-rocm.sh docker/Dockerfile.rocm_base --default
|
||||||
# bash .buildkite/scripts/push-nightly-builds-rocm.sh
|
|
||||||
# Requires: AWS CLI configured (for ECR public login), Docker. For full run: Docker Hub login.
|
# Requires: AWS CLI configured (for ECR public login), Docker. For full run: Docker Hub login.
|
||||||
|
|
||||||
set -euxo pipefail
|
set -euxo pipefail
|
||||||
|
|
||||||
usage() {
|
usage() {
|
||||||
echo "Usage: $0 [ECR_TAG_SUFFIX TAG_VARIANT]" >&2
|
echo "Usage: $0 <base-dockerfile> [--default]" >&2
|
||||||
}
|
}
|
||||||
|
|
||||||
DOCKERHUB_REPO="vllm/vllm-openai-rocm"
|
PUSH_DEFAULT=0
|
||||||
|
|
||||||
case "$#" in
|
case "$#" in
|
||||||
0)
|
1) ;;
|
||||||
ECR_TAG_SUFFIX="rocm"
|
|
||||||
TAG_VARIANT=""
|
|
||||||
;;
|
|
||||||
2)
|
2)
|
||||||
if [[ -z "$1" || -z "$2" ]]; then
|
if [[ "$2" != "--default" ]]; then
|
||||||
usage
|
usage
|
||||||
exit 2
|
exit 2
|
||||||
fi
|
fi
|
||||||
ECR_TAG_SUFFIX="$1"
|
PUSH_DEFAULT=1
|
||||||
TAG_VARIANT="$2"
|
|
||||||
;;
|
;;
|
||||||
*)
|
*)
|
||||||
usage
|
usage
|
||||||
@@ -49,61 +43,44 @@ esac
|
|||||||
BUILDKITE_COMMIT="${BUILDKITE_COMMIT:?Set BUILDKITE_COMMIT to the commit SHA that has the image in ECR (e.g. from a previous release pipeline run)}"
|
BUILDKITE_COMMIT="${BUILDKITE_COMMIT:?Set BUILDKITE_COMMIT to the commit SHA that has the image in ECR (e.g. from a previous release pipeline run)}"
|
||||||
DRY_RUN="${DRY_RUN:-0}"
|
DRY_RUN="${DRY_RUN:-0}"
|
||||||
|
|
||||||
ECR_REPO="public.ecr.aws/q9t5s3a7/vllm-release-repo"
|
# shellcheck source=.buildkite/scripts/rocm/stack.sh
|
||||||
|
source "$(dirname "${BASH_SOURCE[0]}")/rocm/stack.sh" "$1"
|
||||||
|
DOCKERHUB_REPO="vllm/vllm-openai-rocm"
|
||||||
|
VARIANT="$ROCM_STACK_VARIANT"
|
||||||
|
|
||||||
# Get the base image ECR tag (set by the build-*-release-image pipeline step)
|
BASE_TAGS=("base-nightly-${VARIANT}" "base-nightly-${VARIANT}-${BUILDKITE_COMMIT}")
|
||||||
BASE_METADATA_KEY="${ECR_TAG_SUFFIX}-base-ecr-tag"
|
TAGS=("nightly-${VARIANT}" "nightly-${VARIANT}-${BUILDKITE_COMMIT}")
|
||||||
if [[ -n "${BASE_ECR_IMAGE:-}" ]]; then
|
if [[ "$PUSH_DEFAULT" == "1" ]]; then
|
||||||
if [[ "$DRY_RUN" != "1" ]]; then
|
BASE_TAGS+=("base-nightly" "base-nightly-${BUILDKITE_COMMIT}")
|
||||||
echo "ERROR: BASE_ECR_IMAGE may only be used with DRY_RUN=1" >&2
|
TAGS+=("nightly" "nightly-${BUILDKITE_COMMIT}")
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
BASE_ORIG_TAG="$BASE_ECR_IMAGE"
|
|
||||||
elif ! BASE_ORIG_TAG="$(buildkite-agent meta-data get "$BASE_METADATA_KEY")"; then
|
|
||||||
echo "ERROR: Failed to read required Buildkite metadata '$BASE_METADATA_KEY'" >&2
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
if [[ -z "$BASE_ORIG_TAG" ]]; then
|
|
||||||
echo "ERROR: Required Buildkite metadata '$BASE_METADATA_KEY' is empty" >&2
|
|
||||||
echo "Set BASE_ECR_IMAGE to the full ECR base image reference for local testing" >&2
|
|
||||||
exit 1
|
|
||||||
fi
|
fi
|
||||||
|
|
||||||
ORIG_TAG="${BUILDKITE_COMMIT}-${ECR_TAG_SUFFIX}"
|
echo "Pushing base image $ROCM_STACK_ECR_BASE as: ${BASE_TAGS[*]}"
|
||||||
VARIANT_SUFFIX=""
|
echo "Pushing release image $ROCM_STACK_ECR_IMAGE as: ${TAGS[*]}"
|
||||||
[[ -n "$TAG_VARIANT" ]] && VARIANT_SUFFIX="-$TAG_VARIANT"
|
|
||||||
BASE_TAG_NAME="base-nightly${VARIANT_SUFFIX}"
|
|
||||||
TAG_NAME="nightly${VARIANT_SUFFIX}"
|
|
||||||
BASE_TAG_NAME_COMMIT="base-nightly${VARIANT_SUFFIX}-${BUILDKITE_COMMIT}"
|
|
||||||
TAG_NAME_COMMIT="nightly${VARIANT_SUFFIX}-${BUILDKITE_COMMIT}"
|
|
||||||
|
|
||||||
echo "Pushing base image from ECR: $BASE_ORIG_TAG"
|
# Login to ECR and pull the stack's images
|
||||||
echo "Pushing release image from ECR tag: $ORIG_TAG to Docker Hub as $DOCKERHUB_REPO:$TAG_NAME and $DOCKERHUB_REPO:$TAG_NAME_COMMIT"
|
|
||||||
[[ "$DRY_RUN" == "1" ]] && echo "[DRY_RUN] Skipping push to Docker Hub"
|
|
||||||
|
|
||||||
# Login to ECR and pull the images built by build-*-release-image
|
|
||||||
aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7
|
aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7
|
||||||
docker pull "$BASE_ORIG_TAG"
|
docker pull "$ROCM_STACK_ECR_BASE"
|
||||||
docker pull "${ECR_REPO}:${ORIG_TAG}"
|
docker pull "$ROCM_STACK_ECR_IMAGE"
|
||||||
|
|
||||||
# Tag for Docker Hub (base-nightly and base-nightly-<commit>, nightly and nightly-<commit>)
|
for tag in "${BASE_TAGS[@]}"; do docker tag "$ROCM_STACK_ECR_BASE" "$DOCKERHUB_REPO:$tag"; done
|
||||||
docker tag "$BASE_ORIG_TAG" "$DOCKERHUB_REPO":"$BASE_TAG_NAME"
|
for tag in "${TAGS[@]}"; do docker tag "$ROCM_STACK_ECR_IMAGE" "$DOCKERHUB_REPO:$tag"; done
|
||||||
docker tag "$BASE_ORIG_TAG" "$DOCKERHUB_REPO":"$BASE_TAG_NAME_COMMIT"
|
|
||||||
docker tag "${ECR_REPO}:${ORIG_TAG}" "$DOCKERHUB_REPO":"$TAG_NAME"
|
|
||||||
docker tag "${ECR_REPO}:${ORIG_TAG}" "$DOCKERHUB_REPO":"$TAG_NAME_COMMIT"
|
|
||||||
|
|
||||||
if [[ "$DRY_RUN" == "1" ]]; then
|
if [[ "$DRY_RUN" == "1" ]]; then
|
||||||
echo "[DRY_RUN] Would push $DOCKERHUB_REPO:$BASE_TAG_NAME and $DOCKERHUB_REPO:$BASE_TAG_NAME_COMMIT"
|
|
||||||
echo "[DRY_RUN] Would push $DOCKERHUB_REPO:$TAG_NAME and $DOCKERHUB_REPO:$TAG_NAME_COMMIT"
|
|
||||||
echo "[DRY_RUN] Local tags created. Exiting without push."
|
echo "[DRY_RUN] Local tags created. Exiting without push."
|
||||||
exit 0
|
exit 0
|
||||||
fi
|
fi
|
||||||
|
|
||||||
# Push to Docker Hub (docker-login plugin runs before this step in CI)
|
# Push to Docker Hub (docker-login plugin runs before this step in CI)
|
||||||
docker push "$DOCKERHUB_REPO":"$BASE_TAG_NAME"
|
for tag in "${BASE_TAGS[@]}" "${TAGS[@]}"; do docker push "$DOCKERHUB_REPO:$tag"; done
|
||||||
docker push "$DOCKERHUB_REPO":"$BASE_TAG_NAME_COMMIT"
|
echo "Pushed $DOCKERHUB_REPO: ${BASE_TAGS[*]} ${TAGS[*]}"
|
||||||
docker push "$DOCKERHUB_REPO":"$TAG_NAME"
|
|
||||||
docker push "$DOCKERHUB_REPO":"$TAG_NAME_COMMIT"
|
|
||||||
|
|
||||||
echo "Pushed $DOCKERHUB_REPO:$BASE_TAG_NAME and $DOCKERHUB_REPO:$BASE_TAG_NAME_COMMIT"
|
# Keep only the last 14 builds of each tag family. The plain nightly- families
|
||||||
echo "Pushed $DOCKERHUB_REPO:$TAG_NAME and $DOCKERHUB_REPO:$TAG_NAME_COMMIT"
|
# exclude the variant ones sharing their prefix; commit SHAs never start with "rocm".
|
||||||
|
CLEANUP=.buildkite/scripts/cleanup-nightly-builds.sh
|
||||||
|
bash "$CLEANUP" "nightly-${VARIANT}-" "$DOCKERHUB_REPO"
|
||||||
|
bash "$CLEANUP" "base-nightly-${VARIANT}-" "$DOCKERHUB_REPO"
|
||||||
|
if [[ "$PUSH_DEFAULT" == "1" ]]; then
|
||||||
|
bash "$CLEANUP" "nightly-" "$DOCKERHUB_REPO" "nightly-rocm"
|
||||||
|
bash "$CLEANUP" "base-nightly-" "$DOCKERHUB_REPO" "base-nightly-rocm"
|
||||||
|
fi
|
||||||
|
|||||||
+112
@@ -0,0 +1,112 @@
|
|||||||
|
#!/bin/bash
|
||||||
|
# Install the AITER nightly wheel over this build's ci_base.
|
||||||
|
#
|
||||||
|
# Runs in CI when AITER_NIGHTLY=1, once the stock ci_base it builds on is
|
||||||
|
# published. In order:
|
||||||
|
# 1. Select the newest nightly wheel that fits the stock ci_base
|
||||||
|
# (select_aiter_nightly_wheel.py, beside this script, run inside that image)
|
||||||
|
# 2. Build a new image: pip install that wheel over the stock ci_base
|
||||||
|
# 3. Push the new image as this build's ci_base-build tag, replacing the stock
|
||||||
|
# one, so later steps and native jobs use it; record its digest
|
||||||
|
#
|
||||||
|
# Buildkite meta-data, a key-value store shared by every job in this build:
|
||||||
|
# reads rocm-ci-base-image the stock ci_base
|
||||||
|
# r/w aiter-nightly-wheel-url the wheel step 1 chose; a retry reads it
|
||||||
|
# back and installs that same wheel
|
||||||
|
# writes aiter-nightly-ci-base the new image as tag@digest; the vLLM
|
||||||
|
# image build uses it as its ci_base
|
||||||
|
#
|
||||||
|
# Exit status:
|
||||||
|
# 10 no wheel fits this ci_base
|
||||||
|
# 11 the wheel does not install
|
||||||
|
# Anything else is unexpected and passed through as is.
|
||||||
|
# Buildkite retries this step once on exit status 1 or 2, which it treats as
|
||||||
|
# transient Docker/registry failures (amd_infra_retry in the template).
|
||||||
|
# 10 and 11 sit outside that range: they are real AITER failures, and a retry
|
||||||
|
# would only fail the same way.
|
||||||
|
|
||||||
|
set -euo pipefail
|
||||||
|
|
||||||
|
SELECT_WHEEL="$(dirname "${BASH_SOURCE[0]}")/select_aiter_nightly_wheel.py"
|
||||||
|
BUILD_TAG="rocm/vllm-dev:ci_base-build-${BUILDKITE_BUILD_ID:?BUILDKITE_BUILD_ID is required}"
|
||||||
|
|
||||||
|
# Scratch space for the build context and captured errors. The trap deletes it
|
||||||
|
# however the script exits: success, fail, or set -e.
|
||||||
|
scratch="$(mktemp -d)"
|
||||||
|
trap 'rm -rf "${scratch}"' EXIT
|
||||||
|
errors="${scratch}/errors"
|
||||||
|
|
||||||
|
fail() {
|
||||||
|
local status="$1" title="$2" detail="$3"
|
||||||
|
echo "+++ :x: AITER nightly: ${title}"
|
||||||
|
echo "${detail}" >&2
|
||||||
|
# shellcheck disable=SC2016 # the backticks are a literal markdown fence
|
||||||
|
printf ':x: **AITER nightly: %s**\n\n```\n%s\n```\n' "${title}" "${detail}" \
|
||||||
|
| buildkite-agent annotate --style error --context aiter-nightly
|
||||||
|
exit "${status}"
|
||||||
|
}
|
||||||
|
|
||||||
|
# Set by ensure-ci-base-amd; this step's depends_on guarantees it is there.
|
||||||
|
ci_base="$(buildkite-agent meta-data get rocm-ci-base-image)"
|
||||||
|
# Set below on the first attempt. Meta-data is per build, so a retry reuses
|
||||||
|
# that wheel, not a newer nightly.
|
||||||
|
pinned="$(buildkite-agent meta-data get aiter-nightly-wheel-url --default "")"
|
||||||
|
|
||||||
|
echo "--- :docker: Pulling ${ci_base}"
|
||||||
|
docker pull "${ci_base}"
|
||||||
|
|
||||||
|
echo "--- :mag: Selecting the AITER nightly for ${ci_base}"
|
||||||
|
set +e
|
||||||
|
out="$(docker run --rm -i --entrypoint python3 "${ci_base}" \
|
||||||
|
-P - ${pinned:+--wheel-url "${pinned}"} \
|
||||||
|
< "${SELECT_WHEEL}" 2> "${errors}")"
|
||||||
|
status=$?
|
||||||
|
set -e
|
||||||
|
cat "${errors}" >&2
|
||||||
|
case "${status}" in
|
||||||
|
0) ;;
|
||||||
|
10) fail 10 "no wheel for this image" "${out}" ;;
|
||||||
|
*) fail "${status}" "could not select a wheel" "$(tail -n 20 "${errors}")" ;;
|
||||||
|
esac
|
||||||
|
# The first line is the wheel's URL; the rest, the annotation naming it.
|
||||||
|
wheel_url="$(head -n 1 <<< "${out}")"
|
||||||
|
note="$(tail -n +2 <<< "${out}")"
|
||||||
|
buildkite-agent meta-data set aiter-nightly-wheel-url "${wheel_url}"
|
||||||
|
|
||||||
|
cat > "${scratch}/Dockerfile" <<'EOF'
|
||||||
|
ARG CI_BASE_IMAGE
|
||||||
|
FROM ${CI_BASE_IMAGE}
|
||||||
|
ARG AITER_WHEEL_URL
|
||||||
|
RUN python3 -m pip install --no-cache-dir "$AITER_WHEEL_URL"
|
||||||
|
EOF
|
||||||
|
|
||||||
|
echo "--- :docker: Installing ${wheel_url##*/}"
|
||||||
|
if ! docker buildx build \
|
||||||
|
--builder default \
|
||||||
|
--provenance=false \
|
||||||
|
--progress plain \
|
||||||
|
--build-arg "CI_BASE_IMAGE=${ci_base}" \
|
||||||
|
--build-arg "AITER_WHEEL_URL=${wheel_url}" \
|
||||||
|
-t "${BUILD_TAG}" \
|
||||||
|
"${scratch}"; then
|
||||||
|
fail 11 "the wheel does not install" \
|
||||||
|
"Installing ${wheel_url##*/} over ${ci_base} failed; see this step's log."
|
||||||
|
fi
|
||||||
|
|
||||||
|
docker push "${BUILD_TAG}"
|
||||||
|
# Handed off as tag@digest: build-test-image.sh rejects a ci_base that is not
|
||||||
|
# digest-pinned.
|
||||||
|
digest="$(docker buildx imagetools inspect "${BUILD_TAG}" | awk '$1 == "Digest:" { print $2; exit }')"
|
||||||
|
if [[ ! "${digest}" =~ ^sha256:[0-9a-f]{64}$ ]]; then
|
||||||
|
echo "Could not resolve the pushed digest of ${BUILD_TAG}" >&2
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
# The vLLM image build uses this as its ci_base.
|
||||||
|
buildkite-agent meta-data set aiter-nightly-ci-base "${BUILD_TAG}@${digest}"
|
||||||
|
# The annotation starts with :warning: when the wheel is stale.
|
||||||
|
style=info
|
||||||
|
if [[ "${note}" == :warning:* ]]; then
|
||||||
|
style=warning
|
||||||
|
fi
|
||||||
|
echo "${note}" | buildkite-agent annotate --style "${style}" --context aiter-nightly
|
||||||
|
echo "--- :white_check_mark: ${BUILD_TAG}@${digest}"
|
||||||
@@ -1,8 +1,8 @@
|
|||||||
#!/usr/bin/env bash
|
#!/usr/bin/env bash
|
||||||
# Shared Dockerfile selection for the normal AMD CI build chain.
|
# Shared Dockerfile selection for the normal AMD CI build chain.
|
||||||
# CI_ROCM_DOCKERFILE_BASE and CI_ROCM_DOCKERFILE accept repository-relative paths.
|
# CI_ROCM_DOCKERFILE_BASE and CI_ROCM_DOCKERFILE accept repository-relative paths.
|
||||||
# For Rock, set CI_ROCM_DOCKERFILE_BASE=docker/Dockerfile.rock_base and
|
# For the legacy ROCm 7.2 stack, set CI_ROCM_DOCKERFILE_BASE=docker/Dockerfile.rocm_72_base
|
||||||
# CI_ROCM_DOCKERFILE=docker/Dockerfile.rock.
|
# and CI_ROCM_DOCKERFILE=docker/Dockerfile.rocm_72.
|
||||||
# Custom recipes must preserve the CI targets and artifact layout. Additional
|
# Custom recipes must preserve the CI targets and artifact layout. Additional
|
||||||
# COPY inputs also need the corresponding *_CONTENT_FILES overrides.
|
# COPY inputs also need the corresponding *_CONTENT_FILES overrides.
|
||||||
|
|
||||||
|
|||||||
+260
@@ -0,0 +1,260 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
# SPDX-License-Identifier: Apache-2.0
|
||||||
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||||
|
"""Select the AITER nightly wheel for a vLLM ROCm image.
|
||||||
|
|
||||||
|
aiter-nightly-overlay.sh runs this inside the stock ci_base, so it reads that
|
||||||
|
image's ROCm, torch and Python. It prints the wheel's URL, then the Buildkite
|
||||||
|
annotation naming it.
|
||||||
|
"""
|
||||||
|
|
||||||
|
import argparse
|
||||||
|
import datetime
|
||||||
|
import importlib.metadata
|
||||||
|
import os
|
||||||
|
import sys
|
||||||
|
import urllib.request
|
||||||
|
from dataclasses import dataclass
|
||||||
|
from html.parser import HTMLParser
|
||||||
|
from pathlib import Path
|
||||||
|
from urllib.parse import unquote, urldefrag, urljoin
|
||||||
|
|
||||||
|
import regex as re
|
||||||
|
|
||||||
|
INDEX_URL = "https://rocm.frameworks-nightlies.amd.com/whl-multi-arch/amd-aiter/"
|
||||||
|
AITER_COMMIT_URL = "https://github.com/ROCm/aiter/commit/"
|
||||||
|
STALE_AFTER = datetime.timedelta(days=1)
|
||||||
|
|
||||||
|
# Example:
|
||||||
|
# amd_aiter-0.1.25+rocm7.2.3.torch2.12.ae984f5.d20261008-cp312-cp312-linux_x86_64.whl
|
||||||
|
# is AITER main at commit ae984f5, built 2026-10-08, for ROCm 7.2.3, torch 2.12
|
||||||
|
# and Python 3.12. 0.1.25 is a guess at the next release, not a real one.
|
||||||
|
WHEEL_NAME = re.compile(
|
||||||
|
r"^amd_aiter-(?P<base_version>[^+-]+)\+(?P<local>[^-]+)"
|
||||||
|
r"-(?P<python>cp\d+)-(?P=python)-linux_x86_64\.whl$"
|
||||||
|
)
|
||||||
|
ROCM_FIELD = re.compile(r"(?:^|\.)rocm(\d+(?:\.\d+)*)(?:a\d+)?(?=\.|$)")
|
||||||
|
TORCH_FIELD = re.compile(r"(?:^|\.)torch(\d+\.\d+)(?=\.|$)")
|
||||||
|
COMMIT_AND_DATE_FIELD = re.compile(r"(?:^|\.)([0-9a-f]{7,40})\.d(\d{8})(?=\.|$)")
|
||||||
|
|
||||||
|
|
||||||
|
@dataclass(frozen=True)
|
||||||
|
class Wheel:
|
||||||
|
"""An AITER nightly wheel, read from its filename (see WHEEL_NAME)."""
|
||||||
|
|
||||||
|
filename: str
|
||||||
|
url: str
|
||||||
|
version: str
|
||||||
|
base_version: str
|
||||||
|
rocm: str
|
||||||
|
torch: str
|
||||||
|
commit: str
|
||||||
|
build_date: datetime.date
|
||||||
|
python: str
|
||||||
|
|
||||||
|
|
||||||
|
class _LinkParser(HTMLParser):
|
||||||
|
"""Collects every link on the index page, which lists one per wheel."""
|
||||||
|
|
||||||
|
def __init__(self):
|
||||||
|
super().__init__()
|
||||||
|
self.hrefs: list[str] = []
|
||||||
|
|
||||||
|
def handle_starttag(self, tag, attrs):
|
||||||
|
if tag == "a":
|
||||||
|
self.hrefs.extend(
|
||||||
|
value for name, value in attrs if name == "href" and value
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
def wheel_from_url(url: str) -> Wheel | None:
|
||||||
|
"""The AITER nightly wheel an absolute URL points at, if it is one."""
|
||||||
|
filename = unquote(urldefrag(url).url.rsplit("/", 1)[-1])
|
||||||
|
match = WHEEL_NAME.match(filename)
|
||||||
|
if not match:
|
||||||
|
return None
|
||||||
|
local = match["local"]
|
||||||
|
rocm, torch, build = (
|
||||||
|
field.search(local)
|
||||||
|
for field in (ROCM_FIELD, TORCH_FIELD, COMMIT_AND_DATE_FIELD)
|
||||||
|
)
|
||||||
|
if not (rocm and torch and build):
|
||||||
|
return None
|
||||||
|
return Wheel(
|
||||||
|
filename=filename,
|
||||||
|
url=url,
|
||||||
|
version=f"{match['base_version']}+{local}",
|
||||||
|
base_version=match["base_version"],
|
||||||
|
rocm=rocm[1],
|
||||||
|
torch=torch[1],
|
||||||
|
commit=build[1],
|
||||||
|
build_date=datetime.datetime.strptime(build[2], "%Y%m%d").date(),
|
||||||
|
python=match["python"],
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
def parse_index(html: str, index_url: str) -> list[Wheel]:
|
||||||
|
"""Every AITER nightly wheel linked from the index page, a plain HTML list
|
||||||
|
of links, one per file (the format pip reads)."""
|
||||||
|
parser = _LinkParser()
|
||||||
|
parser.feed(html)
|
||||||
|
wheels = (wheel_from_url(urljoin(index_url, href)) for href in parser.hrefs)
|
||||||
|
return [wheel for wheel in wheels if wheel]
|
||||||
|
|
||||||
|
|
||||||
|
def rocm_version() -> str:
|
||||||
|
"""This image's ROCm version; ROCm 10+ ships as the `rocm` pip SDK."""
|
||||||
|
try:
|
||||||
|
return importlib.metadata.version("rocm")
|
||||||
|
except importlib.metadata.PackageNotFoundError:
|
||||||
|
# No pip SDK: fall back to older ROCm releases, which install to ROCM_PATH.
|
||||||
|
rocm_path = Path(os.environ.get("ROCM_PATH", "/opt/rocm"))
|
||||||
|
return (rocm_path / ".info" / "version").read_text()
|
||||||
|
|
||||||
|
|
||||||
|
def rocm_release(version: str) -> str:
|
||||||
|
"""`7.2.3-49` or `10.0.0a20261001` -> `7.2.3` or `10.0.0`, as wheel names
|
||||||
|
spell it."""
|
||||||
|
match = re.match(r"\d+(?:\.\d+)*", version.strip())
|
||||||
|
if not match:
|
||||||
|
raise ValueError(f"Unrecognised ROCm version: {version!r}")
|
||||||
|
return match.group(0)
|
||||||
|
|
||||||
|
|
||||||
|
def torch_release(version: str) -> str:
|
||||||
|
"""`2.12.0a0+git6bbd260` -> `2.12`, as wheel names spell it."""
|
||||||
|
match = re.match(r"\d+\.\d+", version)
|
||||||
|
if not match:
|
||||||
|
raise ValueError(f"Unrecognised torch version: {version!r}")
|
||||||
|
return match.group(0)
|
||||||
|
|
||||||
|
|
||||||
|
def python_tag(version_info: tuple[int, int]) -> str:
|
||||||
|
"""(3, 12) -> `cp312`, as wheel names spell it."""
|
||||||
|
return f"cp{version_info[0]}{version_info[1]}"
|
||||||
|
|
||||||
|
|
||||||
|
def _base_version_key(wheel: Wheel) -> tuple[int, ...]:
|
||||||
|
"""`0.1.25` -> (0, 1, 25), so versions sort as numbers: 0.1.10 > 0.1.9."""
|
||||||
|
return tuple(int(part) for part in re.findall(r"\d+", wheel.base_version))
|
||||||
|
|
||||||
|
|
||||||
|
def _label(rocm: str, torch: str, python: str) -> str:
|
||||||
|
"""`rocm7.2.3/torch2.12/cp312`, for messages."""
|
||||||
|
return f"rocm{rocm}/torch{torch}/{python}"
|
||||||
|
|
||||||
|
|
||||||
|
def select_wheel(wheels: list[Wheel], rocm: str, torch: str, python: str) -> Wheel:
|
||||||
|
"""Newest build for this ROCm, torch and Python, by date: version labels lag.
|
||||||
|
|
||||||
|
Two builds with the same date and version: whichever the index lists first.
|
||||||
|
"""
|
||||||
|
target = (rocm, torch, python)
|
||||||
|
matching = [w for w in wheels if (w.rocm, w.torch, w.python) == target]
|
||||||
|
if not matching:
|
||||||
|
available = sorted({_label(w.rocm, w.torch, w.python) for w in wheels})
|
||||||
|
raise LookupError(
|
||||||
|
f"No AITER nightly for {_label(*target)}. "
|
||||||
|
f"Available: {', '.join(available) or 'none'}"
|
||||||
|
)
|
||||||
|
return max(matching, key=lambda w: (w.build_date, _base_version_key(w)))
|
||||||
|
|
||||||
|
|
||||||
|
def fetch(url: str) -> str:
|
||||||
|
"""GET url as text. A failure exits 1, so Buildkite retries the step."""
|
||||||
|
with urllib.request.urlopen(url, timeout=60) as response:
|
||||||
|
return response.read().decode()
|
||||||
|
|
||||||
|
|
||||||
|
def annotation(wheel: Wheel, today: datetime.date) -> str:
|
||||||
|
"""The Buildkite annotation naming the wheel this build tests.
|
||||||
|
|
||||||
|
Starts with :warning: if the wheel is stale; the overlay script styles it so.
|
||||||
|
"""
|
||||||
|
age = today - wheel.build_date
|
||||||
|
stale = (
|
||||||
|
f":warning: **AITER nightly is {age.days} days old**: "
|
||||||
|
f"no newer build has been published for "
|
||||||
|
f"{_label(wheel.rocm, wheel.torch, wheel.python)}.\n\n"
|
||||||
|
if age > STALE_AFTER
|
||||||
|
else ""
|
||||||
|
)
|
||||||
|
return stale + (
|
||||||
|
f":crescent_moon: **AITER nightly**: main at "
|
||||||
|
f"[`{wheel.commit}`]({AITER_COMMIT_URL}{wheel.commit}), "
|
||||||
|
f"built {wheel.build_date.isoformat()} for torch {wheel.torch} "
|
||||||
|
f"(`{wheel.version}`)"
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
class NoWheel(Exception):
|
||||||
|
"""No wheel fits this image's ROCm, torch and Python. Exit 10."""
|
||||||
|
|
||||||
|
|
||||||
|
def _image_wheel(wheel_url: str) -> Wheel:
|
||||||
|
"""The wheel at wheel_url, if it fits this image's ROCm, torch and Python."""
|
||||||
|
wheel = wheel_from_url(wheel_url)
|
||||||
|
if not wheel:
|
||||||
|
raise NoWheel(f"Not an AITER nightly wheel: {wheel_url}")
|
||||||
|
return _for_image([wheel])
|
||||||
|
|
||||||
|
|
||||||
|
def _image() -> tuple[str, str, str]:
|
||||||
|
"""This image's ROCm, torch and Python, as wheel names spell them."""
|
||||||
|
try:
|
||||||
|
rocm = rocm_release(rocm_version())
|
||||||
|
except (OSError, ValueError) as error:
|
||||||
|
raise NoWheel(f"Cannot read this image's ROCm version: {error}") from error
|
||||||
|
try:
|
||||||
|
torch = torch_release(importlib.metadata.version("torch"))
|
||||||
|
except (importlib.metadata.PackageNotFoundError, ValueError) as error:
|
||||||
|
raise NoWheel(f"Cannot read this image's torch version: {error}") from error
|
||||||
|
return rocm, torch, python_tag(sys.version_info[:2])
|
||||||
|
|
||||||
|
|
||||||
|
def _for_image(wheels: list[Wheel]) -> Wheel:
|
||||||
|
"""The newest of wheels for the image this runs in."""
|
||||||
|
try:
|
||||||
|
return select_wheel(wheels, *_image())
|
||||||
|
except LookupError as error:
|
||||||
|
raise NoWheel(str(error)) from error
|
||||||
|
|
||||||
|
|
||||||
|
def select(index_url: str, wheel_url: str = "") -> Wheel:
|
||||||
|
"""The wheel to install: wheel_url on a retry, else the newest.
|
||||||
|
|
||||||
|
However old the newest is, it is tested; the annotation shows its build date.
|
||||||
|
"""
|
||||||
|
if wheel_url:
|
||||||
|
return _image_wheel(wheel_url)
|
||||||
|
return _for_image(parse_index(fetch(index_url), index_url))
|
||||||
|
|
||||||
|
|
||||||
|
def _today() -> datetime.date:
|
||||||
|
"""Today in UTC; a function so tests can set the date."""
|
||||||
|
return datetime.datetime.now(datetime.UTC).date()
|
||||||
|
|
||||||
|
|
||||||
|
# Not 1 or 2, which Buildkite retries; see aiter-nightly-overlay.sh.
|
||||||
|
EXIT_NO_WHEEL = 10
|
||||||
|
|
||||||
|
|
||||||
|
def main(argv=None) -> int:
|
||||||
|
parser = argparse.ArgumentParser(description=__doc__)
|
||||||
|
parser.add_argument("--index-url", default=INDEX_URL)
|
||||||
|
parser.add_argument(
|
||||||
|
"--wheel-url", default="", help="a retry's earlier choice; skips the index"
|
||||||
|
)
|
||||||
|
args = parser.parse_args(argv)
|
||||||
|
try:
|
||||||
|
wheel = select(args.index_url, args.wheel_url)
|
||||||
|
except NoWheel as error:
|
||||||
|
print(error)
|
||||||
|
return EXIT_NO_WHEEL
|
||||||
|
print(wheel.url)
|
||||||
|
print(annotation(wheel, _today()))
|
||||||
|
return 0
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
sys.exit(main())
|
||||||
@@ -0,0 +1,78 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
# SPDX-License-Identifier: Apache-2.0
|
||||||
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||||
|
#
|
||||||
|
# Derive everything the release pipeline needs about a ROCm stack from its base
|
||||||
|
# Dockerfile, so the stack's image is the single input to every ROCm script.
|
||||||
|
#
|
||||||
|
# Usage: source .buildkite/scripts/rocm/stack.sh <base-dockerfile>
|
||||||
|
# e.g. docker/Dockerfile.rocm_base (ROCm 10.0) or docker/Dockerfile.rocm_72_base
|
||||||
|
#
|
||||||
|
# Exports:
|
||||||
|
# ROCM_STACK_BASE_DOCKERFILE the base Dockerfile
|
||||||
|
# ROCM_STACK_DOCKERFILE the matching vLLM Dockerfile (base name minus _base)
|
||||||
|
# ROCM_STACK_THEROCK 1 if the ROCm SDK comes from TheRock wheels
|
||||||
|
# ROCM_STACK_VERSION ROCm version, e.g. 10.0.0 or 7.2.3
|
||||||
|
# ROCM_STACK_VARIANT wheel variant and Docker Hub tag flavor from major.minor,
|
||||||
|
# same rule as setup.py (rocm100, rocm72)
|
||||||
|
# ROCM_STACK_IMAGE_KEY hash of the base Dockerfile (base image cache key)
|
||||||
|
# ROCM_STACK_WHEEL_KEY hash of the base Dockerfile plus files it COPYs from
|
||||||
|
# the repo (base wheel cache key)
|
||||||
|
# ROCM_STACK_ECR_BASE ECR tag of the cached base image
|
||||||
|
# ROCM_STACK_ECR_IMAGE ECR tag of this commit's release image
|
||||||
|
# ROCM_STACK_BASE_WHEELS_DIR local dir for base wheels (also the artifact path)
|
||||||
|
# ROCM_STACK_VLLM_WHEEL_DIR local dir for the vLLM wheel (also the artifact path)
|
||||||
|
|
||||||
|
rocm_stack_init() {
|
||||||
|
local base="$1"
|
||||||
|
if [[ ! -f "$base" ]]; then
|
||||||
|
echo "ROCm base Dockerfile not found: $base" >&2
|
||||||
|
return 2
|
||||||
|
fi
|
||||||
|
ROCM_STACK_BASE_DOCKERFILE="$base"
|
||||||
|
ROCM_STACK_DOCKERFILE="${base%_base}"
|
||||||
|
|
||||||
|
local sdk
|
||||||
|
sdk=$(sed -nE 's/^ARG ROCM_SDK_VERSION=([0-9.]+).*/\1/p' "$base" | head -1)
|
||||||
|
if [[ -n "$sdk" ]]; then
|
||||||
|
ROCM_STACK_THEROCK=1
|
||||||
|
ROCM_STACK_VERSION="$sdk"
|
||||||
|
else
|
||||||
|
ROCM_STACK_THEROCK=0
|
||||||
|
# BASE_IMAGE format: rocm/dev-ubuntu-22.04:7.2.3-complete -> 7.2.3
|
||||||
|
ROCM_STACK_VERSION=$(sed -nE 's/^ARG BASE_IMAGE=.*:([0-9]+(\.[0-9]+)+).*/\1/p' "$base" | head -1)
|
||||||
|
fi
|
||||||
|
if [[ -z "$ROCM_STACK_VERSION" ]]; then
|
||||||
|
echo "Could not determine the ROCm version from $base" >&2
|
||||||
|
return 2
|
||||||
|
fi
|
||||||
|
|
||||||
|
local major minor
|
||||||
|
IFS=. read -r major minor _ <<< "$ROCM_STACK_VERSION"
|
||||||
|
ROCM_STACK_VARIANT="rocm${major}${minor}"
|
||||||
|
|
||||||
|
ROCM_STACK_IMAGE_KEY=$(sha256sum "$base" | cut -c1-16)
|
||||||
|
local inputs
|
||||||
|
inputs=$(grep -E '^COPY ' "$base" | grep -v -- '--from' | awk '{print $2}' || true)
|
||||||
|
if [[ -z "$inputs" ]]; then
|
||||||
|
ROCM_STACK_WHEEL_KEY="$ROCM_STACK_IMAGE_KEY"
|
||||||
|
else
|
||||||
|
# shellcheck disable=SC2086
|
||||||
|
ROCM_STACK_WHEEL_KEY=$(sha256sum "$base" $inputs | sha256sum | cut -c1-16)
|
||||||
|
fi
|
||||||
|
|
||||||
|
local ecr="public.ecr.aws/q9t5s3a7/vllm-release-repo"
|
||||||
|
ROCM_STACK_ECR_BASE="${ecr}:${ROCM_STACK_IMAGE_KEY}-${ROCM_STACK_VARIANT}-base"
|
||||||
|
ROCM_STACK_ECR_IMAGE="${ecr}:${BUILDKITE_COMMIT:-unknown}-${ROCM_STACK_VARIANT}"
|
||||||
|
ROCM_STACK_BASE_WHEELS_DIR="artifacts/${ROCM_STACK_VARIANT}-base-wheels"
|
||||||
|
ROCM_STACK_VLLM_WHEEL_DIR="artifacts/${ROCM_STACK_VARIANT}-vllm-wheel"
|
||||||
|
|
||||||
|
export ROCM_STACK_BASE_DOCKERFILE ROCM_STACK_DOCKERFILE ROCM_STACK_THEROCK \
|
||||||
|
ROCM_STACK_VERSION ROCM_STACK_VARIANT ROCM_STACK_IMAGE_KEY \
|
||||||
|
ROCM_STACK_WHEEL_KEY ROCM_STACK_ECR_BASE ROCM_STACK_ECR_IMAGE \
|
||||||
|
ROCM_STACK_BASE_WHEELS_DIR ROCM_STACK_VLLM_WHEEL_DIR
|
||||||
|
}
|
||||||
|
|
||||||
|
if [[ $# -gt 0 ]]; then
|
||||||
|
rocm_stack_init "$1"
|
||||||
|
fi
|
||||||
@@ -23,7 +23,7 @@ export PATH="$CARGO_HOME/bin:$PATH"
|
|||||||
|
|
||||||
CARGO_BINSTALL_VERSION="${CARGO_BINSTALL_VERSION:-1.20.1}"
|
CARGO_BINSTALL_VERSION="${CARGO_BINSTALL_VERSION:-1.20.1}"
|
||||||
UV_VERSION="${UV_VERSION:-0.11.28}"
|
UV_VERSION="${UV_VERSION:-0.11.28}"
|
||||||
PYO3_PYTHON_VERSION="${PYO3_PYTHON_VERSION:-3.12}"
|
UV_SCRIPT_PYTHON_VERSION="${UV_SCRIPT_PYTHON_VERSION:-3.12}"
|
||||||
|
|
||||||
CARGO_SORT_VERSION_REQ="${CARGO_SORT_VERSION_REQ:-2}"
|
CARGO_SORT_VERSION_REQ="${CARGO_SORT_VERSION_REQ:-2}"
|
||||||
CARGO_DENY_VERSION_REQ="${CARGO_DENY_VERSION_REQ:-0.20}"
|
CARGO_DENY_VERSION_REQ="${CARGO_DENY_VERSION_REQ:-0.20}"
|
||||||
@@ -60,12 +60,12 @@ install_cargo_binstall() {
|
|||||||
|
|
||||||
install_cargo_sort() {
|
install_cargo_sort() {
|
||||||
log_section "Installing cargo-sort ${CARGO_SORT_VERSION_REQ}"
|
log_section "Installing cargo-sort ${CARGO_SORT_VERSION_REQ}"
|
||||||
cargo binstall --no-confirm --force "cargo-sort@${CARGO_SORT_VERSION_REQ}"
|
cargo binstall --no-confirm --force --locked "cargo-sort@${CARGO_SORT_VERSION_REQ}"
|
||||||
}
|
}
|
||||||
|
|
||||||
install_cargo_deny() {
|
install_cargo_deny() {
|
||||||
log_section "Installing cargo-deny ${CARGO_DENY_VERSION_REQ}"
|
log_section "Installing cargo-deny ${CARGO_DENY_VERSION_REQ}"
|
||||||
cargo binstall --no-confirm --force "cargo-deny@${CARGO_DENY_VERSION_REQ}"
|
cargo binstall --no-confirm --force --locked "cargo-deny@${CARGO_DENY_VERSION_REQ}"
|
||||||
}
|
}
|
||||||
|
|
||||||
install_cargo_nextest() {
|
install_cargo_nextest() {
|
||||||
@@ -74,6 +74,7 @@ install_cargo_nextest() {
|
|||||||
--no-confirm \
|
--no-confirm \
|
||||||
--force \
|
--force \
|
||||||
--secure \
|
--secure \
|
||||||
|
--locked \
|
||||||
"cargo-nextest@${CARGO_NEXTEST_VERSION_REQ}"
|
"cargo-nextest@${CARGO_NEXTEST_VERSION_REQ}"
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -83,34 +84,7 @@ install_uv() {
|
|||||||
"https://github.com/astral-sh/uv/releases/download/${UV_VERSION}/uv-installer.sh" \
|
"https://github.com/astral-sh/uv/releases/download/${UV_VERSION}/uv-installer.sh" \
|
||||||
| env UV_INSTALL_DIR="$CARGO_HOME/bin" sh
|
| env UV_INSTALL_DIR="$CARGO_HOME/bin" sh
|
||||||
uv --version
|
uv --version
|
||||||
}
|
uv python install "$UV_SCRIPT_PYTHON_VERSION"
|
||||||
|
|
||||||
setup_pyo3_python() {
|
|
||||||
log_section "Installing Python ${PYO3_PYTHON_VERSION} for PyO3 tests"
|
|
||||||
uv python install "$PYO3_PYTHON_VERSION"
|
|
||||||
PYO3_PYTHON="$(uv python find \
|
|
||||||
--managed-python \
|
|
||||||
--no-project \
|
|
||||||
--resolve-links \
|
|
||||||
"$PYO3_PYTHON_VERSION")"
|
|
||||||
export PYO3_PYTHON
|
|
||||||
|
|
||||||
local python_libdir
|
|
||||||
python_libdir="$("$PYO3_PYTHON" - <<'PY'
|
|
||||||
import pathlib
|
|
||||||
import sysconfig
|
|
||||||
|
|
||||||
libdir = pathlib.Path(sysconfig.get_config_var("LIBDIR"))
|
|
||||||
ldlibrary = sysconfig.get_config_var("LDLIBRARY")
|
|
||||||
assert sysconfig.get_config_var("Py_ENABLE_SHARED") == 1
|
|
||||||
assert ldlibrary
|
|
||||||
assert (libdir / ldlibrary).exists(), libdir / ldlibrary
|
|
||||||
print(libdir)
|
|
||||||
PY
|
|
||||||
)"
|
|
||||||
|
|
||||||
export LD_LIBRARY_PATH="${python_libdir}:${LD_LIBRARY_PATH:-}"
|
|
||||||
export LIBRARY_PATH="${python_libdir}:${LIBRARY_PATH:-}"
|
|
||||||
}
|
}
|
||||||
|
|
||||||
run_style_clippy() {
|
run_style_clippy() {
|
||||||
@@ -144,7 +118,6 @@ run_style_clippy() {
|
|||||||
|
|
||||||
run_tests() {
|
run_tests() {
|
||||||
install_uv
|
install_uv
|
||||||
setup_pyo3_python
|
|
||||||
install_cargo_binstall
|
install_cargo_binstall
|
||||||
install_cargo_nextest
|
install_cargo_nextest
|
||||||
|
|
||||||
|
|||||||
@@ -1,24 +0,0 @@
|
|||||||
#!/bin/bash
|
|
||||||
|
|
||||||
set -euo pipefail
|
|
||||||
|
|
||||||
docker_root=$(docker info -f '{{.DockerRootDir}}')
|
|
||||||
if [ -z "$docker_root" ]; then
|
|
||||||
echo "Failed to determine Docker root directory."
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
echo "Docker root directory: $docker_root"
|
|
||||||
# Check disk usage of the filesystem where Docker's root directory is located
|
|
||||||
disk_usage=$(df "$docker_root" | tail -1 | awk '{print $5}' | sed 's/%//')
|
|
||||||
# Define the threshold
|
|
||||||
threshold=70
|
|
||||||
if [ "$disk_usage" -gt "$threshold" ]; then
|
|
||||||
echo "Disk usage is above $threshold%. Cleaning up Docker images and volumes..."
|
|
||||||
# Remove dangling images (those that are not tagged and not used by any container)
|
|
||||||
docker image prune -f
|
|
||||||
# Remove unused volumes / force the system prune for old images as well.
|
|
||||||
docker volume prune -f && docker system prune --force --filter "until=24h" --all
|
|
||||||
echo "Docker images and volumes cleanup completed."
|
|
||||||
else
|
|
||||||
echo "Disk usage is below $threshold%. No cleanup needed."
|
|
||||||
fi
|
|
||||||
@@ -1,14 +0,0 @@
|
|||||||
# Environment config
|
|
||||||
TEST_NAME=llama8b
|
|
||||||
CONTAINER_NAME=tpu-test
|
|
||||||
|
|
||||||
# vllm config
|
|
||||||
MODEL=meta-llama/Llama-3.1-8B-Instruct
|
|
||||||
MAX_NUM_SEQS=256
|
|
||||||
MAX_NUM_BATCHED_TOKENS=1024
|
|
||||||
TENSOR_PARALLEL_SIZE=1
|
|
||||||
MAX_MODEL_LEN=2048
|
|
||||||
DOWNLOAD_DIR=/mnt/disks/persist
|
|
||||||
EXPECTED_THROUGHPUT=8.0
|
|
||||||
INPUT_LEN=1800
|
|
||||||
OUTPUT_LEN=128
|
|
||||||
@@ -1,91 +0,0 @@
|
|||||||
#!/bin/bash
|
|
||||||
|
|
||||||
if [ ! -f "$1" ]; then
|
|
||||||
echo "Error: The env file '$1' does not exist."
|
|
||||||
exit 1 # Exit the script with a non-zero status to indicate an error
|
|
||||||
fi
|
|
||||||
|
|
||||||
ENV_FILE=$1
|
|
||||||
|
|
||||||
# For testing on local vm, use `set -a` to export all variables
|
|
||||||
source /etc/environment
|
|
||||||
# shellcheck source=/dev/null
|
|
||||||
source "$ENV_FILE"
|
|
||||||
|
|
||||||
remove_docker_container() {
|
|
||||||
docker rm -f "$CONTAINER_NAME" || true;
|
|
||||||
}
|
|
||||||
|
|
||||||
trap remove_docker_container EXIT
|
|
||||||
|
|
||||||
# Remove the container that might not be cleaned up in the previous run.
|
|
||||||
remove_docker_container
|
|
||||||
|
|
||||||
LOG_ROOT=$(mktemp -d)
|
|
||||||
# If mktemp fails, set -e will cause the script to exit.
|
|
||||||
echo "Results will be stored in: $LOG_ROOT"
|
|
||||||
|
|
||||||
if [ -z "$HF_TOKEN" ]; then
|
|
||||||
echo "Error: HF_TOKEN is not set or is empty."
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
# Make sure mounted disk or dir exists
|
|
||||||
if [ ! -d "$DOWNLOAD_DIR" ]; then
|
|
||||||
echo "Error: Folder $DOWNLOAD_DIR does not exist. This is useually a mounted drive. If no mounted drive, just create a folder."
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
echo "Run model $MODEL"
|
|
||||||
echo
|
|
||||||
|
|
||||||
echo "starting docker...$CONTAINER_NAME"
|
|
||||||
echo
|
|
||||||
docker run \
|
|
||||||
-v "$DOWNLOAD_DIR":"$DOWNLOAD_DIR" \
|
|
||||||
--env-file "$ENV_FILE" \
|
|
||||||
-e HF_TOKEN="$HF_TOKEN" \
|
|
||||||
-e TARGET_COMMIT="$BUILDKITE_COMMIT" \
|
|
||||||
-e MODEL="$MODEL" \
|
|
||||||
-e WORKSPACE=/workspace \
|
|
||||||
--name "$CONTAINER_NAME" \
|
|
||||||
-d \
|
|
||||||
--privileged \
|
|
||||||
--network host \
|
|
||||||
-v /dev/shm:/dev/shm \
|
|
||||||
vllm/vllm-tpu-bm tail -f /dev/null
|
|
||||||
|
|
||||||
echo "run script..."
|
|
||||||
echo
|
|
||||||
docker exec "$CONTAINER_NAME" /bin/bash -c ".buildkite/scripts/tpu/run_bm.sh"
|
|
||||||
|
|
||||||
echo "copy result back..."
|
|
||||||
VLLM_LOG="$LOG_ROOT/$TEST_NAME"_vllm_log.txt
|
|
||||||
BM_LOG="$LOG_ROOT/$TEST_NAME"_bm_log.txt
|
|
||||||
docker cp "$CONTAINER_NAME:/workspace/vllm_log.txt" "$VLLM_LOG"
|
|
||||||
docker cp "$CONTAINER_NAME:/workspace/bm_log.txt" "$BM_LOG"
|
|
||||||
|
|
||||||
throughput=$(grep "Request throughput (req/s):" "$BM_LOG" | sed 's/[^0-9.]//g')
|
|
||||||
echo "throughput for $TEST_NAME at $BUILDKITE_COMMIT: $throughput"
|
|
||||||
|
|
||||||
if [ "$BUILDKITE" = "true" ]; then
|
|
||||||
echo "Running inside Buildkite"
|
|
||||||
buildkite-agent artifact upload "$VLLM_LOG"
|
|
||||||
buildkite-agent artifact upload "$BM_LOG"
|
|
||||||
else
|
|
||||||
echo "Not running inside Buildkite"
|
|
||||||
fi
|
|
||||||
|
|
||||||
#
|
|
||||||
# compare the throughput with EXPECTED_THROUGHPUT
|
|
||||||
# and assert meeting the expectation
|
|
||||||
#
|
|
||||||
if [[ -z "$throughput" || ! "$throughput" =~ ^[0-9]+([.][0-9]+)?$ ]]; then
|
|
||||||
echo "Failed to get the throughput"
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
if (( $(echo "$throughput < $EXPECTED_THROUGHPUT" | bc -l) )); then
|
|
||||||
echo "Error: throughput($throughput) is less than expected($EXPECTED_THROUGHPUT)"
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
@@ -1,14 +0,0 @@
|
|||||||
# Environment config
|
|
||||||
TEST_NAME=llama8bw8a8
|
|
||||||
CONTAINER_NAME=tpu-test
|
|
||||||
|
|
||||||
# vllm config
|
|
||||||
MODEL=RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a8
|
|
||||||
MAX_NUM_SEQS=128
|
|
||||||
MAX_NUM_BATCHED_TOKENS=1024
|
|
||||||
TENSOR_PARALLEL_SIZE=1
|
|
||||||
MAX_MODEL_LEN=2048
|
|
||||||
DOWNLOAD_DIR=/mnt/disks/persist
|
|
||||||
EXPECTED_THROUGHPUT=8.7
|
|
||||||
INPUT_LEN=1800
|
|
||||||
OUTPUT_LEN=128
|
|
||||||
@@ -1,93 +0,0 @@
|
|||||||
#!/bin/bash
|
|
||||||
|
|
||||||
set -euo pipefail
|
|
||||||
|
|
||||||
VLLM_LOG="$WORKSPACE/vllm_log.txt"
|
|
||||||
BM_LOG="$WORKSPACE/bm_log.txt"
|
|
||||||
|
|
||||||
if [ -n "$TARGET_COMMIT" ]; then
|
|
||||||
head_hash=$(git rev-parse HEAD)
|
|
||||||
if [ "$TARGET_COMMIT" != "$head_hash" ]; then
|
|
||||||
echo "Error: target commit $TARGET_COMMIT does not match HEAD: $head_hash"
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
fi
|
|
||||||
|
|
||||||
echo "model: $MODEL"
|
|
||||||
echo
|
|
||||||
|
|
||||||
#
|
|
||||||
# create a log folder
|
|
||||||
#
|
|
||||||
mkdir "$WORKSPACE/log"
|
|
||||||
|
|
||||||
# TODO: Move to image building.
|
|
||||||
pip install pandas
|
|
||||||
pip install datasets
|
|
||||||
|
|
||||||
#
|
|
||||||
# create sonnet_4x
|
|
||||||
#
|
|
||||||
echo "Create sonnet_4x.txt"
|
|
||||||
echo "" > benchmarks/sonnet_4x.txt
|
|
||||||
for _ in {1..4}
|
|
||||||
do
|
|
||||||
cat benchmarks/sonnet.txt >> benchmarks/sonnet_4x.txt
|
|
||||||
done
|
|
||||||
|
|
||||||
#
|
|
||||||
# start vllm service in backend
|
|
||||||
#
|
|
||||||
echo "lanching vllm..."
|
|
||||||
echo "logging to $VLLM_LOG"
|
|
||||||
echo
|
|
||||||
|
|
||||||
vllm serve "$MODEL" \
|
|
||||||
--seed 42 \
|
|
||||||
--max-num-seqs "$MAX_NUM_SEQS" \
|
|
||||||
--max-num-batched-tokens "$MAX_NUM_BATCHED_TOKENS" \
|
|
||||||
--tensor-parallel-size "$TENSOR_PARALLEL_SIZE" \
|
|
||||||
--no-enable-prefix-caching \
|
|
||||||
--download_dir "$DOWNLOAD_DIR" \
|
|
||||||
--max-model-len "$MAX_MODEL_LEN" > "$VLLM_LOG" 2>&1 &
|
|
||||||
|
|
||||||
|
|
||||||
echo "wait for 20 minutes.."
|
|
||||||
echo
|
|
||||||
# sleep 1200
|
|
||||||
# wait for 10 minutes...
|
|
||||||
for _ in {1..120}; do
|
|
||||||
# TODO: detect other type of errors.
|
|
||||||
if grep -Fq "raise RuntimeError" "$VLLM_LOG"; then
|
|
||||||
echo "Detected RuntimeError, exiting."
|
|
||||||
exit 1
|
|
||||||
elif grep -Fq "Application startup complete" "$VLLM_LOG"; then
|
|
||||||
echo "Application started"
|
|
||||||
break
|
|
||||||
else
|
|
||||||
echo "wait for 10 seconds..."
|
|
||||||
sleep 10
|
|
||||||
fi
|
|
||||||
done
|
|
||||||
|
|
||||||
#
|
|
||||||
# run test
|
|
||||||
#
|
|
||||||
echo "run benchmark test..."
|
|
||||||
echo "logging to $BM_LOG"
|
|
||||||
echo
|
|
||||||
vllm bench serve \
|
|
||||||
--backend vllm \
|
|
||||||
--model "$MODEL" \
|
|
||||||
--dataset-name sonnet \
|
|
||||||
--dataset-path benchmarks/sonnet_4x.txt \
|
|
||||||
--sonnet-input-len "$INPUT_LEN" \
|
|
||||||
--sonnet-output-len "$OUTPUT_LEN" \
|
|
||||||
--ignore-eos > "$BM_LOG"
|
|
||||||
|
|
||||||
echo "completed..."
|
|
||||||
echo
|
|
||||||
|
|
||||||
throughput=$(grep "Request throughput (req/s):" "$BM_LOG" | sed 's/[^0-9.]//g')
|
|
||||||
echo "throughput: $throughput"
|
|
||||||
echo
|
|
||||||
@@ -4,21 +4,31 @@
|
|||||||
#
|
#
|
||||||
# Upload ROCm wheels to S3 with proper index generation
|
# Upload ROCm wheels to S3 with proper index generation
|
||||||
#
|
#
|
||||||
|
# Usage: upload-rocm-wheels.sh <base-dockerfile>
|
||||||
|
# base-dockerfile the ROCm stack, e.g. docker/Dockerfile.rocm_base (see rocm/stack.sh)
|
||||||
|
#
|
||||||
# Required environment variables:
|
# Required environment variables:
|
||||||
# AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY (or IAM role)
|
# AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY (or IAM role)
|
||||||
# S3_BUCKET (default: vllm-wheels)
|
# S3_BUCKET (default: vllm-wheels)
|
||||||
#
|
#
|
||||||
# S3 path structure:
|
# S3 path structure:
|
||||||
# s3://vllm-wheels/rocm/{commit}/ - All wheels for this commit
|
# s3://vllm-wheels/rocm/{commit}/<variant>-wheels/ - This stack's wheels for this commit
|
||||||
# s3://vllm-wheels/rocm/nightly/ - Index pointing to latest nightly
|
# s3://vllm-wheels/rocm/{commit}/<variant>/ - Index per ROCm variant (e.g. rocm100)
|
||||||
# s3://vllm-wheels/rocm/{version}/ - Index for release versions
|
# s3://vllm-wheels/rocm/nightly/<variant>/ - Index pointing to latest nightly
|
||||||
|
# s3://vllm-wheels/rocm/{version}/<variant>/ - Index for release versions
|
||||||
|
# The top-level index.html at each prefix lists every variant present, since
|
||||||
|
# several ROCm stacks publish into the same prefixes.
|
||||||
|
|
||||||
set -ex
|
set -ex
|
||||||
|
|
||||||
# ======== Configuration ========
|
# ======== Configuration ========
|
||||||
BUCKET="${S3_BUCKET:-vllm-wheels}"
|
BUCKET="${S3_BUCKET:-vllm-wheels}"
|
||||||
|
# shellcheck source=.buildkite/scripts/rocm/stack.sh
|
||||||
|
source "$(dirname "${BASH_SOURCE[0]}")/rocm/stack.sh" "${1:?Usage: $0 <base-dockerfile>}"
|
||||||
ROCM_SUBPATH="rocm/${BUILDKITE_COMMIT}"
|
ROCM_SUBPATH="rocm/${BUILDKITE_COMMIT}"
|
||||||
S3_COMMIT_PREFIX="s3://$BUCKET/$ROCM_SUBPATH/"
|
WHEEL_DIRS="$ROCM_STACK_BASE_WHEELS_DIR $ROCM_STACK_VLLM_WHEEL_DIR"
|
||||||
|
WHEEL_SUBPATH="$ROCM_SUBPATH/${ROCM_STACK_VARIANT}-wheels"
|
||||||
|
S3_WHEEL_PREFIX="s3://$BUCKET/$WHEEL_SUBPATH/"
|
||||||
INDICES_OUTPUT_DIR="rocm-indices"
|
INDICES_OUTPUT_DIR="rocm-indices"
|
||||||
|
|
||||||
echo "========================================"
|
echo "========================================"
|
||||||
@@ -49,9 +59,11 @@ source .buildkite/scripts/lib/manylinux.sh
|
|||||||
# ======== Part 1: Collect and prepare wheels ========
|
# ======== Part 1: Collect and prepare wheels ========
|
||||||
|
|
||||||
# Collect all wheels
|
# Collect all wheels
|
||||||
|
rm -rf all-rocm-wheels "$INDICES_OUTPUT_DIR"
|
||||||
mkdir -p all-rocm-wheels
|
mkdir -p all-rocm-wheels
|
||||||
cp artifacts/rocm-base-wheels/*.whl all-rocm-wheels/ 2>/dev/null || true
|
for dir in $WHEEL_DIRS; do
|
||||||
cp artifacts/rocm-vllm-wheel/*.whl all-rocm-wheels/ 2>/dev/null || true
|
cp "$dir"/*.whl all-rocm-wheels/ 2>/dev/null || true
|
||||||
|
done
|
||||||
|
|
||||||
WHEEL_COUNT=$(find all-rocm-wheels -maxdepth 1 -name '*.whl' 2>/dev/null | wc -l)
|
WHEEL_COUNT=$(find all-rocm-wheels -maxdepth 1 -name '*.whl' 2>/dev/null | wc -l)
|
||||||
echo "Total wheels to upload: $WHEEL_COUNT"
|
echo "Total wheels to upload: $WHEEL_COUNT"
|
||||||
@@ -84,9 +96,9 @@ ls -lh all-rocm-wheels/
|
|||||||
# ======== Part 2: Upload wheels to S3 ========
|
# ======== Part 2: Upload wheels to S3 ========
|
||||||
|
|
||||||
echo ""
|
echo ""
|
||||||
echo "Uploading wheels to $S3_COMMIT_PREFIX"
|
echo "Uploading wheels to $S3_WHEEL_PREFIX"
|
||||||
for wheel in all-rocm-wheels/*.whl; do
|
for wheel in all-rocm-wheels/*.whl; do
|
||||||
aws s3 cp "$wheel" "$S3_COMMIT_PREFIX"
|
aws s3 cp "$wheel" "$S3_WHEEL_PREFIX"
|
||||||
done
|
done
|
||||||
|
|
||||||
# ======== Part 3: Generate and upload indices ========
|
# ======== Part 3: Generate and upload indices ========
|
||||||
@@ -95,28 +107,63 @@ done
|
|||||||
echo ""
|
echo ""
|
||||||
echo "Generating indices..."
|
echo "Generating indices..."
|
||||||
obj_json="rocm-objects.json"
|
obj_json="rocm-objects.json"
|
||||||
aws s3api list-objects-v2 --bucket "$BUCKET" --prefix "$ROCM_SUBPATH/" --delimiter / --output json > "$obj_json"
|
aws s3api list-objects-v2 --bucket "$BUCKET" --prefix "$WHEEL_SUBPATH/" --delimiter / --output json > "$obj_json"
|
||||||
|
|
||||||
mkdir -p "$INDICES_OUTPUT_DIR"
|
mkdir -p "$INDICES_OUTPUT_DIR"
|
||||||
|
|
||||||
# Use the existing generate-nightly-index.py
|
# Use the existing generate-nightly-index.py
|
||||||
# HACK: Replace regex module with stdlib re (same as CUDA script)
|
# HACK: Replace regex module with stdlib re (same as CUDA script)
|
||||||
sed -i 's/import regex as re/import re/g' .buildkite/scripts/generate-nightly-index.py
|
sed -i 's/import regex as re/import re/g' .buildkite/scripts/generate-nightly-index.py
|
||||||
|
sed -i 's/import regex as re/import re/g' tools/vllm-rocm/therock_wheels.py
|
||||||
|
sed -i 's/import pybase64 as base64/import base64/g' tools/vllm-rocm/therock_wheels.py
|
||||||
|
|
||||||
|
INDEX_ARGS=(--version "$ROCM_SUBPATH" --wheel-dir "${WHEEL_SUBPATH#rocm/}")
|
||||||
|
# TheRock's SDK, device kernels and torchvision/torchaudio are linked, not hosted
|
||||||
|
if [[ "$ROCM_STACK_THEROCK" == "1" ]]; then
|
||||||
|
$PYTHON tools/vllm-rocm/therock_wheels.py external-links \
|
||||||
|
--dockerfile "$ROCM_STACK_BASE_DOCKERFILE" \
|
||||||
|
--torch-wheel "$(ls "$ROCM_STACK_BASE_WHEELS_DIR"/torch-*.whl)" > therock-external-links.txt
|
||||||
|
cat therock-external-links.txt
|
||||||
|
INDEX_ARGS+=(--external-links therock-external-links.txt)
|
||||||
|
fi
|
||||||
$PYTHON .buildkite/scripts/generate-nightly-index.py \
|
$PYTHON .buildkite/scripts/generate-nightly-index.py \
|
||||||
--version "$ROCM_SUBPATH" \
|
"${INDEX_ARGS[@]}" \
|
||||||
--current-objects "$obj_json" \
|
--current-objects "$obj_json" \
|
||||||
--output-dir "$INDICES_OUTPUT_DIR" \
|
--output-dir "$INDICES_OUTPUT_DIR" \
|
||||||
--comment "ROCm commit $BUILDKITE_COMMIT"
|
--comment "ROCm commit $BUILDKITE_COMMIT"
|
||||||
|
|
||||||
# Upload indices to commit directory
|
# Upload this build's variant indices under an S3 prefix (e.g. rocm/nightly), then
|
||||||
echo "Uploading indices to $S3_COMMIT_PREFIX"
|
# rebuild that prefix's top-level project list from every variant now present.
|
||||||
aws s3 cp --recursive "$INDICES_OUTPUT_DIR/" "$S3_COMMIT_PREFIX"
|
publish_indices() {
|
||||||
|
local prefix="$1"
|
||||||
|
local listing variants merged
|
||||||
|
echo "Uploading indices to s3://$BUCKET/$prefix/"
|
||||||
|
aws s3 cp --recursive "$INDICES_OUTPUT_DIR/" "s3://$BUCKET/$prefix/" --exclude "index.html"
|
||||||
|
listing=$(aws s3api list-objects-v2 --bucket "$BUCKET" --prefix "$prefix/" \
|
||||||
|
--delimiter / --query 'CommonPrefixes[].Prefix' --output text)
|
||||||
|
variants=$(tr '\t' '\n' <<< "$listing" | sed -n "s|^$prefix/\(rocm[0-9]*\)/$|\1|p" | sort -u)
|
||||||
|
merged=$(mktemp)
|
||||||
|
{
|
||||||
|
echo '<!DOCTYPE html>'
|
||||||
|
echo '<html>'
|
||||||
|
echo ' <meta name="pypi:repository-version" content="1.0">'
|
||||||
|
echo ' <body>'
|
||||||
|
for variant in $variants; do
|
||||||
|
echo " <a href=\"$variant/\">$variant/</a><br/>"
|
||||||
|
done
|
||||||
|
echo ' </body>'
|
||||||
|
echo '</html>'
|
||||||
|
} > "$merged"
|
||||||
|
echo "Variants under $prefix/: $(echo "$variants" | tr '\n' ' ')"
|
||||||
|
aws s3 cp "$merged" "s3://$BUCKET/$prefix/index.html"
|
||||||
|
rm -f "$merged"
|
||||||
|
}
|
||||||
|
|
||||||
|
publish_indices "$ROCM_SUBPATH"
|
||||||
|
|
||||||
# Only scheduled nightly builds should update the moving nightly index.
|
# Only scheduled nightly builds should update the moving nightly index.
|
||||||
if [[ "${NIGHTLY:-0}" == "1" ]]; then
|
if [[ "${NIGHTLY:-0}" == "1" ]]; then
|
||||||
echo "Updating rocm/nightly/ index..."
|
publish_indices "rocm/nightly"
|
||||||
aws s3 cp --recursive "$INDICES_OUTPUT_DIR/" "s3://$BUCKET/rocm/nightly/"
|
|
||||||
fi
|
fi
|
||||||
|
|
||||||
# Extract version from vLLM wheel and update version-specific index
|
# Extract version from vLLM wheel and update version-specific index
|
||||||
@@ -129,8 +176,7 @@ if [ -n "$VLLM_WHEEL" ]; then
|
|||||||
echo "Pure version: $PURE_VERSION"
|
echo "Pure version: $PURE_VERSION"
|
||||||
|
|
||||||
if [[ "$VERSION" != *"dev"* ]]; then
|
if [[ "$VERSION" != *"dev"* ]]; then
|
||||||
echo "Updating rocm/$PURE_VERSION/ index..."
|
publish_indices "rocm/$PURE_VERSION"
|
||||||
aws s3 cp --recursive "$INDICES_OUTPUT_DIR/" "s3://$BUCKET/rocm/$PURE_VERSION/"
|
|
||||||
fi
|
fi
|
||||||
fi
|
fi
|
||||||
|
|
||||||
@@ -142,14 +188,14 @@ echo "ROCm Wheel Upload Complete!"
|
|||||||
echo "========================================"
|
echo "========================================"
|
||||||
echo ""
|
echo ""
|
||||||
echo "Wheels available at:"
|
echo "Wheels available at:"
|
||||||
echo " s3://$BUCKET/$ROCM_SUBPATH/"
|
echo " s3://$BUCKET/$WHEEL_SUBPATH/"
|
||||||
echo ""
|
echo ""
|
||||||
echo "Install command (by commit):"
|
echo "Install command (by commit):"
|
||||||
echo " pip install vllm --extra-index-url https://${BUCKET}.s3.amazonaws.com/$ROCM_SUBPATH/"
|
echo " pip install vllm --extra-index-url https://${BUCKET}.s3.amazonaws.com/$ROCM_SUBPATH/$ROCM_STACK_VARIANT/"
|
||||||
echo ""
|
echo ""
|
||||||
if [[ "${NIGHTLY:-0}" == "1" ]]; then
|
if [[ "${NIGHTLY:-0}" == "1" ]]; then
|
||||||
echo "Install command (nightly):"
|
echo "Install command (nightly):"
|
||||||
echo " pip install vllm --extra-index-url https://${BUCKET}.s3.amazonaws.com/rocm/nightly/"
|
echo " pip install vllm --extra-index-url https://${BUCKET}.s3.amazonaws.com/rocm/nightly/$ROCM_STACK_VARIANT/"
|
||||||
fi
|
fi
|
||||||
echo ""
|
echo ""
|
||||||
echo "Wheel count: $WHEEL_COUNT"
|
echo "Wheel count: $WHEEL_COUNT"
|
||||||
|
|||||||
+484
-415
File diff suppressed because it is too large
Load Diff
@@ -2,8 +2,9 @@ group: Attention
|
|||||||
depends_on:
|
depends_on:
|
||||||
- image-build
|
- image-build
|
||||||
steps:
|
steps:
|
||||||
- label: ":nvidia: (H100) V1 Attention Shard %N"
|
- label: ":nvidia: (H100) V1 Attention"
|
||||||
key: v1-attention-h100-mi300
|
key: v1-attention-h100-mi300
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 85
|
timeout_in_minutes: 85
|
||||||
device: h100
|
device: h100
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
@@ -12,14 +13,18 @@ steps:
|
|||||||
- vllm/v1/attention
|
- vllm/v1/attention
|
||||||
- tests/v1/attention
|
- tests/v1/attention
|
||||||
commands:
|
commands:
|
||||||
- pytest -v -s v1/attention --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
|
- pytest -v -s v1/attention
|
||||||
parallelism: 2
|
|
||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI300) V1 Attention Shard %N"
|
label: ":amd: (MI300) V1 Attention Shard %N"
|
||||||
dind: false
|
dind: false
|
||||||
device: mi300_1
|
device: mi300_1
|
||||||
timeout_in_minutes: 125
|
timeout_in_minutes: 125
|
||||||
|
# automatic_shard covers NVIDIA steps only; the mirror keeps its
|
||||||
|
# fixed pytest shards.
|
||||||
|
parallelism: 2
|
||||||
|
commands:
|
||||||
|
- pytest -v -s v1/attention --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-amd
|
- image-build-amd
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
@@ -30,9 +35,14 @@ steps:
|
|||||||
- vllm/_aiter_ops.py
|
- vllm/_aiter_ops.py
|
||||||
- vllm/envs.py
|
- vllm/envs.py
|
||||||
- vllm/platforms/rocm.py
|
- vllm/platforms/rocm.py
|
||||||
|
- vllm/models/deepseek_v32/amd/rocm.py
|
||||||
|
commands:
|
||||||
|
- pytest -v -s v1/attention --ignore=v1/attention/test_sparse_mla_backends.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
|
||||||
|
- VLLM_ROCM_USE_AITER=1 pytest -v -s v1/attention/test_sparse_mla_backends.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
|
||||||
|
|
||||||
- label: ":nvidia: (B200) V1 Attention Shard %N"
|
- label: ":nvidia: (B200) V1 Attention"
|
||||||
key: v1-attention-b200
|
key: v1-attention-b200
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 80
|
timeout_in_minutes: 80
|
||||||
device: b200-k8s
|
device: b200-k8s
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
@@ -41,14 +51,16 @@ steps:
|
|||||||
- vllm/v1/attention
|
- vllm/v1/attention
|
||||||
- tests/v1/attention
|
- tests/v1/attention
|
||||||
commands:
|
commands:
|
||||||
- pytest -v -s v1/attention --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
|
- pytest -v -s v1/attention
|
||||||
parallelism: 2
|
|
||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI355 DPX) V1 Attention Shard %N"
|
label: ":amd: (MI355 DPX) V1 Attention Shard %N"
|
||||||
dind: false
|
dind: false
|
||||||
device: mi355_dpx
|
device: mi355_dpx
|
||||||
timeout_in_minutes: 125
|
timeout_in_minutes: 125
|
||||||
|
# automatic_shard covers NVIDIA steps only; the mirror keeps its
|
||||||
|
# fixed pytest shards.
|
||||||
|
parallelism: 2
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-amd
|
- image-build-amd
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
@@ -59,6 +71,21 @@ steps:
|
|||||||
- vllm/_aiter_ops.py
|
- vllm/_aiter_ops.py
|
||||||
- vllm/envs.py
|
- vllm/envs.py
|
||||||
- vllm/platforms/rocm.py
|
- vllm/platforms/rocm.py
|
||||||
|
- vllm/models/deepseek_v32/amd/rocm.py
|
||||||
commands:
|
commands:
|
||||||
- pytest -v -s v1/attention --ignore=v1/attention/test_mla_backends.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
|
- pytest -v -s v1/attention --ignore=v1/attention/test_mla_backends.py --ignore=v1/attention/test_sparse_mla_backends.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
|
||||||
- VLLM_ROCM_USE_AITER=1 pytest -v -s v1/attention/test_mla_backends.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
|
- VLLM_ROCM_USE_AITER=1 pytest -v -s v1/attention/test_mla_backends.py v1/attention/test_sparse_mla_backends.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
|
||||||
|
|
||||||
|
- label: ":nvidia: (DGX) Spark FlashInfer NVFP4 XQA"
|
||||||
|
key: flashinfer-nvfp4-xqa-dgx-spark
|
||||||
|
timeout_in_minutes: 30
|
||||||
|
device: dgx-spark
|
||||||
|
optional: true
|
||||||
|
num_devices: 1
|
||||||
|
depends_on:
|
||||||
|
- arm64-image-build
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/v1/attention/backends/flashinfer.py
|
||||||
|
- tests/v1/attention/test_attention_backends.py
|
||||||
|
commands:
|
||||||
|
- pytest -v -s v1/attention/test_attention_backends.py -k test_flashinfer_xqa_nvfp4_decode_correctness
|
||||||
|
|||||||
@@ -4,7 +4,7 @@ depends_on:
|
|||||||
steps:
|
steps:
|
||||||
- label: ":nvidia: (H200 MIG 18GB) Benchmarks CLI"
|
- label: ":nvidia: (H200 MIG 18GB) Benchmarks CLI"
|
||||||
key: benchmarks-cli-test
|
key: benchmarks-cli-test
|
||||||
timeout_in_minutes: 45
|
timeout_in_minutes: 55
|
||||||
device: h200_18gb
|
device: h200_18gb
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- vllm/
|
- vllm/
|
||||||
|
|||||||
@@ -2,84 +2,6 @@ group: Compile
|
|||||||
depends_on:
|
depends_on:
|
||||||
- image-build
|
- image-build
|
||||||
steps:
|
steps:
|
||||||
- label: ":nvidia: (B200) Sequence Parallel Correctness"
|
|
||||||
key: sequence-parallel-correctness-tests-2xb200
|
|
||||||
timeout_in_minutes: 45
|
|
||||||
working_dir: "/vllm-workspace/"
|
|
||||||
device: b200-k8s
|
|
||||||
optional: true
|
|
||||||
num_devices: 2
|
|
||||||
commands:
|
|
||||||
- export VLLM_TEST_CLEAN_GPU_MEMORY=1
|
|
||||||
- pytest -v -s tests/compile/correctness_e2e/test_sequence_parallel.py
|
|
||||||
mirror:
|
|
||||||
amd:
|
|
||||||
label: ":amd: (MI355) Sequence Parallel Correctness"
|
|
||||||
dind: false
|
|
||||||
device: mi355_2
|
|
||||||
num_devices: 2
|
|
||||||
timeout_in_minutes: 180
|
|
||||||
depends_on:
|
|
||||||
- image-build-amd
|
|
||||||
source_file_dependencies:
|
|
||||||
- .buildkite/test_areas/compile.yaml
|
|
||||||
- vllm/compilation/
|
|
||||||
- vllm/config/
|
|
||||||
- vllm/distributed/
|
|
||||||
- vllm/model_executor/kernels/linear/
|
|
||||||
- vllm/model_executor/layers/
|
|
||||||
- vllm/model_executor/models/llama.py
|
|
||||||
- vllm/v1/attention/
|
|
||||||
- vllm/v1/worker/
|
|
||||||
- vllm/v1/cudagraph_dispatcher.py
|
|
||||||
- vllm/platforms/rocm.py
|
|
||||||
- tests/compile/correctness_e2e/test_sequence_parallel.py
|
|
||||||
- tests/models/registry.py
|
|
||||||
- tests/utils.py
|
|
||||||
|
|
||||||
- label: ":nvidia: (B200) AsyncTP Correctness"
|
|
||||||
key: asynctp-correctness-tests-b200
|
|
||||||
timeout_in_minutes: 30
|
|
||||||
working_dir: "/vllm-workspace/"
|
|
||||||
device: b200-k8s
|
|
||||||
optional: true
|
|
||||||
num_devices: 2
|
|
||||||
commands:
|
|
||||||
- export VLLM_TEST_CLEAN_GPU_MEMORY=1
|
|
||||||
- pytest -v -s tests/compile/correctness_e2e/test_async_tp.py
|
|
||||||
mirror:
|
|
||||||
amd:
|
|
||||||
label: ":amd: (MI355) AsyncTP Correctness"
|
|
||||||
dind: false
|
|
||||||
device: mi355_2
|
|
||||||
num_devices: 2
|
|
||||||
timeout_in_minutes: 60
|
|
||||||
working_dir: "/vllm-workspace/"
|
|
||||||
depends_on:
|
|
||||||
- image-build-amd
|
|
||||||
source_file_dependencies:
|
|
||||||
- .buildkite/test_areas/compile.yaml
|
|
||||||
- vllm/compilation/
|
|
||||||
- vllm/config/
|
|
||||||
- vllm/distributed/
|
|
||||||
- vllm/model_executor/layers/
|
|
||||||
- vllm/model_executor/kernels/linear/
|
|
||||||
- vllm/model_executor/models/llama.py
|
|
||||||
- vllm/model_executor/models/qwen3.py
|
|
||||||
- vllm/v1/attention/
|
|
||||||
- vllm/_aiter_ops.py
|
|
||||||
- vllm/platforms/rocm.py
|
|
||||||
- vllm/transformers_utils/repo_utils.py
|
|
||||||
- tests/compile/correctness_e2e/test_async_tp.py
|
|
||||||
- tests/compile/fusions_e2e/common.py
|
|
||||||
- tests/models/registry.py
|
|
||||||
- tests/utils.py
|
|
||||||
commands:
|
|
||||||
- export VLLM_TEST_CLEAN_GPU_MEMORY=1
|
|
||||||
- pytest -v -s tests/compile/correctness_e2e/test_async_tp.py::test_rocm_async_tp_bf16_output_correctness
|
|
||||||
- pytest -v -s tests/compile/correctness_e2e/test_async_tp.py::test_async_tp_pass_correctness -k RedHatAI
|
|
||||||
- pytest -v -s tests/compile/correctness_e2e/test_async_tp.py::test_async_tp_pass_nvfp4_correctness
|
|
||||||
|
|
||||||
- label: ":nvidia: (H100) Distributed Compile"
|
- label: ":nvidia: (H100) Distributed Compile"
|
||||||
key: distributed-compile-unit-tests-2xh100
|
key: distributed-compile-unit-tests-2xh100
|
||||||
timeout_in_minutes: 45
|
timeout_in_minutes: 45
|
||||||
@@ -300,7 +222,6 @@ steps:
|
|||||||
- nvidia-smi
|
- nvidia-smi
|
||||||
# Run all models and attn backends but only Inductor partition and native custom ops
|
# Run all models and attn backends but only Inductor partition and native custom ops
|
||||||
- pytest -v -s tests/compile/fusions_e2e/test_tp2_ar_rms.py -k "inductor_partition and not +rms_norm and (not +quant_fp8 or +quant_fp8 and (qwen3 or deepseek))"
|
- pytest -v -s tests/compile/fusions_e2e/test_tp2_ar_rms.py -k "inductor_partition and not +rms_norm and (not +quant_fp8 or +quant_fp8 and (qwen3 or deepseek))"
|
||||||
- pytest -v -s tests/compile/fusions_e2e/test_tp2_async_tp.py -k "inductor_partition and not +rms_norm and (not +quant_fp8 or +quant_fp8 and (qwen3 or deepseek))"
|
|
||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI355) Fusion E2E TP2 Quick"
|
label: ":amd: (MI355) Fusion E2E TP2 Quick"
|
||||||
@@ -388,53 +309,6 @@ steps:
|
|||||||
- amd-smi
|
- amd-smi
|
||||||
- VLLM_ROCM_USE_AITER=1 VLLM_ROCM_USE_AITER_CUSTOM_AR=1 pytest -v -s tests/compile/fusions_e2e/test_tp2_ar_rms.py -k 'test_tp2_ar_rms_fp8_fusions and Llama-3 and ROCM_AITER_UNIFIED_ATTN and (dynamo_partition or +quant_fp8 or +rms_norm)'
|
- VLLM_ROCM_USE_AITER=1 VLLM_ROCM_USE_AITER_CUSTOM_AR=1 pytest -v -s tests/compile/fusions_e2e/test_tp2_ar_rms.py -k 'test_tp2_ar_rms_fp8_fusions and Llama-3 and ROCM_AITER_UNIFIED_ATTN and (dynamo_partition or +quant_fp8 or +rms_norm)'
|
||||||
|
|
||||||
- label: ":nvidia: (H100) Fusion E2E TP2 AsyncTP Config Sweep"
|
|
||||||
key: fusion-e2e-tp2-asynctp-config-sweep-h100
|
|
||||||
timeout_in_minutes: 40
|
|
||||||
working_dir: "/vllm-workspace/"
|
|
||||||
device: h100
|
|
||||||
num_devices: 2
|
|
||||||
source_file_dependencies:
|
|
||||||
- csrc/quantization/
|
|
||||||
- vllm/compilation/
|
|
||||||
# can affect pattern matching
|
|
||||||
- vllm/model_executor/layers/layernorm.py
|
|
||||||
- vllm/model_executor/layers/activation.py
|
|
||||||
- vllm/model_executor/layers/attention/attention.py
|
|
||||||
- vllm/model_executor/layers/quantization/input_quant_fp8.py
|
|
||||||
- tests/compile/fusions_e2e/
|
|
||||||
commands:
|
|
||||||
- nvidia-smi
|
|
||||||
# Run just llama3 (fp8 & bf16) for all config combinations
|
|
||||||
- pytest -v -s tests/compile/fusions_e2e/test_tp2_async_tp.py -k "llama-3"
|
|
||||||
mirror:
|
|
||||||
amd:
|
|
||||||
label: ':amd: (MI355) Fusion E2E TP2 AsyncTP BF16 Config Sweep'
|
|
||||||
dind: false
|
|
||||||
device: mi355_2
|
|
||||||
num_devices: 2
|
|
||||||
working_dir: /vllm-workspace/
|
|
||||||
timeout_in_minutes: 30
|
|
||||||
depends_on:
|
|
||||||
- image-build-amd
|
|
||||||
source_file_dependencies:
|
|
||||||
- vllm/compilation/
|
|
||||||
- vllm/model_executor/layers/linear.py
|
|
||||||
- vllm/model_executor/layers/utils.py
|
|
||||||
- vllm/distributed/
|
|
||||||
- vllm/v1/attention/backends/triton_attn.py
|
|
||||||
- tests/compile/fusions_e2e/
|
|
||||||
- tests/compile/passes/distributed/test_async_tp.py
|
|
||||||
- tests/compile/rocm/test_async_tp.py
|
|
||||||
- tests/compile/correctness_e2e/test_async_tp.py
|
|
||||||
- vllm/model_executor/kernels/linear/
|
|
||||||
- vllm/model_executor/models/qwen3.py
|
|
||||||
commands:
|
|
||||||
- rocm-smi
|
|
||||||
- pytest -v -s tests/compile/rocm/test_async_tp.py
|
|
||||||
- pytest -v -s tests/compile/fusions_e2e/test_tp2_rocm_async_tp.py
|
|
||||||
- pytest -v -s tests/compile/correctness_e2e/test_async_tp.py::test_rocm_async_tp_bf16_output_correctness
|
|
||||||
|
|
||||||
- label: ":nvidia: (B200) Fusion E2E TP2"
|
- label: ":nvidia: (B200) Fusion E2E TP2"
|
||||||
key: fusion-e2e-tp2-b200
|
key: fusion-e2e-tp2-b200
|
||||||
timeout_in_minutes: 45
|
timeout_in_minutes: 45
|
||||||
@@ -453,7 +327,6 @@ steps:
|
|||||||
# include qwen/deepseek with +quant_fp8 as -quant_fp8 rms+quant fusion is not supported
|
# include qwen/deepseek with +quant_fp8 as -quant_fp8 rms+quant fusion is not supported
|
||||||
# for ar-rms-quant-fp4, also sweep llama3
|
# for ar-rms-quant-fp4, also sweep llama3
|
||||||
- pytest -v -s tests/compile/fusions_e2e/test_tp2_ar_rms.py -k "(FLASHINFER and inductor_partition and not +rms_norm and (not +quant_fp8 or +quant_fp8 and (qwen3 or deepseek))) or Llama-3.1-8B-Instruct-FP4"
|
- pytest -v -s tests/compile/fusions_e2e/test_tp2_ar_rms.py -k "(FLASHINFER and inductor_partition and not +rms_norm and (not +quant_fp8 or +quant_fp8 and (qwen3 or deepseek))) or Llama-3.1-8B-Instruct-FP4"
|
||||||
- pytest -v -s tests/compile/fusions_e2e/test_tp2_async_tp.py -k "FLASHINFER and inductor_partition and not +rms_norm and (not +quant_fp8 or +quant_fp8 and (qwen3 or deepseek))"
|
|
||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI355) Fusion E2E TP2 FP8 BF16 rewrites"
|
label: ":amd: (MI355) Fusion E2E TP2 FP8 BF16 rewrites"
|
||||||
@@ -480,7 +353,6 @@ steps:
|
|||||||
# TODO: FP4 output-quant and trained MXFP4 AR/RMS fusion remain unsupported.
|
# TODO: FP4 output-quant and trained MXFP4 AR/RMS fusion remain unsupported.
|
||||||
- amd-smi
|
- amd-smi
|
||||||
- VLLM_ROCM_USE_AITER=1 VLLM_ROCM_USE_AITER_CUSTOM_AR=1 pytest -v -s tests/compile/fusions_e2e/test_tp2_ar_rms.py -k 'test_tp2_ar_rms_fp8_fusions and qwen3 and ROCM_AITER_UNIFIED_ATTN and +quant_fp8 and (dynamo_partition or not +rms_norm)'
|
- VLLM_ROCM_USE_AITER=1 VLLM_ROCM_USE_AITER_CUSTOM_AR=1 pytest -v -s tests/compile/fusions_e2e/test_tp2_ar_rms.py -k 'test_tp2_ar_rms_fp8_fusions and qwen3 and ROCM_AITER_UNIFIED_ATTN and +quant_fp8 and (dynamo_partition or not +rms_norm)'
|
||||||
- pytest -v -s tests/compile/fusions_e2e/test_tp2_rocm_moe.py
|
|
||||||
|
|
||||||
- label: ':amd: (MI355) Fusion E2E TP2 AR-RMS (Inductor Partition)'
|
- label: ':amd: (MI355) Fusion E2E TP2 AR-RMS (Inductor Partition)'
|
||||||
key: fusion-e2e-tp2-ar-rms-inductor-partition-amd
|
key: fusion-e2e-tp2-ar-rms-inductor-partition-amd
|
||||||
|
|||||||
@@ -33,14 +33,20 @@ steps:
|
|||||||
- label: ":nvidia: (H200 MIG 18GB) CUDAGraph"
|
- label: ":nvidia: (H200 MIG 18GB) CUDAGraph"
|
||||||
device: h200_18gb
|
device: h200_18gb
|
||||||
key: cudagraph
|
key: cudagraph
|
||||||
timeout_in_minutes: 30
|
automatic_shard: true
|
||||||
|
timeout_in_minutes: 45
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- tests/v1/cudagraph
|
- tests/v1/cudagraph
|
||||||
- vllm/v1/cudagraph_dispatcher.py
|
- vllm/v1/cudagraph_dispatcher.py
|
||||||
- vllm/config/compilation.py
|
- vllm/config/compilation.py
|
||||||
|
- vllm/config/vllm.py
|
||||||
- vllm/compilation
|
- vllm/compilation
|
||||||
|
- vllm/v1/worker/gpu/cudagraph_utils.py
|
||||||
|
- vllm/v1/worker/gpu/dp_utils.py
|
||||||
- vllm/v1/worker/encoder_cudagraph.py
|
- vllm/v1/worker/encoder_cudagraph.py
|
||||||
- vllm/v1/worker/encoder_cudagraph_defs.py
|
- vllm/v1/worker/encoder_cudagraph_defs.py
|
||||||
|
- vllm/v1/worker/gpu/model_runner.py
|
||||||
|
- vllm/v1/worker/gpu/ubatch_utils.py
|
||||||
commands:
|
commands:
|
||||||
- pytest -v -s v1/cudagraph/test_cudagraph_dispatch.py
|
- pytest -v -s v1/cudagraph/test_cudagraph_dispatch.py
|
||||||
- pytest -v -s v1/cudagraph/test_cudagraph_mode.py
|
- pytest -v -s v1/cudagraph/test_cudagraph_mode.py
|
||||||
|
|||||||
@@ -426,7 +426,7 @@ steps:
|
|||||||
# Keep TP=2 prefill and TP=1 decode above both hybrid page-size minima.
|
# Keep TP=2 prefill and TP=1 decode above both hybrid page-size minima.
|
||||||
PREFILL_BLOCK_SIZE: "2048"
|
PREFILL_BLOCK_SIZE: "2048"
|
||||||
DECODE_BLOCK_SIZE: "2048"
|
DECODE_BLOCK_SIZE: "2048"
|
||||||
VLLM_SERVE_EXTRA_ARGS: "--trust-remote-code,--mamba-cache-mode align,--max-model-len 32768"
|
VLLM_SERVE_EXTRA_ARGS: "--trust-remote-code,--max-model-len 32768"
|
||||||
commands:
|
commands:
|
||||||
- bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh
|
- bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh
|
||||||
- bash v1/kv_connector/nixl_integration/run_accuracy_test.sh
|
- bash v1/kv_connector/nixl_integration/run_accuracy_test.sh
|
||||||
|
|||||||
@@ -4,6 +4,8 @@ depends_on:
|
|||||||
steps:
|
steps:
|
||||||
- label: ":nvidia: (B200) Distributed MooncakeConnector PD accuracy"
|
- label: ":nvidia: (B200) Distributed MooncakeConnector PD accuracy"
|
||||||
key: distributed-mooncakeconnector-pd-accuracy-4-gpus
|
key: distributed-mooncakeconnector-pd-accuracy-4-gpus
|
||||||
|
# Nightly only: 4-GPU B200 pods wait hours behind smaller jobs on per-PR runs.
|
||||||
|
optional: true
|
||||||
timeout_in_minutes: 10
|
timeout_in_minutes: 10
|
||||||
working_dir: "/vllm-workspace/tests"
|
working_dir: "/vllm-workspace/tests"
|
||||||
# Runs on b200-k8s because it is the only NVIDIA pool that can carry mooncake
|
# Runs on b200-k8s because it is the only NVIDIA pool that can carry mooncake
|
||||||
@@ -22,6 +24,7 @@ steps:
|
|||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI355) Distributed MooncakeConnector HIP PD accuracy"
|
label: ":amd: (MI355) Distributed MooncakeConnector HIP PD accuracy"
|
||||||
|
optional: true
|
||||||
dind: false
|
dind: false
|
||||||
device: mi355_4
|
device: mi355_4
|
||||||
num_devices: 4
|
num_devices: 4
|
||||||
|
|||||||
@@ -14,6 +14,7 @@ steps:
|
|||||||
- tests/distributed
|
- tests/distributed
|
||||||
commands:
|
commands:
|
||||||
- pytest -v -s distributed/test_comm_ops.py
|
- pytest -v -s distributed/test_comm_ops.py
|
||||||
|
- pytest -v -s distributed/test_cpu_all_reduce.py
|
||||||
- pytest -v -s distributed/test_shm_broadcast.py
|
- pytest -v -s distributed/test_shm_broadcast.py
|
||||||
- pytest -v -s distributed/test_shm_buffer.py
|
- pytest -v -s distributed/test_shm_buffer.py
|
||||||
- pytest -v -s distributed/test_shm_storage.py
|
- pytest -v -s distributed/test_shm_storage.py
|
||||||
@@ -77,6 +78,7 @@ steps:
|
|||||||
|
|
||||||
- label: ":nvidia: (L4) Distributed DP Basic"
|
- label: ":nvidia: (L4) Distributed DP Basic"
|
||||||
key: distributed-dp-tests-2-gpus
|
key: distributed-dp-tests-2-gpus
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 45
|
timeout_in_minutes: 45
|
||||||
working_dir: "/vllm-workspace/tests"
|
working_dir: "/vllm-workspace/tests"
|
||||||
device: l4
|
device: l4
|
||||||
@@ -108,6 +110,7 @@ steps:
|
|||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI355) Distributed DP Basic"
|
label: ":amd: (MI355) Distributed DP Basic"
|
||||||
dind: false
|
dind: false
|
||||||
|
automatic_shard: true
|
||||||
device: mi355_2
|
device: mi355_2
|
||||||
timeout_in_minutes: 45
|
timeout_in_minutes: 45
|
||||||
depends_on:
|
depends_on:
|
||||||
@@ -300,6 +303,7 @@ steps:
|
|||||||
|
|
||||||
- label: ":nvidia: (L4) Distributed DP Extended"
|
- label: ":nvidia: (L4) Distributed DP Extended"
|
||||||
key: distributed-dp-tests-4-gpus
|
key: distributed-dp-tests-4-gpus
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 45
|
timeout_in_minutes: 45
|
||||||
working_dir: "/vllm-workspace/tests"
|
working_dir: "/vllm-workspace/tests"
|
||||||
device: l4
|
device: l4
|
||||||
@@ -329,6 +333,7 @@ steps:
|
|||||||
amd:
|
amd:
|
||||||
label: ':amd: (MI355) Distributed DP Extended'
|
label: ':amd: (MI355) Distributed DP Extended'
|
||||||
dind: false
|
dind: false
|
||||||
|
automatic_shard: true
|
||||||
device: mi355_4
|
device: mi355_4
|
||||||
timeout_in_minutes: 60
|
timeout_in_minutes: 60
|
||||||
working_dir: /vllm-workspace/tests
|
working_dir: /vllm-workspace/tests
|
||||||
@@ -397,6 +402,7 @@ steps:
|
|||||||
- label: ":nvidia: (H100) Distributed DP + EP"
|
- label: ":nvidia: (H100) Distributed DP + EP"
|
||||||
key: distributed-tests-8xh100
|
key: distributed-tests-8xh100
|
||||||
timeout_in_minutes: 20
|
timeout_in_minutes: 20
|
||||||
|
optional: true
|
||||||
device: h100
|
device: h100
|
||||||
num_devices: 8
|
num_devices: 8
|
||||||
working_dir: "/vllm-workspace/tests"
|
working_dir: "/vllm-workspace/tests"
|
||||||
@@ -419,6 +425,7 @@ steps:
|
|||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI355) Distributed DP + EP"
|
label: ":amd: (MI355) Distributed DP + EP"
|
||||||
dind: false
|
dind: false
|
||||||
|
optional: false
|
||||||
device: mi355_8
|
device: mi355_8
|
||||||
timeout_in_minutes: 50
|
timeout_in_minutes: 50
|
||||||
depends_on:
|
depends_on:
|
||||||
@@ -506,9 +513,7 @@ steps:
|
|||||||
- examples/features/data_parallel/data_parallel_offline.py
|
- examples/features/data_parallel/data_parallel_offline.py
|
||||||
- vllm/_aiter_ops.py
|
- vllm/_aiter_ops.py
|
||||||
- vllm/platforms/rocm.py
|
- vllm/platforms/rocm.py
|
||||||
- csrc/custom_quickreduce.cu
|
- csrc/rocm/quickreduce/
|
||||||
- csrc/ops.h
|
|
||||||
- csrc/torch_bindings.cpp
|
|
||||||
- vllm/model_executor/layers/
|
- vllm/model_executor/layers/
|
||||||
- vllm/entrypoints/llm.py
|
- vllm/entrypoints/llm.py
|
||||||
- vllm/config/parallel.py
|
- vllm/config/parallel.py
|
||||||
@@ -520,13 +525,17 @@ steps:
|
|||||||
- tests/distributed/test_rocm_aiter_custom_ar.py
|
- tests/distributed/test_rocm_aiter_custom_ar.py
|
||||||
- tests/distributed/test_rocm_quick_reduce.py
|
- tests/distributed/test_rocm_quick_reduce.py
|
||||||
- tests/distributed/test_quick_all_reduce.py
|
- tests/distributed/test_quick_all_reduce.py
|
||||||
|
- tests/distributed/test_aiter_rms_fallback.py
|
||||||
- tests/v1/e2e/general/test_rocm_aiter_custom_ar.py
|
- tests/v1/e2e/general/test_rocm_aiter_custom_ar.py
|
||||||
- tests/utils.py
|
- tests/utils.py
|
||||||
- examples/rl/rlhf_async_new_apis.py
|
- examples/rl/rlhf_async_new_apis.py
|
||||||
- tests/distributed/test_weight_transfer.py
|
- tests/distributed/test_weight_transfer.py
|
||||||
- tests/distributed/test_packed_tensor.py
|
- tests/distributed/test_packed_tensor.py
|
||||||
|
- tests/v1/attention/test_rocm_mla_dcp_context.py
|
||||||
|
- vllm/v1/attention/ops/rocm_aiter_mla_prefill.py
|
||||||
commands:
|
commands:
|
||||||
- pytest -v -s tests/distributed/test_context_parallel.py
|
- pytest -v -s tests/distributed/test_context_parallel.py
|
||||||
|
- pytest -v -s tests/v1/attention/test_rocm_mla_dcp_context.py
|
||||||
- VLLM_ALLOW_INSECURE_SERIALIZATION=1 python3 examples/rl/rlhf_async_new_apis.py
|
- VLLM_ALLOW_INSECURE_SERIALIZATION=1 python3 examples/rl/rlhf_async_new_apis.py
|
||||||
- VLLM_LOGGING_LEVEL=DEBUG python3 examples/features/data_parallel/data_parallel_offline.py --model=Qwen/Qwen1.5-MoE-A2.7B -tp=1 -dp=2 --max-model-len=2048 --all2all-backend=deepep_high_throughput
|
- VLLM_LOGGING_LEVEL=DEBUG python3 examples/features/data_parallel/data_parallel_offline.py --model=Qwen/Qwen1.5-MoE-A2.7B -tp=1 -dp=2 --max-model-len=2048 --all2all-backend=deepep_high_throughput
|
||||||
- VLLM_LOGGING_LEVEL=DEBUG python3 examples/features/data_parallel/data_parallel_offline.py --model=Qwen/Qwen1.5-MoE-A2.7B -tp=1 -dp=2 --max-model-len=2048 --all2all-backend=allgather_reducescatter --disable-nccl-for-dp-synchronization
|
- VLLM_LOGGING_LEVEL=DEBUG python3 examples/features/data_parallel/data_parallel_offline.py --model=Qwen/Qwen1.5-MoE-A2.7B -tp=1 -dp=2 --max-model-len=2048 --all2all-backend=allgather_reducescatter --disable-nccl-for-dp-synchronization
|
||||||
@@ -537,6 +546,7 @@ steps:
|
|||||||
- pytest -v -s tests/v1/e2e/general/test_rocm_aiter_custom_ar.py
|
- pytest -v -s tests/v1/e2e/general/test_rocm_aiter_custom_ar.py
|
||||||
- pytest -v -s tests/distributed/test_rocm_quick_reduce.py
|
- pytest -v -s tests/distributed/test_rocm_quick_reduce.py
|
||||||
- pytest -v -s tests/distributed/test_quick_all_reduce.py
|
- pytest -v -s tests/distributed/test_quick_all_reduce.py
|
||||||
|
- pytest -v -s tests/distributed/test_aiter_rms_fallback.py
|
||||||
|
|
||||||
- label: ":nvidia: (B200) Distributed"
|
- label: ":nvidia: (B200) Distributed"
|
||||||
key: distributed-tests-2xb200
|
key: distributed-tests-2xb200
|
||||||
@@ -630,10 +640,11 @@ steps:
|
|||||||
- tests/distributed/
|
- tests/distributed/
|
||||||
- examples/features/data_parallel/data_parallel_offline.py
|
- examples/features/data_parallel/data_parallel_offline.py
|
||||||
commands:
|
commands:
|
||||||
- ./.buildkite/scripts/run-multi-node-test.sh /vllm-workspace/tests 2 2 $IMAGE_TAG "VLLM_TEST_SAME_HOST=0 torchrun --nnodes 2 --nproc-per-node=2 --rdzv_backend=c10d --rdzv_endpoint=192.168.10.10 distributed/test_same_node.py | grep 'Same node test passed' && NUM_NODES=2 torchrun --nnodes 2 --nproc-per-node=2 --rdzv_backend=c10d --rdzv_endpoint=192.168.10.10 distributed/test_node_count.py | grep 'Node count test passed' && python3 ../examples/features/data_parallel/data_parallel_offline.py -dp=2 -tp=1 --dp-num-nodes=2 --dp-node-rank=0 --dp-master-addr=192.168.10.10 --dp-master-port=12345 --enforce-eager --trust-remote-code && VLLM_MULTI_NODE=1 pytest -v -s distributed/test_multi_node_assignment.py && VLLM_MULTI_NODE=1 pytest -v -s distributed/test_pipeline_parallel.py" "VLLM_TEST_SAME_HOST=0 torchrun --nnodes 2 --nproc-per-node=2 --rdzv_backend=c10d --rdzv_endpoint=192.168.10.10 distributed/test_same_node.py | grep 'Same node test passed' && NUM_NODES=2 torchrun --nnodes 2 --nproc-per-node=2 --rdzv_backend=c10d --rdzv_endpoint=192.168.10.10 distributed/test_node_count.py | grep 'Node count test passed' && python3 ../examples/features/data_parallel/data_parallel_offline.py -dp=2 -tp=1 --dp-num-nodes=2 --dp-node-rank=1 --dp-master-addr=192.168.10.10 --dp-master-port=12345 --enforce-eager --trust-remote-code"
|
- ./.buildkite/scripts/run-multi-node-test.sh /vllm-workspace/tests 2 2 $IMAGE_TAG "VLLM_TEST_SAME_HOST=0 torchrun --nnodes 2 --nproc-per-node=2 --rdzv_backend=c10d --rdzv_endpoint=192.168.10.10 distributed/test_same_node.py | grep 'Same node test passed' && NUM_NODES=2 torchrun --nnodes 2 --nproc-per-node=2 --rdzv_backend=c10d --rdzv_endpoint=192.168.10.10 distributed/test_node_count.py | grep 'Node count test passed' && python3 ../examples/features/data_parallel/data_parallel_offline.py -dp=2 -tp=1 --dp-num-nodes=2 --dp-node-rank=0 --dp-master-addr=192.168.10.10 --dp-master-port=12345 --enforce-eager --trust-remote-code && VLLM_MULTI_NODE=1 pytest -v -s distributed/test_pipeline_parallel.py" "VLLM_TEST_SAME_HOST=0 torchrun --nnodes 2 --nproc-per-node=2 --rdzv_backend=c10d --rdzv_endpoint=192.168.10.10 distributed/test_same_node.py | grep 'Same node test passed' && NUM_NODES=2 torchrun --nnodes 2 --nproc-per-node=2 --rdzv_backend=c10d --rdzv_endpoint=192.168.10.10 distributed/test_node_count.py | grep 'Node count test passed' && python3 ../examples/features/data_parallel/data_parallel_offline.py -dp=2 -tp=1 --dp-num-nodes=2 --dp-node-rank=1 --dp-master-addr=192.168.10.10 --dp-master-port=12345 --enforce-eager --trust-remote-code"
|
||||||
|
|
||||||
- label: ":nvidia: (L4) Pipeline + Context Parallelism"
|
- label: ":nvidia: (L4) Pipeline + Context Parallelism"
|
||||||
key: pipeline-context-parallelism-4-gpus
|
key: pipeline-context-parallelism-4-gpus
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 55
|
timeout_in_minutes: 55
|
||||||
working_dir: "/vllm-workspace/tests"
|
working_dir: "/vllm-workspace/tests"
|
||||||
device: l4
|
device: l4
|
||||||
@@ -675,6 +686,7 @@ steps:
|
|||||||
|
|
||||||
- label: ":nvidia: (L4) RayExecutorV2"
|
- label: ":nvidia: (L4) RayExecutorV2"
|
||||||
key: rayexecutorv2-4-gpus
|
key: rayexecutorv2-4-gpus
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 45
|
timeout_in_minutes: 45
|
||||||
working_dir: "/vllm-workspace/tests"
|
working_dir: "/vllm-workspace/tests"
|
||||||
device: l4
|
device: l4
|
||||||
@@ -688,7 +700,6 @@ steps:
|
|||||||
- tests/distributed/test_pipeline_parallel.py
|
- tests/distributed/test_pipeline_parallel.py
|
||||||
- tests/basic_correctness/models/test_basic_correctness.py
|
- tests/basic_correctness/models/test_basic_correctness.py
|
||||||
commands:
|
commands:
|
||||||
- export VLLM_USE_RAY_V2_EXECUTOR_BACKEND=1
|
|
||||||
- export NCCL_CUMEM_HOST_ENABLE=0
|
- export NCCL_CUMEM_HOST_ENABLE=0
|
||||||
- pytest -v -s distributed/test_ray_v2_executor.py
|
- pytest -v -s distributed/test_ray_v2_executor.py
|
||||||
- pytest -v -s distributed/test_ray_v2_executor_e2e.py
|
- pytest -v -s distributed/test_ray_v2_executor_e2e.py
|
||||||
@@ -698,6 +709,7 @@ steps:
|
|||||||
amd:
|
amd:
|
||||||
label: ':amd: (MI355) RayExecutorV2'
|
label: ':amd: (MI355) RayExecutorV2'
|
||||||
dind: false
|
dind: false
|
||||||
|
automatic_shard: true
|
||||||
device: mi355_4
|
device: mi355_4
|
||||||
timeout_in_minutes: 75
|
timeout_in_minutes: 75
|
||||||
working_dir: /vllm-workspace/tests
|
working_dir: /vllm-workspace/tests
|
||||||
@@ -713,7 +725,6 @@ steps:
|
|||||||
- tests/basic_correctness/models/test_basic_correctness.py
|
- tests/basic_correctness/models/test_basic_correctness.py
|
||||||
- vllm/platforms/rocm.py
|
- vllm/platforms/rocm.py
|
||||||
commands:
|
commands:
|
||||||
- export VLLM_USE_RAY_V2_EXECUTOR_BACKEND=1
|
|
||||||
- pytest -v -s distributed/test_ray_v2_executor.py
|
- pytest -v -s distributed/test_ray_v2_executor.py
|
||||||
- pytest -v -s distributed/test_ray_v2_executor_e2e.py
|
- pytest -v -s distributed/test_ray_v2_executor_e2e.py
|
||||||
- pytest -v -s distributed/test_pipeline_parallel.py -k "ray"
|
- pytest -v -s distributed/test_pipeline_parallel.py -k "ray"
|
||||||
|
|||||||
@@ -38,6 +38,7 @@ steps:
|
|||||||
|
|
||||||
- label: ":nvidia: (L4) V1 Engine"
|
- label: ":nvidia: (L4) V1 Engine"
|
||||||
key: engine-1-gpu
|
key: engine-1-gpu
|
||||||
|
automatic_shard: true
|
||||||
device: l4
|
device: l4
|
||||||
num_devices: 1
|
num_devices: 1
|
||||||
timeout_in_minutes: 45
|
timeout_in_minutes: 45
|
||||||
@@ -108,6 +109,7 @@ steps:
|
|||||||
- label: ":nvidia: (H200 MIG 18GB) E2E Core"
|
- label: ":nvidia: (H200 MIG 18GB) E2E Core"
|
||||||
device: h200_18gb
|
device: h200_18gb
|
||||||
key: e2e-core-1-gpu
|
key: e2e-core-1-gpu
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 65
|
timeout_in_minutes: 65
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- vllm/v1/
|
- vllm/v1/
|
||||||
@@ -139,7 +141,7 @@ steps:
|
|||||||
- tests/v1/e2e/general/
|
- tests/v1/e2e/general/
|
||||||
commands:
|
commands:
|
||||||
- pytest -v -s v1/e2e/general/test_kv_sharing_fast_prefill.py
|
- pytest -v -s v1/e2e/general/test_kv_sharing_fast_prefill.py
|
||||||
- pytest -v -s v1/e2e/general/test_mamba_prefix_cache.py::test_mamba_prefix_cache_mrv2 v1/e2e/general/test_mamba_prefix_cache.py::test_mamba_prefix_cache_mrv2_async
|
- pytest -v -s v1/e2e/general/test_mamba_prefix_cache.py::test_mamba_prefix_cache_mrv2 v1/e2e/general/test_mamba_prefix_cache.py::test_mamba_prefix_cache_mrv2_async v1/e2e/general/test_mamba_prefix_cache.py::test_mamba_prefix_cache_mrv2_async_flashinfer
|
||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI355 DPX) E2E Core Large Memory"
|
label: ":amd: (MI355 DPX) E2E Core Large Memory"
|
||||||
@@ -162,6 +164,7 @@ steps:
|
|||||||
device: h100
|
device: h100
|
||||||
num_devices: 2
|
num_devices: 2
|
||||||
key: replayssm-e2e
|
key: replayssm-e2e
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 90
|
timeout_in_minutes: 90
|
||||||
working_dir: "/vllm-workspace/tests"
|
working_dir: "/vllm-workspace/tests"
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
@@ -235,9 +238,9 @@ steps:
|
|||||||
- pytest -v -s v1/e2e/test_hybrid_chunked_prefill.py
|
- pytest -v -s v1/e2e/test_hybrid_chunked_prefill.py
|
||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI300) V1 E2E Hybrid Chunked Prefill"
|
label: ":amd: (MI355 DPX) V1 E2E Hybrid Chunked Prefill"
|
||||||
dind: false
|
dind: false
|
||||||
device: mi300_1
|
device: mi355_dpx
|
||||||
timeout_in_minutes: 35
|
timeout_in_minutes: 35
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-amd
|
- image-build-amd
|
||||||
|
|||||||
@@ -26,21 +26,22 @@ steps:
|
|||||||
- label: ":nvidia: (H200 MIG 35GB) Entrypoints Unit"
|
- label: ":nvidia: (H200 MIG 35GB) Entrypoints Unit"
|
||||||
device: h200_35gb
|
device: h200_35gb
|
||||||
key: entrypoints-unit-tests
|
key: entrypoints-unit-tests
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 40
|
timeout_in_minutes: 40
|
||||||
working_dir: "/vllm-workspace/tests"
|
working_dir: "/vllm-workspace/tests"
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- vllm/entrypoints
|
- vllm/entrypoints
|
||||||
|
- vllm/utils/flashinfer.py
|
||||||
- tests/entrypoints/unit_tests
|
- tests/entrypoints/unit_tests
|
||||||
- tests/entrypoints/weight_transfer
|
|
||||||
- tests/entrypoints/launchers
|
- tests/entrypoints/launchers
|
||||||
commands:
|
commands:
|
||||||
- pytest -v -s entrypoints/unit_tests
|
- pytest -v -s entrypoints/unit_tests
|
||||||
- pytest -v -s entrypoints/weight_transfer
|
|
||||||
- pytest -v -s entrypoints/launchers
|
- pytest -v -s entrypoints/launchers
|
||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI355 DPX) Entrypoints Unit"
|
label: ":amd: (MI355 DPX) Entrypoints Unit"
|
||||||
dind: false
|
dind: false
|
||||||
|
automatic_shard: true
|
||||||
device: mi355_dpx
|
device: mi355_dpx
|
||||||
timeout_in_minutes: 50
|
timeout_in_minutes: 50
|
||||||
depends_on:
|
depends_on:
|
||||||
@@ -121,6 +122,7 @@ steps:
|
|||||||
- label: ":nvidia: (H200 MIG 35GB) Entrypoints Integration (OpenAI API chat_completion)"
|
- label: ":nvidia: (H200 MIG 35GB) Entrypoints Integration (OpenAI API chat_completion)"
|
||||||
device: h200_35gb
|
device: h200_35gb
|
||||||
key: entrypoints-integration-api-server-openai-chat_completion
|
key: entrypoints-integration-api-server-openai-chat_completion
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 83
|
timeout_in_minutes: 83
|
||||||
working_dir: "/vllm-workspace/tests"
|
working_dir: "/vllm-workspace/tests"
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
@@ -142,6 +144,7 @@ steps:
|
|||||||
- label: ":nvidia: (H200 MIG 35GB) Entrypoints Integration (API Server Generate)"
|
- label: ":nvidia: (H200 MIG 35GB) Entrypoints Integration (API Server Generate)"
|
||||||
device: h200_35gb
|
device: h200_35gb
|
||||||
key: entrypoints-integration-api-server-generate
|
key: entrypoints-integration-api-server-generate
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 50
|
timeout_in_minutes: 50
|
||||||
working_dir: "/vllm-workspace/tests"
|
working_dir: "/vllm-workspace/tests"
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
@@ -170,6 +173,7 @@ steps:
|
|||||||
- label: ":nvidia: (H200 MIG 35GB) Entrypoints Integration (Responses API)"
|
- label: ":nvidia: (H200 MIG 35GB) Entrypoints Integration (Responses API)"
|
||||||
device: h200_35gb
|
device: h200_35gb
|
||||||
key: entrypoints-integration-responses-api
|
key: entrypoints-integration-responses-api
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 50
|
timeout_in_minutes: 50
|
||||||
working_dir: "/vllm-workspace/tests"
|
working_dir: "/vllm-workspace/tests"
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
@@ -190,6 +194,7 @@ steps:
|
|||||||
- label: ":nvidia: (H200 MIG 35GB) Entrypoints Integration (Speech to Text)"
|
- label: ":nvidia: (H200 MIG 35GB) Entrypoints Integration (Speech to Text)"
|
||||||
device: h200_35gb
|
device: h200_35gb
|
||||||
key: entrypoints-integration-speech_to_text
|
key: entrypoints-integration-speech_to_text
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 45
|
timeout_in_minutes: 45
|
||||||
working_dir: "/vllm-workspace/tests"
|
working_dir: "/vllm-workspace/tests"
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
@@ -203,6 +208,7 @@ steps:
|
|||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI355 DPX) Entrypoints Integration (Speech to Text)"
|
label: ":amd: (MI355 DPX) Entrypoints Integration (Speech to Text)"
|
||||||
dind: false
|
dind: false
|
||||||
|
automatic_shard: true
|
||||||
device: mi355_dpx
|
device: mi355_dpx
|
||||||
timeout_in_minutes: 60
|
timeout_in_minutes: 60
|
||||||
working_dir: "/vllm-workspace/tests"
|
working_dir: "/vllm-workspace/tests"
|
||||||
@@ -212,6 +218,7 @@ steps:
|
|||||||
- label: ":nvidia: (H200 MIG 35GB) Entrypoints Integration (Multimodal)"
|
- label: ":nvidia: (H200 MIG 35GB) Entrypoints Integration (Multimodal)"
|
||||||
device: h200_35gb
|
device: h200_35gb
|
||||||
key: entrypoints-integration-multimodal
|
key: entrypoints-integration-multimodal
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 45
|
timeout_in_minutes: 45
|
||||||
working_dir: "/vllm-workspace/tests"
|
working_dir: "/vllm-workspace/tests"
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
@@ -233,6 +240,7 @@ steps:
|
|||||||
- label: ":nvidia: (H200 MIG 35GB) Entrypoints Integration (Pooling)"
|
- label: ":nvidia: (H200 MIG 35GB) Entrypoints Integration (Pooling)"
|
||||||
device: h200_35gb
|
device: h200_35gb
|
||||||
key: entrypoints-integration-pooling
|
key: entrypoints-integration-pooling
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 75
|
timeout_in_minutes: 75
|
||||||
working_dir: "/vllm-workspace/tests"
|
working_dir: "/vllm-workspace/tests"
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
@@ -246,6 +254,7 @@ steps:
|
|||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI355 DPX) Entrypoints Integration (Pooling)"
|
label: ":amd: (MI355 DPX) Entrypoints Integration (Pooling)"
|
||||||
dind: false
|
dind: false
|
||||||
|
automatic_shard: true
|
||||||
device: mi355_dpx
|
device: mi355_dpx
|
||||||
timeout_in_minutes: 65
|
timeout_in_minutes: 65
|
||||||
working_dir: "/vllm-workspace/tests"
|
working_dir: "/vllm-workspace/tests"
|
||||||
|
|||||||
@@ -58,6 +58,8 @@ steps:
|
|||||||
|
|
||||||
- label: ":nvidia: (H100) Elastic EP Scaling"
|
- label: ":nvidia: (H100) Elastic EP Scaling"
|
||||||
key: elastic-ep-scaling-test
|
key: elastic-ep-scaling-test
|
||||||
|
# Nightly only: 4-GPU H100 pods wait behind smaller jobs on per-PR runs.
|
||||||
|
optional: true
|
||||||
timeout_in_minutes: 40
|
timeout_in_minutes: 40
|
||||||
device: h100
|
device: h100
|
||||||
working_dir: "/vllm-workspace/tests"
|
working_dir: "/vllm-workspace/tests"
|
||||||
|
|||||||
@@ -30,9 +30,10 @@ steps:
|
|||||||
- vllm/_aiter_ops.py
|
- vllm/_aiter_ops.py
|
||||||
- vllm/platforms/rocm.py
|
- vllm/platforms/rocm.py
|
||||||
|
|
||||||
- label: ":nvidia: (H200 MIG 35GB) Core Operation Kernels Shard %N"
|
- label: ":nvidia: (H200 MIG 35GB) Core Operation Kernels"
|
||||||
device: h200_35gb
|
device: h200_35gb
|
||||||
key: kernels-core-operation-test
|
key: kernels-core-operation-test
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 120
|
timeout_in_minutes: 120
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- csrc/
|
- csrc/
|
||||||
@@ -40,10 +41,10 @@ steps:
|
|||||||
- tests/kernels/test_concat_mla_q.py
|
- tests/kernels/test_concat_mla_q.py
|
||||||
- tests/kernels/test_fused_qk_norm_rope_gate.py
|
- tests/kernels/test_fused_qk_norm_rope_gate.py
|
||||||
commands:
|
commands:
|
||||||
- pytest -v -s kernels/core --ignore=kernels/core/test_minimax_reduce_rms.py kernels/test_concat_mla_q.py kernels/test_fused_qk_norm_rope_gate.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
|
- pytest -v -s kernels/core --ignore=kernels/core/test_minimax_reduce_rms.py kernels/test_concat_mla_q.py kernels/test_fused_qk_norm_rope_gate.py
|
||||||
parallelism: 3
|
|
||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
|
parallelism: 3
|
||||||
label: ":amd: (MI300) Core Operation Kernels Shard %N"
|
label: ":amd: (MI300) Core Operation Kernels Shard %N"
|
||||||
dind: false
|
dind: false
|
||||||
device: mi300_1
|
device: mi300_1
|
||||||
@@ -72,10 +73,10 @@ steps:
|
|||||||
num_devices: 2
|
num_devices: 2
|
||||||
device: h100
|
device: h100
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- csrc/libtorch_stable/minimax_reduce_rms_kernel.cu
|
- csrc/minimax_reduce_rms_kernel.cu
|
||||||
- csrc/libtorch_stable/minimax_reduce_rms_kernel.h
|
- csrc/minimax_reduce_rms_kernel.h
|
||||||
- csrc/libtorch_stable/ops.h
|
- csrc/ops.h
|
||||||
- csrc/libtorch_stable/torch_bindings.cpp
|
- csrc/torch_bindings.cpp
|
||||||
- vllm/model_executor/layers/minimax_rms_norm/
|
- vllm/model_executor/layers/minimax_rms_norm/
|
||||||
- vllm/model_executor/layers/mamba/linear/minimax_linear_attn.py
|
- vllm/model_executor/layers/mamba/linear/minimax_linear_attn.py
|
||||||
- tests/kernels/core/test_minimax_reduce_rms.py
|
- tests/kernels/core/test_minimax_reduce_rms.py
|
||||||
@@ -122,7 +123,7 @@ steps:
|
|||||||
depends_on:
|
depends_on:
|
||||||
- image-build-amd
|
- image-build-amd
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- csrc/libtorch_stable/fused_deepseek_v4_qnorm_rope_kv_insert_kernel.cu
|
- csrc/fused_deepseek_v4_qnorm_rope_kv_insert_kernel.cu
|
||||||
- vllm/models/deepseek_v4/common/ops/
|
- vllm/models/deepseek_v4/common/ops/
|
||||||
- tests/kernels/test_fused_deepseek_v4_qnorm_rope_kv_insert.py
|
- tests/kernels/test_fused_deepseek_v4_qnorm_rope_kv_insert.py
|
||||||
- vllm/platforms/rocm.py
|
- vllm/platforms/rocm.py
|
||||||
@@ -137,11 +138,15 @@ steps:
|
|||||||
- csrc/fused_deepseek_v4_qnorm_rope_kv_insert_kernel.cu
|
- csrc/fused_deepseek_v4_qnorm_rope_kv_insert_kernel.cu
|
||||||
- vllm/models/deepseek_v4/common/ops/
|
- vllm/models/deepseek_v4/common/ops/
|
||||||
- vllm/models/deepseek_v4/nvidia/
|
- vllm/models/deepseek_v4/nvidia/
|
||||||
|
- vllm/model_executor/layers/fused_moe/deep_gemm_mega_moe.py
|
||||||
|
- vllm/model_executor/layers/fused_moe/prepare_megamoe.py
|
||||||
- vllm/utils/deep_gemm.py
|
- vllm/utils/deep_gemm.py
|
||||||
- tests/kernels/test_fused_deepseek_v4_qnorm_rope_kv_insert.py
|
- tests/kernels/test_fused_deepseek_v4_qnorm_rope_kv_insert.py
|
||||||
|
- tests/kernels/moe/test_deep_gemm_mega_moe.py
|
||||||
- tests/models/test_deepseek_v4_mega_moe.py
|
- tests/models/test_deepseek_v4_mega_moe.py
|
||||||
commands:
|
commands:
|
||||||
- pytest -v -s kernels/test_fused_deepseek_v4_*.py
|
- pytest -v -s kernels/test_fused_deepseek_v4_*.py
|
||||||
|
- pytest -v -s kernels/moe/test_deep_gemm_mega_moe.py
|
||||||
- pytest -v -s models/test_deepseek_v4_mega_moe.py
|
- pytest -v -s models/test_deepseek_v4_mega_moe.py
|
||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
@@ -155,6 +160,7 @@ steps:
|
|||||||
- image-build-amd
|
- image-build-amd
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- tests/models/test_deepseek_v4_vl_rocm.py
|
- tests/models/test_deepseek_v4_vl_rocm.py
|
||||||
|
- tests/models/test_deepseek_v4_aiter_mega_moe.py
|
||||||
- vllm/models/deepseek_v4/amd/
|
- vllm/models/deepseek_v4/amd/
|
||||||
- vllm/models/deepseek_v4/common/
|
- vllm/models/deepseek_v4/common/
|
||||||
- vllm/model_executor/layers/fused_moe/
|
- vllm/model_executor/layers/fused_moe/
|
||||||
@@ -170,6 +176,7 @@ steps:
|
|||||||
# Common qnorm/RoPE/cache kernels already run in the H100 AMD mirror.
|
# Common qnorm/RoPE/cache kernels already run in the H100 AMD mirror.
|
||||||
# Pin the tested BF16 Triton routing and shared-expert path before imports.
|
# Pin the tested BF16 Triton routing and shared-expert path before imports.
|
||||||
- VLLM_ROCM_USE_AITER_MOE=0 pytest -v -s models/test_deepseek_v4_vl_rocm.py
|
- VLLM_ROCM_USE_AITER_MOE=0 pytest -v -s models/test_deepseek_v4_vl_rocm.py
|
||||||
|
- pytest -v -s models/test_deepseek_v4_aiter_mega_moe.py
|
||||||
|
|
||||||
# Own job so mHC never shares a process with FlashInfer's import-time
|
# Own job so mHC never shares a process with FlashInfer's import-time
|
||||||
# ptxas override.
|
# ptxas override.
|
||||||
@@ -228,8 +235,8 @@ steps:
|
|||||||
# Catch-all for test files at the tests/kernels root. This job collects
|
# Catch-all for test files at the tests/kernels root. This job collects
|
||||||
# the whole root so new files are wired by default.
|
# the whole root so new files are wired by default.
|
||||||
# Files with dedicated jobs elsewhere in this file are excluded via --ignore
|
# Files with dedicated jobs elsewhere in this file are excluded via --ignore
|
||||||
# (test_bf16x3_router_gemm_cutedsl and test_ll_bf16_gemm run in their own jobs /
|
# (test_bf16x3_router_gemm_cutedsl runs in Kernels (B200); test_ll_bf16_gemm and
|
||||||
# Kernels (B200)).
|
# test_ll_fp32w_gemm run in Gate Linear CuTeDSL Kernels (B200)).
|
||||||
- label: ":nvidia: (B200) Miscellaneous Kernels"
|
- label: ":nvidia: (B200) Miscellaneous Kernels"
|
||||||
key: kernels-root-misc-test-b200
|
key: kernels-root-misc-test-b200
|
||||||
timeout_in_minutes: 30
|
timeout_in_minutes: 30
|
||||||
@@ -254,8 +261,11 @@ steps:
|
|||||||
--ignore=kernels/test_fused_qk_norm_rope_gate.py
|
--ignore=kernels/test_fused_qk_norm_rope_gate.py
|
||||||
--ignore=kernels/test_fused_deepseek_v4_qnorm_rope_kv_insert.py
|
--ignore=kernels/test_fused_deepseek_v4_qnorm_rope_kv_insert.py
|
||||||
--ignore=kernels/test_top_k_per_row.py
|
--ignore=kernels/test_top_k_per_row.py
|
||||||
|
--ignore=kernels/test_cpu_fused_sampling.py
|
||||||
--ignore=kernels/test_bf16x3_router_gemm_cutedsl.py
|
--ignore=kernels/test_bf16x3_router_gemm_cutedsl.py
|
||||||
|
--ignore=kernels/test_bf16x3_router_gemm_rocm.py
|
||||||
--ignore=kernels/test_ll_bf16_gemm.py
|
--ignore=kernels/test_ll_bf16_gemm.py
|
||||||
|
--ignore=kernels/test_ll_fp32w_gemm.py
|
||||||
--ignore=kernels/test_shuffle_rows.py
|
--ignore=kernels/test_shuffle_rows.py
|
||||||
# BROKEN on main, pending kernel fixes (B200):
|
# BROKEN on main, pending kernel fixes (B200):
|
||||||
# test_shuffle_rows.py (1: test_shuffle_rows_edge_cases)
|
# test_shuffle_rows.py (1: test_shuffle_rows_edge_cases)
|
||||||
@@ -294,14 +304,12 @@ steps:
|
|||||||
kernels/test_fused_inv_rope_fp8_quant.py
|
kernels/test_fused_inv_rope_fp8_quant.py
|
||||||
kernels/test_fused_minimax_m3_qknorm_rope_kv_insert.py
|
kernels/test_fused_minimax_m3_qknorm_rope_kv_insert.py
|
||||||
kernels/test_fused_quant_activation.py
|
kernels/test_fused_quant_activation.py
|
||||||
kernels/test_gate_linear_rocm_dispatch.py
|
|
||||||
kernels/test_gemm_rs_ar.py
|
kernels/test_gemm_rs_ar.py
|
||||||
kernels/test_kpool_decode_update_batched.py
|
kernels/test_kpool_decode_update_batched.py
|
||||||
kernels/test_minimax_m3_amd_ops.py
|
kernels/test_minimax_m3_amd_ops.py
|
||||||
kernels/test_minimax_m3_sparse_attn_fp8_scale.py
|
kernels/test_minimax_m3_sparse_attn_fp8_scale.py
|
||||||
kernels/test_onednn.py
|
kernels/test_onednn.py
|
||||||
kernels/test_relu2_fp8_quant.py
|
kernels/test_relu2_fp8_quant.py
|
||||||
kernels/test_rocm_fp32_router_gemm.py
|
|
||||||
--deselect=tests/kernels/test_bf16_skinny_gemm.py::test_every_dsv3_routed_shape_is_instantiated
|
--deselect=tests/kernels/test_bf16_skinny_gemm.py::test_every_dsv3_routed_shape_is_instantiated
|
||||||
|
|
||||||
- label: ":nvidia: (L4) Attention Kernels Shard %N"
|
- label: ":nvidia: (L4) Attention Kernels Shard %N"
|
||||||
@@ -311,6 +319,7 @@ steps:
|
|||||||
timeout_in_minutes: 30
|
timeout_in_minutes: 30
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- csrc/attention/
|
- csrc/attention/
|
||||||
|
- csrc/core/vec_dtypes/
|
||||||
- vllm/v1/attention
|
- vllm/v1/attention
|
||||||
# TODO: remove this dependency (https://github.com/vllm-project/vllm/issues/32267)
|
# TODO: remove this dependency (https://github.com/vllm-project/vllm/issues/32267)
|
||||||
- vllm/model_executor/layers/attention
|
- vllm/model_executor/layers/attention
|
||||||
@@ -330,6 +339,7 @@ steps:
|
|||||||
- image-build-amd
|
- image-build-amd
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- csrc/attention/
|
- csrc/attention/
|
||||||
|
- csrc/core/vec_dtypes/
|
||||||
- vllm/v1/attention
|
- vllm/v1/attention
|
||||||
- vllm/model_executor/layers/attention
|
- vllm/model_executor/layers/attention
|
||||||
- tests/kernels/attention
|
- tests/kernels/attention
|
||||||
@@ -402,10 +412,14 @@ steps:
|
|||||||
depends_on:
|
depends_on:
|
||||||
- image-build-amd
|
- image-build-amd
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
|
- vllm/models/deepseek_v41/amd/rocm.py
|
||||||
|
- vllm/models/deepseek_v41/sparse_mla.py
|
||||||
- vllm/v1/attention/backends/mla/rocm_aiter_mla.py
|
- vllm/v1/attention/backends/mla/rocm_aiter_mla.py
|
||||||
|
- vllm/v1/attention/ops/rocm_aiter_mla_sparse.py
|
||||||
- vllm/v1/attention/selector.py
|
- vllm/v1/attention/selector.py
|
||||||
- vllm/platforms/rocm.py
|
- vllm/platforms/rocm.py
|
||||||
- vllm/_aiter_ops.py
|
- vllm/_aiter_ops.py
|
||||||
|
- tests/kernels/attention/test_rocm_triton_attn_dsv4.py
|
||||||
- tests/kernels/attention/test_rocm_aiter_mla_decode.py
|
- tests/kernels/attention/test_rocm_aiter_mla_decode.py
|
||||||
- tests/kernels/attention/test_rocm_aiter_mla_decode_metadata.py
|
- tests/kernels/attention/test_rocm_aiter_mla_decode_metadata.py
|
||||||
- tests/kernels/attention/test_rocm_aiter_mla_fp8_support.py
|
- tests/kernels/attention/test_rocm_aiter_mla_fp8_support.py
|
||||||
@@ -416,6 +430,7 @@ steps:
|
|||||||
- pytest -v -s tests/kernels/attention/test_rocm_aiter_mla_decode.py
|
- pytest -v -s tests/kernels/attention/test_rocm_aiter_mla_decode.py
|
||||||
- pytest -v -s tests/kernels/attention/test_rocm_aiter_mla_fp8_support.py
|
- pytest -v -s tests/kernels/attention/test_rocm_aiter_mla_fp8_support.py
|
||||||
- pytest -v -s tests/kernels/attention/test_rocm_aiter_mla_op_registration.py
|
- pytest -v -s tests/kernels/attention/test_rocm_aiter_mla_op_registration.py
|
||||||
|
- pytest -v -s tests/kernels/attention/test_rocm_triton_attn_dsv4.py::test_dsv41_adaptive_mla_swa_metadata_graph_replay
|
||||||
|
|
||||||
- label: ":nvidia: (L4) Quantization Kernels Shard %N"
|
- label: ":nvidia: (L4) Quantization Kernels Shard %N"
|
||||||
key: kernels-quantization-test
|
key: kernels-quantization-test
|
||||||
@@ -462,7 +477,7 @@ steps:
|
|||||||
num_devices: 1
|
num_devices: 1
|
||||||
timeout_in_minutes: 50
|
timeout_in_minutes: 50
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- csrc/quantization/cutlass_w8a8/moe/
|
- csrc/quantization/w8a8/cutlass/moe/
|
||||||
- csrc/moe/
|
- csrc/moe/
|
||||||
- tests/kernels/moe
|
- tests/kernels/moe
|
||||||
- vllm/model_executor/layers/fused_moe/
|
- vllm/model_executor/layers/fused_moe/
|
||||||
@@ -480,7 +495,7 @@ steps:
|
|||||||
device: mi300_1
|
device: mi300_1
|
||||||
timeout_in_minutes: 55
|
timeout_in_minutes: 55
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- csrc/quantization/cutlass_w8a8/moe/
|
- csrc/quantization/w8a8/cutlass/moe/
|
||||||
- csrc/moe/
|
- csrc/moe/
|
||||||
- tests/kernels/moe
|
- tests/kernels/moe
|
||||||
- vllm/model_executor/layers/fused_moe/
|
- vllm/model_executor/layers/fused_moe/
|
||||||
@@ -499,18 +514,22 @@ steps:
|
|||||||
- label: ":nvidia: (H200 MIG 35GB) Mamba Kernels"
|
- label: ":nvidia: (H200 MIG 35GB) Mamba Kernels"
|
||||||
device: h200_35gb
|
device: h200_35gb
|
||||||
key: kernels-mamba-test
|
key: kernels-mamba-test
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 60
|
timeout_in_minutes: 60
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- csrc/mamba/
|
- csrc/mamba/
|
||||||
- tests/kernels/mamba
|
- tests/kernels/mamba
|
||||||
|
- vllm/model_executor/layers/mamba/checkpoint.py
|
||||||
- vllm/model_executor/layers/mamba/gdn
|
- vllm/model_executor/layers/mamba/gdn
|
||||||
- vllm/model_executor/layers/mamba/ops
|
- vllm/model_executor/layers/mamba/ops
|
||||||
|
- vllm/v1/attention/backends/gdn_attn.py
|
||||||
commands:
|
commands:
|
||||||
- pytest -v -s kernels/mamba
|
- pytest -v -s kernels/mamba
|
||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI250) Mamba Kernels"
|
label: ":amd: (MI250) Mamba Kernels"
|
||||||
dind: false
|
dind: false
|
||||||
|
automatic_shard: true
|
||||||
device: mi250_1
|
device: mi250_1
|
||||||
timeout_in_minutes: 55
|
timeout_in_minutes: 55
|
||||||
depends_on:
|
depends_on:
|
||||||
@@ -526,7 +545,6 @@ steps:
|
|||||||
num_devices: 1
|
num_devices: 1
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- cmake/external_projects/deepgemm.cmake
|
- cmake/external_projects/deepgemm.cmake
|
||||||
- tools/install_deepgemm.sh
|
|
||||||
- tools/build_deepgemm_C.py
|
- tools/build_deepgemm_C.py
|
||||||
- tools/setup_deepgemm_pythons.sh
|
- tools/setup_deepgemm_pythons.sh
|
||||||
- tools/check_wheel_deepgemm.py
|
- tools/check_wheel_deepgemm.py
|
||||||
@@ -546,6 +564,21 @@ steps:
|
|||||||
- pytest -v -s kernels/attention/test_deepgemm_attention.py
|
- pytest -v -s kernels/attention/test_deepgemm_attention.py
|
||||||
- pytest -v -s quantization/test_cutlass_w4a16.py
|
- pytest -v -s quantization/test_cutlass_w4a16.py
|
||||||
|
|
||||||
|
- label: ":nvidia: (B200) MiniMax-M3 Attention Kernels"
|
||||||
|
key: kernels-minimax-m3-attention-b200
|
||||||
|
timeout_in_minutes: 30
|
||||||
|
working_dir: "/vllm-workspace/"
|
||||||
|
device: b200-k8s
|
||||||
|
num_devices: 1
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/models/minimax_m3/
|
||||||
|
- vllm/config/cache.py
|
||||||
|
- vllm/v1/kv_cache_interface.py
|
||||||
|
- tests/v1/attention/utils.py
|
||||||
|
- tests/kernels/attention/test_minimax_m3.py
|
||||||
|
commands:
|
||||||
|
- pytest -v -s tests/kernels/attention/test_minimax_m3.py
|
||||||
|
|
||||||
- label: ":nvidia: (B200) Kernels Shard %N"
|
- label: ":nvidia: (B200) Kernels Shard %N"
|
||||||
key: kernels-b200
|
key: kernels-b200
|
||||||
timeout_in_minutes: 30
|
timeout_in_minutes: 30
|
||||||
@@ -555,11 +588,10 @@ steps:
|
|||||||
# optional: true
|
# optional: true
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- csrc/quantization/fp4/
|
- csrc/quantization/fp4/
|
||||||
- csrc/libtorch_stable/nvfp4_kv_cache_kernels.cu
|
- csrc/nvfp4_kv_cache_kernels.cu
|
||||||
- csrc/libtorch_stable/quantization/fp4/
|
- csrc/quantization/w8a8/cutlass/
|
||||||
- csrc/libtorch_stable/quantization/w8a8/cutlass/
|
|
||||||
- csrc/attention/mla/
|
- csrc/attention/mla/
|
||||||
- csrc/quantization/cutlass_w8a8/moe/
|
- csrc/quantization/w8a8/cutlass/moe/
|
||||||
- vllm/model_executor/layers/fusion/
|
- vllm/model_executor/layers/fusion/
|
||||||
- vllm/model_executor/layers/fused_moe/experts/cutlass_moe.py
|
- vllm/model_executor/layers/fused_moe/experts/cutlass_moe.py
|
||||||
- vllm/model_executor/layers/fused_moe/experts/flashinfer_cutlass_moe.py
|
- vllm/model_executor/layers/fused_moe/experts/flashinfer_cutlass_moe.py
|
||||||
@@ -573,9 +605,6 @@ steps:
|
|||||||
- vllm/v1/attention/backends/mla/flashinfer_mla.py
|
- vllm/v1/attention/backends/mla/flashinfer_mla.py
|
||||||
- vllm/v1/attention/selector.py
|
- vllm/v1/attention/selector.py
|
||||||
- vllm/platforms/cuda.py
|
- vllm/platforms/cuda.py
|
||||||
- vllm/model_executor/kernels/linear/cute_dsl/ll_bf16.py
|
|
||||||
- vllm/model_executor/kernels/linear/cute_dsl/_ll_bf16_dotprod.py
|
|
||||||
- vllm/model_executor/kernels/linear/cute_dsl/_ll_bf16_splitk.py
|
|
||||||
- vllm/cute_utils/
|
- vllm/cute_utils/
|
||||||
- vllm/model_executor/layers/mamba/ops/gdn_chunk_cutedsl/
|
- vllm/model_executor/layers/mamba/ops/gdn_chunk_cutedsl/
|
||||||
- vllm/model_executor/layers/fused_moe/router/bf16x3_router_gemm_cutedsl.py
|
- vllm/model_executor/layers/fused_moe/router/bf16x3_router_gemm_cutedsl.py
|
||||||
@@ -585,9 +614,9 @@ steps:
|
|||||||
- vllm/config/attention.py
|
- vllm/config/attention.py
|
||||||
- vllm/v1/attention/backends/registry.py
|
- vllm/v1/attention/backends/registry.py
|
||||||
- vllm/_custom_ops.py
|
- vllm/_custom_ops.py
|
||||||
- csrc/libtorch_stable/fused_minimax_m3_qknorm_rope_kv_insert_kernel.cu
|
- csrc/fused_minimax_m3_qknorm_rope_kv_insert_kernel.cu
|
||||||
- csrc/libtorch_stable/ops.h
|
- csrc/ops.h
|
||||||
- csrc/libtorch_stable/torch_bindings.cpp
|
- csrc/torch_bindings.cpp
|
||||||
- tests/kernels/attention/test_flashinfer_mla_decode.py
|
- tests/kernels/attention/test_flashinfer_mla_decode.py
|
||||||
- tests/kernels/attention/test_minimax_m3_msa_cutlass_sparse_decode.py
|
- tests/kernels/attention/test_minimax_m3_msa_cutlass_sparse_decode.py
|
||||||
- tests/kernels/attention/test_cache.py
|
- tests/kernels/attention/test_cache.py
|
||||||
@@ -595,8 +624,6 @@ steps:
|
|||||||
- tests/kernels/test_fused_minimax_m3_qknorm_rope_kv_insert.py
|
- tests/kernels/test_fused_minimax_m3_qknorm_rope_kv_insert.py
|
||||||
- tests/kernels/mamba/test_gdn_prefill_cutedsl.py
|
- tests/kernels/mamba/test_gdn_prefill_cutedsl.py
|
||||||
- tests/kernels/test_bf16x3_router_gemm_cutedsl.py
|
- tests/kernels/test_bf16x3_router_gemm_cutedsl.py
|
||||||
- tests/kernels/attention/test_minimax_m3.py
|
|
||||||
- tests/kernels/test_ll_bf16_gemm.py
|
|
||||||
- tests/kernels/test_top_k_per_row.py
|
- tests/kernels/test_top_k_per_row.py
|
||||||
- tests/kernels/quantization/test_silu_mul_nvfp4_quant.py
|
- tests/kernels/quantization/test_silu_mul_nvfp4_quant.py
|
||||||
- tests/kernels/quantization/test_block_fp8.py
|
- tests/kernels/quantization/test_block_fp8.py
|
||||||
@@ -617,7 +644,6 @@ steps:
|
|||||||
pytest -v -s tests/kernels/moe/test_nvfp4_moe.py
|
pytest -v -s tests/kernels/moe/test_nvfp4_moe.py
|
||||||
pytest -v -s tests/kernels/moe/test_ocp_mx_moe.py
|
pytest -v -s tests/kernels/moe/test_ocp_mx_moe.py
|
||||||
pytest -v -s tests/kernels/test_bf16x3_router_gemm_cutedsl.py
|
pytest -v -s tests/kernels/test_bf16x3_router_gemm_cutedsl.py
|
||||||
pytest -v -s tests/kernels/test_ll_bf16_gemm.py
|
|
||||||
;;
|
;;
|
||||||
1)
|
1)
|
||||||
python3 examples/basic/offline_inference/chat.py
|
python3 examples/basic/offline_inference/chat.py
|
||||||
@@ -641,7 +667,6 @@ steps:
|
|||||||
pytest -v -s tests/kernels/moe/test_flashinfer.py
|
pytest -v -s tests/kernels/moe/test_flashinfer.py
|
||||||
pytest -v -s tests/kernels/moe/test_trtllm_nvfp4_moe.py
|
pytest -v -s tests/kernels/moe/test_trtllm_nvfp4_moe.py
|
||||||
pytest -v -s tests/kernels/mamba/test_gdn_prefill_cutedsl.py
|
pytest -v -s tests/kernels/mamba/test_gdn_prefill_cutedsl.py
|
||||||
pytest -v -s tests/kernels/attention/test_minimax_m3.py
|
|
||||||
;;
|
;;
|
||||||
*)
|
*)
|
||||||
echo "unexpected BUILDKITE_PARALLEL_JOB=$$BUILDKITE_PARALLEL_JOB" >&2
|
echo "unexpected BUILDKITE_PARALLEL_JOB=$$BUILDKITE_PARALLEL_JOB" >&2
|
||||||
@@ -675,6 +700,46 @@ steps:
|
|||||||
- amd-smi
|
- amd-smi
|
||||||
- pytest -v -s kernels/quantization/test_nvfp4_emulation.py -k test_nvfp4_dense_emulation --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
|
- pytest -v -s kernels/quantization/test_nvfp4_emulation.py -k test_nvfp4_dense_emulation --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
|
||||||
|
|
||||||
|
- label: ":nvidia: (B200) Gate Linear CuTeDSL Kernels"
|
||||||
|
key: kernels-gate-linear-cutedsl-b200
|
||||||
|
timeout_in_minutes: 15
|
||||||
|
working_dir: "/vllm-workspace/"
|
||||||
|
device: b200-k8s
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/cute_utils/
|
||||||
|
- vllm/platforms/cuda.py
|
||||||
|
- vllm/model_executor/layers/fused_moe/router/gate_linear.py
|
||||||
|
- vllm/model_executor/kernels/linear/cute_dsl/_ll_router_common.py
|
||||||
|
- vllm/model_executor/kernels/linear/cute_dsl/ll_bf16.py
|
||||||
|
- vllm/model_executor/kernels/linear/cute_dsl/_ll_bf16_dotprod.py
|
||||||
|
- vllm/model_executor/kernels/linear/cute_dsl/_ll_bf16_splitk.py
|
||||||
|
- tests/kernels/test_ll_bf16_gemm.py
|
||||||
|
- vllm/model_executor/kernels/linear/cute_dsl/ll_fp32w.py
|
||||||
|
- vllm/model_executor/kernels/linear/cute_dsl/_ll_fp32w_dotprod.py
|
||||||
|
- tests/kernels/test_ll_fp32w_gemm.py
|
||||||
|
commands:
|
||||||
|
- nvidia-smi
|
||||||
|
- pytest -v -s tests/kernels/test_ll_bf16_gemm.py
|
||||||
|
- pytest -v -s tests/kernels/test_ll_fp32w_gemm.py
|
||||||
|
mirror:
|
||||||
|
amd:
|
||||||
|
label: ":amd: (MI355) Gate Linear Router Kernels"
|
||||||
|
dind: false
|
||||||
|
device: mi355_1
|
||||||
|
timeout_in_minutes: 20
|
||||||
|
depends_on:
|
||||||
|
- image-build-amd
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/model_executor/layers/fused_moe/router/gate_linear.py
|
||||||
|
- vllm/model_executor/layers/fused_moe/router/rocm_fp32_router_gemm.py
|
||||||
|
- vllm/model_executor/layers/fused_moe/router/bf16x3_router_gemm_rocm.py
|
||||||
|
- vllm/platforms/rocm.py
|
||||||
|
- tests/kernels/test_rocm_fp32_router_gemm.py
|
||||||
|
- tests/kernels/test_gate_linear_rocm_dispatch.py
|
||||||
|
- tests/kernels/test_bf16x3_router_gemm_rocm.py
|
||||||
|
commands:
|
||||||
|
- pytest -v -s tests/kernels/test_rocm_fp32_router_gemm.py tests/kernels/test_gate_linear_rocm_dispatch.py tests/kernels/test_bf16x3_router_gemm_rocm.py
|
||||||
|
|
||||||
- label: ":nvidia: (DGX) Spark b12x Linear Kernels Nightly"
|
- label: ":nvidia: (DGX) Spark b12x Linear Kernels Nightly"
|
||||||
key: b12x-linear-kernels-dgx-spark-nightly
|
key: b12x-linear-kernels-dgx-spark-nightly
|
||||||
timeout_in_minutes: 60
|
timeout_in_minutes: 60
|
||||||
@@ -707,7 +772,7 @@ steps:
|
|||||||
- tests/quantization/reference_mxfp4.py
|
- tests/quantization/reference_mxfp4.py
|
||||||
- tests/quantization/test_auto_round.py
|
- tests/quantization/test_auto_round.py
|
||||||
commands:
|
commands:
|
||||||
- uv pip install --system b12x==1.3.0
|
- uv pip install --system b12x==1.5.1
|
||||||
- pytest -v -s model_executor/kernels/test_b12x_linear.py
|
- pytest -v -s model_executor/kernels/test_b12x_linear.py
|
||||||
model_executor/test_b12x_warmup.py
|
model_executor/test_b12x_warmup.py
|
||||||
kernels/quantization/test_block_fp8.py
|
kernels/quantization/test_block_fp8.py
|
||||||
@@ -834,7 +899,7 @@ steps:
|
|||||||
device: h100
|
device: h100
|
||||||
num_devices: 2
|
num_devices: 2
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- csrc/quantization/cutlass_w8a8/moe/
|
- csrc/quantization/w8a8/cutlass/moe/
|
||||||
- csrc/moe/
|
- csrc/moe/
|
||||||
- tests/kernels/moe
|
- tests/kernels/moe
|
||||||
- vllm/model_executor/layers/fused_moe/
|
- vllm/model_executor/layers/fused_moe/
|
||||||
@@ -873,11 +938,11 @@ steps:
|
|||||||
|
|
||||||
- label: ":nvidia: (B200) FusedMoE Layer Kernels"
|
- label: ":nvidia: (B200) FusedMoE Layer Kernels"
|
||||||
key: kernels-fusedmoe-layer-test-2-b200s
|
key: kernels-fusedmoe-layer-test-2-b200s
|
||||||
timeout_in_minutes: 90
|
timeout_in_minutes: 45
|
||||||
device: b200-k8s
|
device: b200-k8s
|
||||||
num_devices: 2
|
num_devices: 2
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- csrc/quantization/cutlass_w8a8/moe/
|
- csrc/quantization/w8a8/cutlass/moe/
|
||||||
- csrc/moe/
|
- csrc/moe/
|
||||||
- tests/kernels/moe
|
- tests/kernels/moe
|
||||||
- vllm/model_executor/layers/fused_moe/
|
- vllm/model_executor/layers/fused_moe/
|
||||||
@@ -990,7 +1055,7 @@ steps:
|
|||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- csrc/quantization/fp4/
|
- csrc/quantization/fp4/
|
||||||
- csrc/attention/mla/
|
- csrc/attention/mla/
|
||||||
- csrc/quantization/cutlass_w8a8/moe/
|
- csrc/quantization/w8a8/cutlass/moe/
|
||||||
- vllm/model_executor/layers/fused_moe/cutlass_moe.py
|
- vllm/model_executor/layers/fused_moe/cutlass_moe.py
|
||||||
- vllm/v1/attention/backends/triton_attn.py
|
- vllm/v1/attention/backends/triton_attn.py
|
||||||
- vllm/v1/attention/backends/rocm_attn.py
|
- vllm/v1/attention/backends/rocm_attn.py
|
||||||
|
|||||||
@@ -5,6 +5,7 @@ steps:
|
|||||||
- label: ":nvidia: (H200 MIG 35GB) LM Eval Small Models"
|
- label: ":nvidia: (H200 MIG 35GB) LM Eval Small Models"
|
||||||
device: h200_35gb
|
device: h200_35gb
|
||||||
key: lm-eval-small-models
|
key: lm-eval-small-models
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 45
|
timeout_in_minutes: 45
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- csrc/
|
- csrc/
|
||||||
@@ -14,9 +15,9 @@ steps:
|
|||||||
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small.txt
|
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small.txt
|
||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI300) LM Eval Small Models"
|
label: ":amd: (MI355) LM Eval Small Models"
|
||||||
dind: false
|
dind: false
|
||||||
device: mi300_1
|
device: mi355_dpx
|
||||||
timeout_in_minutes: 45
|
timeout_in_minutes: 45
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-amd
|
- image-build-amd
|
||||||
@@ -104,6 +105,7 @@ steps:
|
|||||||
|
|
||||||
- label: ":nvidia: (H100) LM Eval Large Models"
|
- label: ":nvidia: (H100) LM Eval Large Models"
|
||||||
key: lm-eval-large-models-4xh100
|
key: lm-eval-large-models-4xh100
|
||||||
|
automatic_shard: true
|
||||||
device: h100
|
device: h100
|
||||||
optional: true
|
optional: true
|
||||||
num_devices: 4
|
num_devices: 4
|
||||||
@@ -138,6 +140,7 @@ steps:
|
|||||||
|
|
||||||
- label: ":nvidia: (B200) LM Eval Small Models"
|
- label: ":nvidia: (B200) LM Eval Small Models"
|
||||||
key: lm-eval-small-models-1xb200
|
key: lm-eval-small-models-1xb200
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 50
|
timeout_in_minutes: 50
|
||||||
device: b200-k8s
|
device: b200-k8s
|
||||||
optional: true
|
optional: true
|
||||||
@@ -208,7 +211,6 @@ steps:
|
|||||||
- tests/evals/gsm8k/
|
- tests/evals/gsm8k/
|
||||||
- tests/utils.py
|
- tests/utils.py
|
||||||
- vllm/distributed/
|
- vllm/distributed/
|
||||||
- vllm/transformers_utils/configs/diffusion_gemma.py
|
|
||||||
- vllm/v1/attention/ops/
|
- vllm/v1/attention/ops/
|
||||||
commands:
|
commands:
|
||||||
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-mi3xx-fp8-and-mixed.txt
|
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-mi3xx-fp8-and-mixed.txt
|
||||||
@@ -230,12 +232,13 @@ steps:
|
|||||||
- vllm/v1/attention/backends/mla/
|
- vllm/v1/attention/backends/mla/
|
||||||
- vllm/model_executor/layers/attention/sparse_mla_attention.py
|
- vllm/model_executor/layers/attention/sparse_mla_attention.py
|
||||||
- vllm/v1/worker/gpu/
|
- vllm/v1/worker/gpu/
|
||||||
- csrc/libtorch_stable/hisparse_kernels.cu
|
- csrc/hisparse_kernels.cu
|
||||||
commands:
|
commands:
|
||||||
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-hisparse.txt
|
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-hisparse.txt
|
||||||
|
|
||||||
- label: ":nvidia: (B200) LM Eval PCP"
|
- label: ":nvidia: (B200) LM Eval PCP"
|
||||||
key: lm-eval-pcp-4xb200
|
key: lm-eval-pcp-4xb200
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 360
|
timeout_in_minutes: 360
|
||||||
device: b200-k8s
|
device: b200-k8s
|
||||||
num_devices: 4
|
num_devices: 4
|
||||||
@@ -270,6 +273,9 @@ steps:
|
|||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- .buildkite/test_areas/lm_eval.yaml
|
- .buildkite/test_areas/lm_eval.yaml
|
||||||
- tests/evals/gsm8k/
|
- tests/evals/gsm8k/
|
||||||
|
- tests/watermarking/test_compatibility.py
|
||||||
|
- tests/watermarking/test_engine_compatibility.py
|
||||||
|
- tests/watermarking/test_parallel_compatibility.py
|
||||||
- vllm/config/speculative.py
|
- vllm/config/speculative.py
|
||||||
- vllm/config/vllm.py
|
- vllm/config/vllm.py
|
||||||
- vllm/config/watermarking.py
|
- vllm/config/watermarking.py
|
||||||
@@ -282,6 +288,7 @@ steps:
|
|||||||
autorun_on_main: true
|
autorun_on_main: true
|
||||||
commands:
|
commands:
|
||||||
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-watermark-dspark-tp2.txt
|
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-watermark-dspark-tp2.txt
|
||||||
|
- pytest -s -v watermarking/test_compatibility.py watermarking/test_engine_compatibility.py watermarking/test_parallel_compatibility.py
|
||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI355) LM Eval Watermark Feature Combination"
|
label: ":amd: (MI355) LM Eval Watermark Feature Combination"
|
||||||
@@ -318,9 +325,11 @@ steps:
|
|||||||
optional: true
|
optional: true
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- tests/evals/gsm8k/configs/DeepSeek-V4-Flash-DSpark-confidence-TEP4.yaml
|
- tests/evals/gsm8k/configs/DeepSeek-V4-Flash-DSpark-confidence-TEP4.yaml
|
||||||
|
- tests/evals/gsm8k/configs/DeepSeek-V4.1-Flash-NVFP4-DSpark-TP4.yaml
|
||||||
- tests/evals/gsm8k/configs/Kimi-K3-pruned75-DSpark-TP4.yaml
|
- tests/evals/gsm8k/configs/Kimi-K3-pruned75-DSpark-TP4.yaml
|
||||||
- tests/evals/gsm8k/configs/models-spec-decode.txt
|
- tests/evals/gsm8k/configs/models-spec-decode.txt
|
||||||
- vllm/models/deepseek_v4/
|
- vllm/models/deepseek_v4/
|
||||||
|
- vllm/models/deepseek_v41/
|
||||||
- vllm/models/kimi_k3/
|
- vllm/models/kimi_k3/
|
||||||
- vllm/model_executor/models/qwen3_dspark.py
|
- vllm/model_executor/models/qwen3_dspark.py
|
||||||
- vllm/v1/spec_decode/metrics.py
|
- vllm/v1/spec_decode/metrics.py
|
||||||
@@ -365,6 +374,7 @@ steps:
|
|||||||
- vllm/tokenizers/
|
- vllm/tokenizers/
|
||||||
- vllm/v1/attention/
|
- vllm/v1/attention/
|
||||||
- vllm/v1/core/kv_cache_utils.py
|
- vllm/v1/core/kv_cache_utils.py
|
||||||
|
- vllm/v1/core/kv_cache_planning.py
|
||||||
- vllm/v1/spec_decode/metrics.py
|
- vllm/v1/spec_decode/metrics.py
|
||||||
- vllm/v1/worker/
|
- vllm/v1/worker/
|
||||||
- vllm/_aiter_ops.py
|
- vllm/_aiter_ops.py
|
||||||
@@ -377,6 +387,7 @@ steps:
|
|||||||
|
|
||||||
- label: ":nvidia: (B200) LM Eval Large Models EP"
|
- label: ":nvidia: (B200) LM Eval Large Models EP"
|
||||||
key: lm-eval-large-models-ep-2xb200
|
key: lm-eval-large-models-ep-2xb200
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 60
|
timeout_in_minutes: 60
|
||||||
device: b200-k8s
|
device: b200-k8s
|
||||||
optional: true
|
optional: true
|
||||||
@@ -411,8 +422,6 @@ steps:
|
|||||||
- vllm/model_executor/models/qwen3_next_mtp.py
|
- vllm/model_executor/models/qwen3_next_mtp.py
|
||||||
- vllm/model_executor/models/nemotron_h.py
|
- vllm/model_executor/models/nemotron_h.py
|
||||||
- vllm/model_executor/models/nemotron_h_mtp.py
|
- vllm/model_executor/models/nemotron_h_mtp.py
|
||||||
- vllm/transformers_utils/configs/qwen3_next.py
|
|
||||||
- vllm/transformers_utils/configs/nemotron_h.py
|
|
||||||
- vllm/model_executor/model_loader/
|
- vllm/model_executor/model_loader/
|
||||||
- vllm/model_executor/layers/quantization/
|
- vllm/model_executor/layers/quantization/
|
||||||
- vllm/model_executor/layers/fused_moe/
|
- vllm/model_executor/layers/fused_moe/
|
||||||
@@ -439,8 +448,6 @@ steps:
|
|||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- vllm/model_executor/models/qwen3_5.py
|
- vllm/model_executor/models/qwen3_5.py
|
||||||
- vllm/model_executor/models/qwen3_5_mtp.py
|
- vllm/model_executor/models/qwen3_5_mtp.py
|
||||||
- vllm/transformers_utils/configs/qwen3_5.py
|
|
||||||
- vllm/transformers_utils/configs/qwen3_5_moe.py
|
|
||||||
- vllm/model_executor/models/qwen3_next.py
|
- vllm/model_executor/models/qwen3_next.py
|
||||||
- vllm/model_executor/models/qwen3_next_mtp.py
|
- vllm/model_executor/models/qwen3_next_mtp.py
|
||||||
- vllm/third_party/flash_linear_attention/ops/
|
- vllm/third_party/flash_linear_attention/ops/
|
||||||
@@ -457,8 +464,6 @@ steps:
|
|||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- vllm/model_executor/models/qwen3_5.py
|
- vllm/model_executor/models/qwen3_5.py
|
||||||
- vllm/model_executor/models/qwen3_5_mtp.py
|
- vllm/model_executor/models/qwen3_5_mtp.py
|
||||||
- vllm/transformers_utils/configs/qwen3_5.py
|
|
||||||
- vllm/transformers_utils/configs/qwen3_5_moe.py
|
|
||||||
- vllm/model_executor/models/qwen2.py
|
- vllm/model_executor/models/qwen2.py
|
||||||
- vllm/model_executor/models/qwen3.py
|
- vllm/model_executor/models/qwen3.py
|
||||||
- vllm/model_executor/models/qwen3_next.py
|
- vllm/model_executor/models/qwen3_next.py
|
||||||
@@ -516,6 +521,7 @@ steps:
|
|||||||
- vllm/v1/spec_decode/
|
- vllm/v1/spec_decode/
|
||||||
- vllm/v1/worker/gpu/spec_decode/
|
- vllm/v1/worker/gpu/spec_decode/
|
||||||
- vllm/v1/core/kv_cache_utils.py
|
- vllm/v1/core/kv_cache_utils.py
|
||||||
|
- vllm/v1/core/kv_cache_planning.py
|
||||||
- vllm/model_executor/layers/layernorm.py
|
- vllm/model_executor/layers/layernorm.py
|
||||||
- csrc/
|
- csrc/
|
||||||
- vllm/_aiter_ops.py
|
- vllm/_aiter_ops.py
|
||||||
@@ -559,6 +565,7 @@ steps:
|
|||||||
- vllm/v1/spec_decode/
|
- vllm/v1/spec_decode/
|
||||||
- vllm/v1/worker/gpu/spec_decode/
|
- vllm/v1/worker/gpu/spec_decode/
|
||||||
- vllm/v1/core/kv_cache_utils.py
|
- vllm/v1/core/kv_cache_utils.py
|
||||||
|
- vllm/v1/core/kv_cache_planning.py
|
||||||
- vllm/model_executor/layers/layernorm.py
|
- vllm/model_executor/layers/layernorm.py
|
||||||
- csrc/
|
- csrc/
|
||||||
- vllm/_aiter_ops.py
|
- vllm/_aiter_ops.py
|
||||||
@@ -602,6 +609,7 @@ steps:
|
|||||||
- vllm/v1/spec_decode/
|
- vllm/v1/spec_decode/
|
||||||
- vllm/v1/worker/gpu/spec_decode/
|
- vllm/v1/worker/gpu/spec_decode/
|
||||||
- vllm/v1/core/kv_cache_utils.py
|
- vllm/v1/core/kv_cache_utils.py
|
||||||
|
- vllm/v1/core/kv_cache_planning.py
|
||||||
- vllm/model_executor/layers/layernorm.py
|
- vllm/model_executor/layers/layernorm.py
|
||||||
- csrc/
|
- csrc/
|
||||||
- vllm/_aiter_ops.py
|
- vllm/_aiter_ops.py
|
||||||
@@ -645,6 +653,7 @@ steps:
|
|||||||
- vllm/v1/spec_decode/
|
- vllm/v1/spec_decode/
|
||||||
- vllm/v1/worker/gpu/spec_decode/
|
- vllm/v1/worker/gpu/spec_decode/
|
||||||
- vllm/v1/core/kv_cache_utils.py
|
- vllm/v1/core/kv_cache_utils.py
|
||||||
|
- vllm/v1/core/kv_cache_planning.py
|
||||||
- vllm/model_executor/layers/layernorm.py
|
- vllm/model_executor/layers/layernorm.py
|
||||||
- csrc/
|
- csrc/
|
||||||
- vllm/_aiter_ops.py
|
- vllm/_aiter_ops.py
|
||||||
@@ -688,6 +697,7 @@ steps:
|
|||||||
- vllm/v1/spec_decode/
|
- vllm/v1/spec_decode/
|
||||||
- vllm/v1/worker/gpu/spec_decode/
|
- vllm/v1/worker/gpu/spec_decode/
|
||||||
- vllm/v1/core/kv_cache_utils.py
|
- vllm/v1/core/kv_cache_utils.py
|
||||||
|
- vllm/v1/core/kv_cache_planning.py
|
||||||
- vllm/model_executor/layers/layernorm.py
|
- vllm/model_executor/layers/layernorm.py
|
||||||
- csrc/
|
- csrc/
|
||||||
- vllm/_aiter_ops.py
|
- vllm/_aiter_ops.py
|
||||||
@@ -697,18 +707,17 @@ steps:
|
|||||||
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
||||||
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-mi355-nemotron-3-super.txt
|
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-mi355-nemotron-3-super.txt
|
||||||
|
|
||||||
- label: ":amd: (MI300) LM Eval Large Models"
|
- label: ":amd: (MI355) LM Eval Large Models"
|
||||||
key: amd-lm-eval-large-models
|
key: amd-lm-eval-large-models
|
||||||
dind: false
|
dind: false
|
||||||
device: mi300_8
|
device: mi355_8
|
||||||
optional: true
|
optional: true
|
||||||
timeout_in_minutes: 65
|
timeout_in_minutes: 65
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-amd
|
- image-build-amd
|
||||||
commands:
|
commands:
|
||||||
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
||||||
- export PYTORCH_ROCM_ARCH=gfx942 # Limit Quark compilation to save time
|
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-gfx950-large.txt
|
||||||
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-mi3xx.txt
|
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- vllm/_aiter_ops.py
|
- vllm/_aiter_ops.py
|
||||||
- vllm/platforms/rocm.py
|
- vllm/platforms/rocm.py
|
||||||
@@ -1185,7 +1194,7 @@ steps:
|
|||||||
optional: true
|
optional: true
|
||||||
num_devices: 4
|
num_devices: 4
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- csrc/libtorch_stable/gdn/
|
- csrc/gdn/
|
||||||
- tests/evals/qwen4_exp/
|
- tests/evals/qwen4_exp/
|
||||||
- vllm/model_executor/layers/mamba/
|
- vllm/model_executor/layers/mamba/
|
||||||
- vllm/models/qwen4_exp/
|
- vllm/models/qwen4_exp/
|
||||||
@@ -1203,7 +1212,7 @@ steps:
|
|||||||
optional: true
|
optional: true
|
||||||
num_devices: 4
|
num_devices: 4
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- csrc/libtorch_stable/gdn/
|
- csrc/gdn/
|
||||||
- tests/evals/qwen4_exp/
|
- tests/evals/qwen4_exp/
|
||||||
- vllm/model_executor/layers/mamba/
|
- vllm/model_executor/layers/mamba/
|
||||||
- vllm/models/qwen4_exp/
|
- vllm/models/qwen4_exp/
|
||||||
@@ -1224,7 +1233,7 @@ steps:
|
|||||||
depends_on:
|
depends_on:
|
||||||
- image-build-amd
|
- image-build-amd
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- csrc/libtorch_stable/gdn/
|
- csrc/gdn/
|
||||||
- tests/evals/qwen4_exp/
|
- tests/evals/qwen4_exp/
|
||||||
- vllm/model_executor/layers/mamba/
|
- vllm/model_executor/layers/mamba/
|
||||||
- vllm/models/qwen4_exp/
|
- vllm/models/qwen4_exp/
|
||||||
@@ -1288,9 +1297,9 @@ steps:
|
|||||||
- pytest -s -v evals/gsm8k/test_gsm8k_offloading.py -k "nemotron-h-8b or gemma-4-e4b-it"
|
- pytest -s -v evals/gsm8k/test_gsm8k_offloading.py -k "nemotron-h-8b or gemma-4-e4b-it"
|
||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI300) LM Eval KV-Offload"
|
label: ":amd: (MI355 DPX) LM Eval KV-Offload"
|
||||||
dind: false
|
dind: false
|
||||||
device: mi300_1
|
device: mi355_dpx
|
||||||
timeout_in_minutes: 55
|
timeout_in_minutes: 55
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-amd
|
- image-build-amd
|
||||||
@@ -1335,6 +1344,8 @@ steps:
|
|||||||
|
|
||||||
- label: ":nvidia: (H100) LM Eval KV-Offload Large"
|
- label: ":nvidia: (H100) LM Eval KV-Offload Large"
|
||||||
key: kv-offload-large
|
key: kv-offload-large
|
||||||
|
# Nightly only: 4-GPU H100 pods wait behind smaller jobs on per-PR runs.
|
||||||
|
optional: true
|
||||||
timeout_in_minutes: 40
|
timeout_in_minutes: 40
|
||||||
device: h100
|
device: h100
|
||||||
num_devices: 4
|
num_devices: 4
|
||||||
@@ -1348,9 +1359,9 @@ steps:
|
|||||||
- pytest -s -v evals/gsm8k/test_gsm8k_offloading.py -k "deepseek-v4-flash"
|
- pytest -s -v evals/gsm8k/test_gsm8k_offloading.py -k "deepseek-v4-flash"
|
||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI300) LM Eval KV-Offload Large"
|
label: ":amd: (MI355) LM Eval KV-Offload Large"
|
||||||
dind: false
|
dind: false
|
||||||
device: mi300_4
|
device: mi355_4
|
||||||
timeout_in_minutes: 65
|
timeout_in_minutes: 65
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-amd
|
- image-build-amd
|
||||||
@@ -1415,10 +1426,10 @@ steps:
|
|||||||
# Qwen2-57B has 28 attention heads and cannot run at TP8.
|
# Qwen2-57B has 28 attention heads and cannot run at TP8.
|
||||||
- pytest -s -v test_lm_eval_correctness.py --config-list-file=configs/models-large.txt --tp-size=4
|
- pytest -s -v test_lm_eval_correctness.py --config-list-file=configs/models-large.txt --tp-size=4
|
||||||
|
|
||||||
- label: ":amd: (MI300) LM Eval Large Models ROCm Harness"
|
- label: ":amd: (MI355) LM Eval Large Models ROCm Harness"
|
||||||
key: amd-lm-eval-large-models-rocm-harness
|
key: amd-lm-eval-large-models-rocm-harness
|
||||||
dind: false
|
dind: false
|
||||||
device: mi300_8
|
device: mi355_8
|
||||||
optional: true
|
optional: true
|
||||||
timeout_in_minutes: 40
|
timeout_in_minutes: 40
|
||||||
depends_on:
|
depends_on:
|
||||||
|
|||||||
@@ -4,7 +4,8 @@ depends_on:
|
|||||||
steps:
|
steps:
|
||||||
- label: ":nvidia: (H200 MIG 18GB) V1 Sample"
|
- label: ":nvidia: (H200 MIG 18GB) V1 Sample"
|
||||||
key: v1-sample
|
key: v1-sample
|
||||||
timeout_in_minutes: 35
|
automatic_shard: true
|
||||||
|
timeout_in_minutes: 45
|
||||||
device: h200_18gb
|
device: h200_18gb
|
||||||
source_file_dependencies: &v1-sample-logits-deps
|
source_file_dependencies: &v1-sample-logits-deps
|
||||||
- vllm/config/
|
- vllm/config/
|
||||||
@@ -31,6 +32,7 @@ steps:
|
|||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI355 DPX) V1 Sample"
|
label: ":amd: (MI355 DPX) V1 Sample"
|
||||||
dind: false
|
dind: false
|
||||||
|
automatic_shard: true
|
||||||
device: mi355_dpx
|
device: mi355_dpx
|
||||||
timeout_in_minutes: 70
|
timeout_in_minutes: 70
|
||||||
depends_on:
|
depends_on:
|
||||||
@@ -38,7 +40,7 @@ steps:
|
|||||||
|
|
||||||
- label: ":nvidia: (H200 MIG 18GB) V1 Logits + Oracle"
|
- label: ":nvidia: (H200 MIG 18GB) V1 Logits + Oracle"
|
||||||
key: v1-logits-oracle
|
key: v1-logits-oracle
|
||||||
timeout_in_minutes: 35
|
timeout_in_minutes: 45
|
||||||
device: h200_18gb
|
device: h200_18gb
|
||||||
source_file_dependencies: *v1-sample-logits-deps
|
source_file_dependencies: *v1-sample-logits-deps
|
||||||
commands:
|
commands:
|
||||||
@@ -162,6 +164,59 @@ steps:
|
|||||||
depends_on:
|
depends_on:
|
||||||
- image-build-amd
|
- image-build-amd
|
||||||
|
|
||||||
|
# The shared KV Connectors steps above exclude vllm/distributed/kv_transfer/ from
|
||||||
|
# their triggers, and CUDA skips MoRIIO's mori/aiter-gated tests. Run the whole
|
||||||
|
# MoRIIO suite on ROCm whenever the connector or its tests change.
|
||||||
|
- label: ":amd: (MI355 DPX) MoRIIO Connector Unit Tests"
|
||||||
|
key: amd-moriio-connector-unit-mi355
|
||||||
|
dind: false
|
||||||
|
device: mi355_dpx
|
||||||
|
num_devices: 1
|
||||||
|
timeout_in_minutes: 30
|
||||||
|
working_dir: /vllm-workspace/tests
|
||||||
|
depends_on:
|
||||||
|
- image-build-amd
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/distributed/kv_transfer/kv_connector/v1/moriio/
|
||||||
|
- vllm/distributed/kv_transfer/kv_connector/v1/base.py
|
||||||
|
- vllm/distributed/kv_transfer/kv_connector/v1/ssm_conv_transfer_utils.py
|
||||||
|
- examples/disaggregated/disaggregated_serving/moriio_toy_proxy_server.py
|
||||||
|
- tests/v1/kv_connector/unit/test_moriio_
|
||||||
|
- tests/v1/kv_connector/unit/utils.py
|
||||||
|
- requirements/kv_connectors_rocm.txt
|
||||||
|
commands:
|
||||||
|
- bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh
|
||||||
|
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
||||||
|
- pytest -v -s -rs v1/kv_connector/unit/test_moriio_*.py
|
||||||
|
|
||||||
|
# Single-node MoRIIO WRITE P/D on dummy weights: prefill and decode on separate
|
||||||
|
# GPUs over xGMI, compared exactly against a direct serve.
|
||||||
|
- label: ":amd: (MI355) MoRIIO WRITE P/D Dummy-Weight E2E Shard %N"
|
||||||
|
key: amd-moriio-write-dummy-e2e-mi355
|
||||||
|
dind: false
|
||||||
|
device: mi355_2
|
||||||
|
num_devices: 2
|
||||||
|
# ~3.5-5 min per case; pytest-shard hashes test ids, so with 20 cases the
|
||||||
|
# largest of 6 shards holds 5 (~22 min on MI355). Every case picks free ports
|
||||||
|
# for its servers and proxy and its own compile-cache dir.
|
||||||
|
parallelism: 6
|
||||||
|
timeout_in_minutes: 45
|
||||||
|
working_dir: /vllm-workspace/tests
|
||||||
|
depends_on:
|
||||||
|
- image-build-amd
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/distributed/kv_transfer/kv_connector/v1/moriio/
|
||||||
|
- vllm/distributed/kv_transfer/kv_connector/v1/base.py
|
||||||
|
- vllm/distributed/kv_transfer/kv_connector/v1/ssm_conv_transfer_utils.py
|
||||||
|
- vllm/model_executor/model_loader/dummy_loader.py
|
||||||
|
- examples/disaggregated/disaggregated_serving/moriio_toy_proxy_server.py
|
||||||
|
- tests/v1/kv_connector/moriio_integration/
|
||||||
|
- requirements/kv_connectors_rocm.txt
|
||||||
|
commands:
|
||||||
|
- bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh
|
||||||
|
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
||||||
|
- pytest -v -s -rs v1/kv_connector/moriio_integration/test_write_dummy_e2e_rocm.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
|
||||||
|
|
||||||
- label: ":nvidia: (H200 MIG 35GB) V1 Metrics + LM Eval"
|
- label: ":nvidia: (H200 MIG 35GB) V1 Metrics + LM Eval"
|
||||||
device: h200_35gb
|
device: h200_35gb
|
||||||
key: v1-metrics-lmeval
|
key: v1-metrics-lmeval
|
||||||
@@ -212,12 +267,14 @@ steps:
|
|||||||
- vllm/v1/
|
- vllm/v1/
|
||||||
- tests/v1
|
- tests/v1
|
||||||
- tests/watermarking
|
- tests/watermarking
|
||||||
|
- examples/disaggregated/mooncake_connector/mooncake_connector_proxy.py
|
||||||
device: cpu-small
|
device: cpu-small
|
||||||
commands:
|
commands:
|
||||||
# split the test to avoid interference
|
# split the test to avoid interference
|
||||||
- pytest -v -s -m 'cpu_test' v1/core
|
- pytest -v -s -m 'cpu_test' v1/core
|
||||||
- pytest -v -s v1/structured_output
|
- pytest -v -s v1/structured_output
|
||||||
- pytest -v -s v1/test_serial_utils.py
|
- pytest -v -s v1/test_serial_utils.py
|
||||||
|
- pytest -v -s v1/worker/test_cpu_worker_kv_budget.py
|
||||||
- pytest -v -s v1/test_kv_cache_spec_registry.py
|
- pytest -v -s v1/test_kv_cache_spec_registry.py
|
||||||
- pytest -v -s v1/cudagraph/test_cudagraph_manager.py
|
- pytest -v -s v1/cudagraph/test_cudagraph_manager.py
|
||||||
- pytest -v -s -m 'cpu_test' v1/kv_connector/unit
|
- pytest -v -s -m 'cpu_test' v1/kv_connector/unit
|
||||||
@@ -296,7 +353,6 @@ steps:
|
|||||||
- vllm/model_executor/models/qwen3_next.py
|
- vllm/model_executor/models/qwen3_next.py
|
||||||
- vllm/model_executor/models/registry.py
|
- vllm/model_executor/models/registry.py
|
||||||
- vllm/transformers_utils/configs/extract_hidden_states.py
|
- vllm/transformers_utils/configs/extract_hidden_states.py
|
||||||
- vllm/transformers_utils/configs/qwen3_5.py
|
|
||||||
- vllm/v1/attention/backends/
|
- vllm/v1/attention/backends/
|
||||||
- vllm/v1/attention/selector.py
|
- vllm/v1/attention/selector.py
|
||||||
- vllm/v1/kv_cache_interface.py
|
- vllm/v1/kv_cache_interface.py
|
||||||
@@ -446,6 +502,17 @@ steps:
|
|||||||
- setup.py
|
- setup.py
|
||||||
- vllm/platforms/rocm.py
|
- vllm/platforms/rocm.py
|
||||||
|
|
||||||
|
- label: ":nvidia: (H200 MIG 18GB) Python 3.14 Smoke Nightly"
|
||||||
|
key: python-314-smoke-nightly
|
||||||
|
depends_on: ~
|
||||||
|
optional: true
|
||||||
|
timeout_in_minutes: 30
|
||||||
|
device: h200_18gb
|
||||||
|
source_file_dependencies:
|
||||||
|
- tests/standalone_tests/python_only_compile.sh
|
||||||
|
commands:
|
||||||
|
- PYTHON_ONLY_COMPILE_PYTHON=3.14 bash standalone_tests/python_only_compile.sh
|
||||||
|
|
||||||
- label: ":nvidia: (H200 MIG 35GB) Async Engine, Inputs, Utils, Worker"
|
- label: ":nvidia: (H200 MIG 35GB) Async Engine, Inputs, Utils, Worker"
|
||||||
device: h200_35gb
|
device: h200_35gb
|
||||||
key: async-engine-inputs-utils-worker
|
key: async-engine-inputs-utils-worker
|
||||||
@@ -556,6 +623,8 @@ steps:
|
|||||||
- tests/multimodal
|
- tests/multimodal
|
||||||
- tests/renderers
|
- tests/renderers
|
||||||
- tests/standalone_tests/lazy_imports.py
|
- tests/standalone_tests/lazy_imports.py
|
||||||
|
- tests/standalone_tests/test_precompiled_wheel.py
|
||||||
|
- setup.py
|
||||||
- tests/reasoning
|
- tests/reasoning
|
||||||
- tools/pre_commit/check_test_tethering.py
|
- tools/pre_commit/check_test_tethering.py
|
||||||
- tools/pre_commit/test_tethering_allowlist.txt
|
- tools/pre_commit/test_tethering_allowlist.txt
|
||||||
@@ -572,6 +641,7 @@ steps:
|
|||||||
commands:
|
commands:
|
||||||
- pip install cmake # test_cmake_utils.py shells out to cmake; the CPU image has none
|
- pip install cmake # test_cmake_utils.py shells out to cmake; the CPU image has none
|
||||||
- python3 standalone_tests/lazy_imports.py
|
- python3 standalone_tests/lazy_imports.py
|
||||||
|
- python3 standalone_tests/test_precompiled_wheel.py
|
||||||
- pytest -v -s device_allocator
|
- pytest -v -s device_allocator
|
||||||
- pytest -v -s test_uvicorn_logging.py
|
- pytest -v -s test_uvicorn_logging.py
|
||||||
- pytest -v -s test_attention_backend_registry.py
|
- pytest -v -s test_attention_backend_registry.py
|
||||||
@@ -641,21 +711,45 @@ steps:
|
|||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- vllm/v1/attention
|
- vllm/v1/attention
|
||||||
- vllm/model_executor/layers
|
- vllm/model_executor/layers
|
||||||
|
- vllm/model_executor/kernels/linear
|
||||||
|
- vllm/model_executor/determinism
|
||||||
- tests/v1/determinism/
|
- tests/v1/determinism/
|
||||||
commands:
|
commands:
|
||||||
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
||||||
- pip install pytest-timeout pytest-forked
|
- pip install pytest-timeout pytest-forked
|
||||||
- pytest -v -s v1/determinism/test_batch_invariance.py
|
- pytest -v -s v1/determinism/test_batch_invariance.py
|
||||||
- VLLM_TEST_MODEL=deepseek-ai/DeepSeek-V2-Lite-Chat pytest -v -s v1/determinism/test_batch_invariance.py::test_v1_generation_is_deterministic_across_batch_sizes_with_needle -k TRITON_MLA
|
- VLLM_TEST_MODEL=deepseek-ai/DeepSeek-V2-Lite-Chat pytest -v -s v1/determinism/test_batch_invariance.py::test_v1_generation_is_deterministic_across_batch_sizes_with_needle -k TRITON_MLA
|
||||||
|
mirror:
|
||||||
|
amd:
|
||||||
|
label: ":amd: (MI250) Batch Invariance"
|
||||||
|
dind: false
|
||||||
|
device: mi250_1
|
||||||
|
timeout_in_minutes: 60
|
||||||
|
env:
|
||||||
|
VLLM_GPU_MEMORY_UTILIZATION: "0.8"
|
||||||
|
VLLM_TEST_CLEAN_GPU_MEMORY: "1"
|
||||||
|
depends_on:
|
||||||
|
- image-build-amd
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/v1/attention
|
||||||
|
- vllm/model_executor/layers
|
||||||
|
- vllm/model_executor/kernels/linear
|
||||||
|
- vllm/model_executor/determinism
|
||||||
|
- tests/v1/determinism/
|
||||||
|
- vllm/_aiter_ops.py
|
||||||
|
- vllm/platforms/rocm.py
|
||||||
|
|
||||||
- label: ":nvidia: (H100) Batch Invariance"
|
- label: ":nvidia: (H100) Batch Invariance"
|
||||||
key: batch-invariance-h100
|
key: batch-invariance-h100
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 60
|
timeout_in_minutes: 60
|
||||||
device: h100
|
device: h100
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- vllm/v1/attention
|
- vllm/v1/attention
|
||||||
- vllm/model_executor/layers
|
- vllm/model_executor/layers
|
||||||
- vllm/lora/ops/triton_ops
|
- vllm/lora/ops/triton_ops
|
||||||
|
- vllm/model_executor/kernels/linear
|
||||||
|
- vllm/model_executor/determinism
|
||||||
- tests/v1/determinism/
|
- tests/v1/determinism/
|
||||||
commands:
|
commands:
|
||||||
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
||||||
@@ -667,15 +761,19 @@ steps:
|
|||||||
- VLLM_TEST_MODEL=Qwen/Qwen3-30B-A3B-Thinking-2507-FP8 pytest -v -s v1/determinism/test_batch_invariance.py::test_v1_generation_is_deterministic_across_batch_sizes_with_needle -k FLASH_ATTN
|
- VLLM_TEST_MODEL=Qwen/Qwen3-30B-A3B-Thinking-2507-FP8 pytest -v -s v1/determinism/test_batch_invariance.py::test_v1_generation_is_deterministic_across_batch_sizes_with_needle -k FLASH_ATTN
|
||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI250) Batch Invariance"
|
label: ":amd: (MI300) Batch Invariance"
|
||||||
dind: false
|
dind: false
|
||||||
device: mi250_1
|
automatic_shard: true
|
||||||
timeout_in_minutes: 35
|
device: mi300_1
|
||||||
|
timeout_in_minutes: 60
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-amd
|
- image-build-amd
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- vllm/v1/attention
|
- vllm/v1/attention
|
||||||
- vllm/model_executor/layers
|
- vllm/model_executor/layers
|
||||||
|
- vllm/lora/ops/triton_ops
|
||||||
|
- vllm/model_executor/kernels/linear
|
||||||
|
- vllm/model_executor/determinism
|
||||||
- tests/v1/determinism/
|
- tests/v1/determinism/
|
||||||
- vllm/_aiter_ops.py
|
- vllm/_aiter_ops.py
|
||||||
- vllm/platforms/rocm.py
|
- vllm/platforms/rocm.py
|
||||||
@@ -684,15 +782,23 @@ steps:
|
|||||||
- pip install pytest-timeout pytest-forked
|
- pip install pytest-timeout pytest-forked
|
||||||
- pytest -v -s v1/determinism/test_batch_invariance.py
|
- pytest -v -s v1/determinism/test_batch_invariance.py
|
||||||
- pytest -v -s v1/determinism/test_rms_norm_batch_invariant.py
|
- pytest -v -s v1/determinism/test_rms_norm_batch_invariant.py
|
||||||
|
- pytest -v -s v1/determinism/test_lora_shrink_batch_invariant.py
|
||||||
|
- pytest -v -s v1/determinism/test_cutlass_batch_invariance.py
|
||||||
|
- pytest -v -s v1/determinism/test_matmul_batch_invariant.py
|
||||||
|
- VLLM_TEST_MODEL=deepseek-ai/DeepSeek-V2-Lite-Chat pytest -v -s v1/determinism/test_batch_invariance.py::test_v1_generation_is_deterministic_across_batch_sizes_with_needle -k TRITON_MLA
|
||||||
|
- VLLM_TEST_MODEL=Qwen/Qwen3-30B-A3B-Thinking-2507-FP8 pytest -v -s v1/determinism/test_batch_invariance.py::test_v1_generation_is_deterministic_across_batch_sizes_with_needle -k TRITON_ATTN
|
||||||
|
|
||||||
- label: ":nvidia: (B200) Batch Invariance"
|
- label: ":nvidia: (B200) Batch Invariance"
|
||||||
key: batch-invariance-b200
|
key: batch-invariance-b200
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 45
|
timeout_in_minutes: 45
|
||||||
device: b200-k8s
|
device: b200-k8s
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- vllm/v1/attention
|
- vllm/v1/attention
|
||||||
- vllm/model_executor/layers
|
- vllm/model_executor/layers
|
||||||
- vllm/lora/ops/triton_ops
|
- vllm/lora/ops/triton_ops
|
||||||
|
- vllm/model_executor/kernels/linear
|
||||||
|
- vllm/model_executor/determinism
|
||||||
- tests/v1/determinism/
|
- tests/v1/determinism/
|
||||||
commands:
|
commands:
|
||||||
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
||||||
@@ -707,6 +813,80 @@ steps:
|
|||||||
- pytest -v -s v1/determinism/test_matmul_batch_invariant.py
|
- pytest -v -s v1/determinism/test_matmul_batch_invariant.py
|
||||||
- pytest -v -s v1/determinism/test_cutlass_batch_invariance.py
|
- pytest -v -s v1/determinism/test_cutlass_batch_invariance.py
|
||||||
- pytest -v -s v1/determinism/test_online_batch_invariance.py
|
- pytest -v -s v1/determinism/test_online_batch_invariance.py
|
||||||
|
mirror:
|
||||||
|
amd:
|
||||||
|
label: ":amd: (MI355) Batch Invariance"
|
||||||
|
dind: false
|
||||||
|
device: mi355_1
|
||||||
|
timeout_in_minutes: 60
|
||||||
|
depends_on:
|
||||||
|
- image-build-amd
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/v1/attention
|
||||||
|
- vllm/model_executor/layers
|
||||||
|
- vllm/lora/ops/triton_ops
|
||||||
|
- vllm/model_executor/kernels/linear
|
||||||
|
- vllm/model_executor/determinism
|
||||||
|
- tests/v1/determinism/
|
||||||
|
- vllm/_aiter_ops.py
|
||||||
|
- vllm/platforms/rocm.py
|
||||||
|
commands:
|
||||||
|
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
||||||
|
- pip install pytest-timeout pytest-forked
|
||||||
|
- pytest -v -s v1/determinism/test_batch_invariance.py
|
||||||
|
- pytest -v -s v1/determinism/test_rms_norm_batch_invariant.py
|
||||||
|
- pytest -v -s v1/determinism/test_lora_shrink_batch_invariant.py
|
||||||
|
- pytest -v -s v1/determinism/test_batch_invariance_vlm.py
|
||||||
|
- VLLM_TEST_MODEL=deepseek-ai/DeepSeek-V2-Lite-Chat pytest -v -s v1/determinism/test_batch_invariance.py::test_v1_generation_is_deterministic_across_batch_sizes_with_needle -k TRITON_MLA
|
||||||
|
- VLLM_TEST_MODEL=Qwen/Qwen3-30B-A3B-Thinking-2507-FP8 pytest -v -s v1/determinism/test_batch_invariance.py::test_v1_generation_is_deterministic_across_batch_sizes_with_needle -k TRITON_ATTN
|
||||||
|
- pytest -v -s v1/determinism/test_nvfp4_batch_invariant.py
|
||||||
|
- pytest -v -s v1/determinism/test_matmul_batch_invariant.py
|
||||||
|
- pytest -v -s v1/determinism/test_cutlass_batch_invariance.py
|
||||||
|
- pytest -v -s v1/determinism/test_online_batch_invariance.py
|
||||||
|
- pytest -v -s v1/determinism/test_mx_linear_batch_invariant.py
|
||||||
|
|
||||||
|
- label: ":nvidia: (H100) Batch Invariance (Distributed)"
|
||||||
|
key: batch-invariance-distributed-4xh100
|
||||||
|
automatic_shard: true
|
||||||
|
timeout_in_minutes: 45
|
||||||
|
device: h100
|
||||||
|
optional: true
|
||||||
|
num_devices: 4
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/distributed/device_communicators/
|
||||||
|
- vllm/model_executor/determinism
|
||||||
|
- vllm/model_executor/layers
|
||||||
|
- vllm/v1/attention
|
||||||
|
- tests/v1/determinism/
|
||||||
|
commands:
|
||||||
|
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
||||||
|
- export VLLM_TEST_CLEAN_GPU_MEMORY=1
|
||||||
|
- VLLM_TEST_TP_SIZE=4 pytest -v -s v1/determinism/test_batch_invariance.py -k "bs1_vs_bsN or without_batch_invariance_should_fail"
|
||||||
|
- VLLM_TEST_TP_SIZE=4 VLLM_TEST_DISABLE_CUSTOM_AR=1 pytest -v -s v1/determinism/test_batch_invariance.py -k bs1_vs_bsN
|
||||||
|
- VLLM_TP_SIZE=4 VLLM_NEEDLE_TRIALS=2 pytest -v -s v1/determinism/test_batch_invariance.py::test_v1_generation_is_deterministic_across_batch_sizes_with_needle -k FLASH_ATTN
|
||||||
|
- VLLM_TEST_MODEL=allenai/OLMoE-1B-7B-0924 VLLM_TEST_SERVER_ARGS="--data-parallel-size 4 --enable-expert-parallel --max-model-len 4096" pytest -v -s v1/determinism/test_online_batch_invariance.py
|
||||||
|
mirror:
|
||||||
|
amd:
|
||||||
|
label: ":amd: (MI300) Batch Invariance (Distributed)"
|
||||||
|
dind: false
|
||||||
|
device: mi300_4
|
||||||
|
timeout_in_minutes: 45
|
||||||
|
depends_on:
|
||||||
|
- image-build-amd
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/distributed/device_communicators/
|
||||||
|
- vllm/model_executor/determinism
|
||||||
|
- vllm/model_executor/layers
|
||||||
|
- vllm/v1/attention
|
||||||
|
- tests/v1/determinism/
|
||||||
|
- vllm/platforms/rocm.py
|
||||||
|
commands:
|
||||||
|
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
||||||
|
- export VLLM_TEST_CLEAN_GPU_MEMORY=1
|
||||||
|
- VLLM_TEST_TP_SIZE=4 pytest -v -s v1/determinism/test_batch_invariance.py -k "bs1_vs_bsN or without_batch_invariance_should_fail"
|
||||||
|
- VLLM_TEST_TP_SIZE=4 VLLM_TEST_DISABLE_CUSTOM_AR=1 pytest -v -s v1/determinism/test_batch_invariance.py -k bs1_vs_bsN
|
||||||
|
- VLLM_TP_SIZE=4 VLLM_NEEDLE_TRIALS=2 pytest -v -s v1/determinism/test_batch_invariance.py::test_v1_generation_is_deterministic_across_batch_sizes_with_needle -k TRITON_ATTN
|
||||||
|
- VLLM_TEST_MODEL=allenai/OLMoE-1B-7B-0924 VLLM_TEST_SERVER_ARGS="--data-parallel-size 4 --enable-expert-parallel --max-model-len 4096" pytest -v -s v1/determinism/test_online_batch_invariance.py
|
||||||
|
|
||||||
- label: ":nvidia: (H200 MIG 35GB) Acceptance Length (Large Models)"
|
- label: ":nvidia: (H200 MIG 35GB) Acceptance Length (Large Models)"
|
||||||
device: h200_35gb
|
device: h200_35gb
|
||||||
@@ -718,7 +898,6 @@ steps:
|
|||||||
working_dir: "/vllm-workspace/tests"
|
working_dir: "/vllm-workspace/tests"
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- vllm/v1/spec_decode/
|
- vllm/v1/spec_decode/
|
||||||
- vllm/model_executor/models/mlp_speculator.py
|
|
||||||
- tests/v1/spec_decode/test_acceptance_length.py
|
- tests/v1/spec_decode/test_acceptance_length.py
|
||||||
commands:
|
commands:
|
||||||
- export VLLM_ALLOW_INSECURE_SERIALIZATION=1
|
- export VLLM_ALLOW_INSECURE_SERIALIZATION=1
|
||||||
@@ -734,6 +913,5 @@ steps:
|
|||||||
working_dir: /vllm-workspace/tests
|
working_dir: /vllm-workspace/tests
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- vllm/v1/spec_decode/
|
- vllm/v1/spec_decode/
|
||||||
- vllm/model_executor/models/mlp_speculator.py
|
|
||||||
- tests/v1/spec_decode/test_acceptance_length.py
|
- tests/v1/spec_decode/test_acceptance_length.py
|
||||||
- vllm/platforms/rocm.py
|
- vllm/platforms/rocm.py
|
||||||
|
|||||||
@@ -5,6 +5,7 @@ steps:
|
|||||||
- label: ":nvidia: (H200 MIG 35GB) Model Executor"
|
- label: ":nvidia: (H200 MIG 35GB) Model Executor"
|
||||||
device: h200_35gb
|
device: h200_35gb
|
||||||
key: model-executor
|
key: model-executor
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 60
|
timeout_in_minutes: 60
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- vllm/engine/arg_utils.py
|
- vllm/engine/arg_utils.py
|
||||||
|
|||||||
@@ -58,6 +58,7 @@ steps:
|
|||||||
- label: ":nvidia: (H200 MIG 35GB) Basic Models (Other)"
|
- label: ":nvidia: (H200 MIG 35GB) Basic Models (Other)"
|
||||||
device: h200_35gb
|
device: h200_35gb
|
||||||
key: basic-models-tests-other
|
key: basic-models-tests-other
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 38
|
timeout_in_minutes: 38
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- vllm/
|
- vllm/
|
||||||
@@ -68,8 +69,12 @@ steps:
|
|||||||
- tests/models/test_deepseek_v4_vl_rocm.py
|
- tests/models/test_deepseek_v4_vl_rocm.py
|
||||||
- tests/models/test_deepseek_v41_decoder_replay_layers.py
|
- tests/models/test_deepseek_v41_decoder_replay_layers.py
|
||||||
- tests/models/test_deepseek_v41_replay_batch.py
|
- tests/models/test_deepseek_v41_replay_batch.py
|
||||||
|
- tests/models/test_deepseek_v41_pcp.py
|
||||||
|
- tests/models/transformers/test_layer_registry_e2e.py
|
||||||
|
- tests/models/test_deepseek_v41_replay_start.py
|
||||||
|
- tests/models/test_deepseek_v4_vl_stream_weights.py
|
||||||
commands:
|
commands:
|
||||||
- pytest -v -s models/test_terratorch.py models/transformers/test_backend.py models/test_registry.py models/test_deepseek_v4_vl_rocm.py models/test_deepseek_v41_decoder_replay_layers.py models/test_deepseek_v41_replay_batch.py
|
- pytest -v -s models/test_terratorch.py models/transformers/test_backend.py models/test_registry.py models/test_deepseek_v4_vl_rocm.py models/transformers/test_layer_registry_e2e.py models/test_deepseek_v41_replay_start.py models/test_deepseek_v41_decoder_replay_layers.py models/test_deepseek_v41_replay_batch.py models/test_deepseek_v41_pcp.py models/test_deepseek_v4_vl_stream_weights.py
|
||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI355) Basic Models (Other)"
|
label: ":amd: (MI355) Basic Models (Other)"
|
||||||
@@ -79,10 +84,21 @@ steps:
|
|||||||
depends_on:
|
depends_on:
|
||||||
- image-build-amd
|
- image-build-amd
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
|
- vllm/models/deepseek_v4/
|
||||||
|
- vllm/models/deepseek_v41/
|
||||||
- tests/models/test_deepseek_v4_vl_rocm.py
|
- tests/models/test_deepseek_v4_vl_rocm.py
|
||||||
- tests/models/test_hyv4_rocm.py
|
- tests/models/test_hyv4_rocm.py
|
||||||
|
- tests/models/transformers/test_layer_registry_e2e.py
|
||||||
|
- tests/models/test_deepseek_v41_replay_start.py
|
||||||
|
- tests/models/test_deepseek_v41_decoder_replay_layers.py
|
||||||
|
- tests/models/test_deepseek_v41_replay_batch.py
|
||||||
|
- tests/models/test_deepseek_v41_amd_replay_forward.py
|
||||||
|
- tests/models/test_deepseek_v4_dspark_rocm.py
|
||||||
|
- tests/models/test_deepseek_v4_rocm_wo_a.py
|
||||||
|
- tests/models/test_deepseek_v4_rocm_compressor_gemm_fusion.py
|
||||||
|
- tests/models/test_dsv41_mono_decode.py
|
||||||
commands:
|
commands:
|
||||||
- pytest -v -s models/test_terratorch.py models/transformers/test_backend.py models/test_registry.py models/test_deepseek_v4_vl_rocm.py
|
- pytest -v -s models/test_terratorch.py models/transformers/test_backend.py models/test_registry.py models/test_deepseek_v4_vl_rocm.py models/transformers/test_layer_registry_e2e.py models/test_deepseek_v41_replay_start.py models/test_deepseek_v41_decoder_replay_layers.py models/test_deepseek_v41_replay_batch.py models/test_deepseek_v41_amd_replay_forward.py models/test_deepseek_v4_dspark_rocm.py models/test_deepseek_v4_rocm_wo_a.py models/test_deepseek_v4_rocm_compressor_gemm_fusion.py models/test_dsv41_mono_decode.py
|
||||||
- VLLM_ROCM_USE_AITER=1 pytest -v -s models/test_hyv4_rocm.py -m 'not distributed'
|
- VLLM_ROCM_USE_AITER=1 pytest -v -s models/test_hyv4_rocm.py -m 'not distributed'
|
||||||
|
|
||||||
- label: ":nvidia: (B200) Inkling"
|
- label: ":nvidia: (B200) Inkling"
|
||||||
@@ -121,7 +137,7 @@ steps:
|
|||||||
device: b200-k8s
|
device: b200-k8s
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- vllm/models/kimi_k3/
|
- vllm/models/kimi_k3/
|
||||||
- csrc/libtorch_stable/kimi_k3/
|
- csrc/kimi_k3/
|
||||||
- tests/models/kimi_k3/
|
- tests/models/kimi_k3/
|
||||||
- tests/kernels/attention/test_kimi_k3_mla_fused_epilogue.py
|
- tests/kernels/attention/test_kimi_k3_mla_fused_epilogue.py
|
||||||
commands:
|
commands:
|
||||||
@@ -145,8 +161,11 @@ steps:
|
|||||||
# cuda.bindings.driver), so it is deliberately left out here.
|
# cuda.bindings.driver), so it is deliberately left out here.
|
||||||
- pytest -v -s models/kimi_k3
|
- pytest -v -s models/kimi_k3
|
||||||
|
|
||||||
- label: ":nvidia: (4xB200) Kimi K3 Prefix Cache Shard %N"
|
- label: ":nvidia: (4xB200) Kimi K3 Prefix Cache"
|
||||||
key: kimi-k3-prefix-cache-4xb200
|
key: kimi-k3-prefix-cache-4xb200
|
||||||
|
# Nightly only: 4-GPU B200 pods wait hours behind smaller jobs on per-PR runs.
|
||||||
|
optional: true
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 75
|
timeout_in_minutes: 75
|
||||||
device: b200-k8s
|
device: b200-k8s
|
||||||
num_devices: 4
|
num_devices: 4
|
||||||
@@ -155,6 +174,8 @@ steps:
|
|||||||
- vllm/v1/core/
|
- vllm/v1/core/
|
||||||
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
|
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
|
||||||
- vllm/distributed/kv_transfer/kv_connector/v1/simple_cpu_offload_connector.py
|
- vllm/distributed/kv_transfer/kv_connector/v1/simple_cpu_offload_connector.py
|
||||||
|
- vllm/distributed/kv_transfer/kv_connector/v1/mooncake/store/
|
||||||
|
- vllm/distributed/mooncake_store.py
|
||||||
- vllm/v1/simple_kv_offload/
|
- vllm/v1/simple_kv_offload/
|
||||||
- vllm/v1/spec_decode/
|
- vllm/v1/spec_decode/
|
||||||
- vllm/model_executor/layers/mamba/
|
- vllm/model_executor/layers/mamba/
|
||||||
@@ -162,8 +183,7 @@ steps:
|
|||||||
- .buildkite/scripts/install-kv-connectors.sh
|
- .buildkite/scripts/install-kv-connectors.sh
|
||||||
commands:
|
commands:
|
||||||
- bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh
|
- bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh
|
||||||
- pytest -v -s models/kimi_k3/test_prefix_cache.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
|
- pytest -v -s models/kimi_k3/test_prefix_cache.py
|
||||||
parallelism: 2
|
|
||||||
|
|
||||||
- label: ":nvidia: (H200) GLM5Next"
|
- label: ":nvidia: (H200) GLM5Next"
|
||||||
key: glm5next-unit-tests
|
key: glm5next-unit-tests
|
||||||
@@ -192,12 +212,12 @@ steps:
|
|||||||
device: h200_35gb
|
device: h200_35gb
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- vllm/models/qwen4_exp/
|
- vllm/models/qwen4_exp/
|
||||||
- vllm/transformers_utils/configs/qwen4_exp.py
|
|
||||||
- vllm/config/compilation.py
|
- vllm/config/compilation.py
|
||||||
- vllm/v1/attention/backends/short_conv_attn.py
|
- vllm/v1/attention/backends/short_conv_attn.py
|
||||||
- tests/models/qwen4_exp/
|
- tests/models/qwen4_exp/
|
||||||
commands:
|
commands:
|
||||||
- pytest -v -s models/qwen4_exp/test_hc_ops.py models/qwen4_exp/test_qsa_prepare.py models/qwen4_exp/test_qsa_reference.py
|
- pytest -v -s models/qwen4_exp/test_hc_ops.py models/qwen4_exp/test_qsa_prepare.py models/qwen4_exp/test_qsa_reference.py
|
||||||
|
- pytest -v -s models/qwen4_exp/test_ple.py
|
||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI355 DPX) Qwen4 Exp"
|
label: ":amd: (MI355 DPX) Qwen4 Exp"
|
||||||
@@ -206,7 +226,7 @@ steps:
|
|||||||
depends_on:
|
depends_on:
|
||||||
- image-build-amd
|
- image-build-amd
|
||||||
commands:
|
commands:
|
||||||
- pytest -v -s models/qwen4_exp/test_qsa_amd.py
|
- pytest -v -s models/qwen4_exp/test_qsa_amd.py models/qwen4_exp/test_qsa_prepare_amd.py
|
||||||
# PLE and QSA import conflicting HC registrations in a shared process.
|
# PLE and QSA import conflicting HC registrations in a shared process.
|
||||||
- pytest -v -s models/qwen4_exp/test_ple.py
|
- pytest -v -s models/qwen4_exp/test_ple.py
|
||||||
|
|
||||||
@@ -218,7 +238,6 @@ steps:
|
|||||||
device: cpu-small
|
device: cpu-small
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- vllm/models/qwen4_exp/
|
- vllm/models/qwen4_exp/
|
||||||
- vllm/transformers_utils/configs/qwen4_exp.py
|
|
||||||
- vllm/config/compilation.py
|
- vllm/config/compilation.py
|
||||||
- vllm/v1/attention/backends/short_conv_attn.py
|
- vllm/v1/attention/backends/short_conv_attn.py
|
||||||
- tests/models/qwen4_exp/
|
- tests/models/qwen4_exp/
|
||||||
@@ -229,7 +248,7 @@ steps:
|
|||||||
key: basic-models-test-other-cpu
|
key: basic-models-test-other-cpu
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-cpu
|
- image-build-cpu
|
||||||
timeout_in_minutes: 20
|
timeout_in_minutes: 30
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- vllm/
|
- vllm/
|
||||||
- "!vllm/distributed/kv_transfer/"
|
- "!vllm/distributed/kv_transfer/"
|
||||||
@@ -237,8 +256,34 @@ steps:
|
|||||||
- tests/models/test_vision.py
|
- tests/models/test_vision.py
|
||||||
- tests/models/test_adapters.py
|
- tests/models/test_adapters.py
|
||||||
- tests/models/test_qwen3_5_mtp_config.py
|
- tests/models/test_qwen3_5_mtp_config.py
|
||||||
|
- tests/models/test_alice_ai.py
|
||||||
|
- tests/models/test_alice_ai_config.py
|
||||||
- tests/models/transformers/fusers/
|
- tests/models/transformers/fusers/
|
||||||
|
- tests/models/transformers/test_dynamic_rope.py
|
||||||
- tests/model_executor/layers/test_activation.py
|
- tests/model_executor/layers/test_activation.py
|
||||||
|
- tests/models/test_language_model_cache_is_weak.py
|
||||||
|
- tests/models/deepseek_v32/test_sequence_parallel.py
|
||||||
|
- tests/models/test_deepseek_v4_fi_moe_ep.py
|
||||||
|
- tests/models/test_dspark_mla.py
|
||||||
|
- tests/models/transformers/test_layer_registry.py
|
||||||
device: cpu-small
|
device: cpu-small
|
||||||
commands:
|
commands:
|
||||||
- pytest -v -s models/test_utils.py models/test_vision.py models/test_adapters.py models/test_qwen3_5_mtp_config.py models/transformers/fusers/ model_executor/layers/test_activation.py
|
- pytest -v -s models/test_utils.py models/test_vision.py models/test_adapters.py models/test_qwen3_5_mtp_config.py models/transformers/fusers/ models/transformers/test_dynamic_rope.py model_executor/layers/test_activation.py models/test_language_model_cache_is_weak.py models/deepseek_v32/test_sequence_parallel.py models/test_deepseek_v4_fi_moe_ep.py models/test_dspark_mla.py models/transformers/test_layer_registry.py models/test_alice_ai.py models/test_alice_ai_config.py
|
||||||
|
|
||||||
|
- label: ':amd: (MI355) DeepSeek-V4.1 Mono Decode Numerics'
|
||||||
|
key: dsv41-mono-decode-numerics-amd
|
||||||
|
dind: false
|
||||||
|
device: mi355_4
|
||||||
|
num_devices: 4
|
||||||
|
timeout_in_minutes: 40
|
||||||
|
working_dir: /vllm-workspace/
|
||||||
|
depends_on:
|
||||||
|
- image-build-amd
|
||||||
|
source_file_dependencies:
|
||||||
|
- docker/Dockerfile.rocm_base
|
||||||
|
- vllm/models/deepseek_v41/amd/
|
||||||
|
- tests/models/test_dsv41_mono_numerics.py
|
||||||
|
- tests/models/test_dsv41_mono_layers.py
|
||||||
|
commands:
|
||||||
|
- pytest -v -s tests/models/test_dsv41_mono_numerics.py
|
||||||
|
- pytest -v -s tests/models/test_dsv41_mono_layers.py
|
||||||
|
|||||||
@@ -2,6 +2,39 @@ group: Models - Distributed
|
|||||||
depends_on:
|
depends_on:
|
||||||
- image-build
|
- image-build
|
||||||
steps:
|
steps:
|
||||||
|
- label: ":nvidia: (L4) Qwen4 Exp SP"
|
||||||
|
key: qwen4-exp-sp-tests-4-gpus
|
||||||
|
timeout_in_minutes: 30
|
||||||
|
working_dir: "/vllm-workspace/tests"
|
||||||
|
device: l4
|
||||||
|
num_devices: 4
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/config/parallel.py
|
||||||
|
- vllm/models/common/ops/sequence_parallel.py
|
||||||
|
- vllm/models/qwen4_exp/
|
||||||
|
- vllm/model_executor/layers/vocab_parallel_embedding.py
|
||||||
|
- vllm/model_executor/models/qwen3_next.py
|
||||||
|
- tests/models/qwen4_exp/test_ple.py
|
||||||
|
- tests/models/qwen4_exp/test_tpsp.py
|
||||||
|
commands:
|
||||||
|
- pytest -v -s models/qwen4_exp/test_tpsp.py
|
||||||
|
mirror:
|
||||||
|
amd:
|
||||||
|
label: ":amd: (MI355) Qwen4 Exp SP"
|
||||||
|
dind: false
|
||||||
|
device: mi355_4
|
||||||
|
depends_on:
|
||||||
|
- image-build-amd
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/config/parallel.py
|
||||||
|
- vllm/models/common/ops/sequence_parallel.py
|
||||||
|
- vllm/models/qwen4_exp/
|
||||||
|
- vllm/model_executor/layers/vocab_parallel_embedding.py
|
||||||
|
- vllm/model_executor/models/qwen3_next.py
|
||||||
|
- vllm/platforms/rocm.py
|
||||||
|
- tests/models/qwen4_exp/test_ple.py
|
||||||
|
- tests/models/qwen4_exp/test_tpsp.py
|
||||||
|
|
||||||
- label: ":nvidia: (L4) Distributed Models Shard %N"
|
- label: ":nvidia: (L4) Distributed Models Shard %N"
|
||||||
key: distributed-model-tests-2-gpus
|
key: distributed-model-tests-2-gpus
|
||||||
timeout_in_minutes: 35
|
timeout_in_minutes: 35
|
||||||
|
|||||||
@@ -184,8 +184,6 @@ steps:
|
|||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- vllm/model_executor/models/qwen3_5.py
|
- vllm/model_executor/models/qwen3_5.py
|
||||||
- vllm/model_executor/models/qwen3_5_mtp.py
|
- vllm/model_executor/models/qwen3_5_mtp.py
|
||||||
- vllm/transformers_utils/configs/qwen3_5.py
|
|
||||||
- vllm/transformers_utils/configs/qwen3_5_moe.py
|
|
||||||
- vllm/model_executor/models/qwen2.py
|
- vllm/model_executor/models/qwen2.py
|
||||||
- vllm/model_executor/models/qwen3.py
|
- vllm/model_executor/models/qwen3.py
|
||||||
- vllm/model_executor/models/qwen3_next.py
|
- vllm/model_executor/models/qwen3_next.py
|
||||||
@@ -201,31 +199,37 @@ steps:
|
|||||||
- vllm/platforms/rocm.py
|
- vllm/platforms/rocm.py
|
||||||
- tests/models/language/generation_ppl_test
|
- tests/models/language/generation_ppl_test
|
||||||
|
|
||||||
- label: ":nvidia: (H200 MIG 35GB) Language Models (Extended Pooling) Shard %N"
|
- label: ":nvidia: (H200 MIG 35GB) Language Models (Extended Pooling)"
|
||||||
device: h200_35gb
|
device: h200_35gb
|
||||||
key: language-models-test-extended-pooling
|
key: language-models-test-extended-pooling
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 120
|
timeout_in_minutes: 120
|
||||||
parallelism: 4
|
|
||||||
optional: true
|
optional: true
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- vllm/
|
- vllm/
|
||||||
- "!vllm/distributed/kv_transfer/"
|
- "!vllm/distributed/kv_transfer/"
|
||||||
- tests/models/language/pooling
|
- tests/models/language/pooling
|
||||||
commands:
|
commands:
|
||||||
- pytest -v -s models/language/pooling -m 'not core_model' --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB
|
# Per-test timeout: a hung test fails with a stack dump instead of holding
|
||||||
|
# the job until Buildkite cancels it, which also blocks the full run's
|
||||||
|
# coverage collection. A whole shard takes 12-21 minutes.
|
||||||
|
- pytest -v -s models/language/pooling -m 'not core_model' --timeout=900 --timeout-method=thread
|
||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI300) Language Models (Extended Pooling) Shard %N"
|
parallelism: 4
|
||||||
|
commands:
|
||||||
|
- "pytest -v -s models/language/pooling -m 'not core_model' --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB"
|
||||||
|
label: ":amd: (MI355 DPX) Language Models (Extended Pooling) Shard %N"
|
||||||
dind: false
|
dind: false
|
||||||
device: mi300_1
|
device: mi355_dpx
|
||||||
timeout_in_minutes: 95
|
timeout_in_minutes: 95
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-amd
|
- image-build-amd
|
||||||
|
|
||||||
- label: ":nvidia: (H200 MIG 18GB) Language Models (MTEB)"
|
- label: ":nvidia: (H200 MIG 35GB) Language Models (MTEB)"
|
||||||
key: language-models-test-mteb
|
key: language-models-test-mteb
|
||||||
timeout_in_minutes: 68
|
timeout_in_minutes: 68
|
||||||
device: h200_18gb
|
device: h200_35gb
|
||||||
optional: true
|
optional: true
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- vllm/
|
- vllm/
|
||||||
|
|||||||
@@ -24,6 +24,7 @@ steps:
|
|||||||
|
|
||||||
- label: ":nvidia: (H200 MIG 18GB) Multimodal Models (Standard) 2: qwen3 + gemma"
|
- label: ":nvidia: (H200 MIG 18GB) Multimodal Models (Standard) 2: qwen3 + gemma"
|
||||||
key: multi-modal-models-standard-2-qwen3-gemma
|
key: multi-modal-models-standard-2-qwen3-gemma
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 75
|
timeout_in_minutes: 75
|
||||||
device: h200_18gb
|
device: h200_18gb
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
@@ -162,9 +163,9 @@ steps:
|
|||||||
- pytest -v -s models/multimodal/test_mapping.py
|
- pytest -v -s models/multimodal/test_mapping.py
|
||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI300) Multimodal Models (Extended Generation 1)"
|
label: ":amd: (MI355 DPX) Multimodal Models (Extended Generation 1)"
|
||||||
dind: false
|
dind: false
|
||||||
device: mi300_1
|
device: mi355_dpx
|
||||||
timeout_in_minutes: 100
|
timeout_in_minutes: 100
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-amd
|
- image-build-amd
|
||||||
@@ -181,9 +182,9 @@ steps:
|
|||||||
- pytest -v -s models/multimodal/generation_ppl_test/
|
- pytest -v -s models/multimodal/generation_ppl_test/
|
||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI300) Multimodal Models (PPL)"
|
label: ":amd: (MI355 DPX) Multimodal Models (PPL)"
|
||||||
dind: false
|
dind: false
|
||||||
device: mi300_1
|
device: mi355_dpx
|
||||||
timeout_in_minutes: 90
|
timeout_in_minutes: 90
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-amd
|
- image-build-amd
|
||||||
@@ -239,9 +240,9 @@ steps:
|
|||||||
- pytest -v -s models/multimodal/pooling -m 'not core_model'
|
- pytest -v -s models/multimodal/pooling -m 'not core_model'
|
||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI300) Multimodal Models (Extended Pooling)"
|
label: ":amd: (MI355 DPX) Multimodal Models (Extended Pooling)"
|
||||||
dind: false
|
dind: false
|
||||||
device: mi300_1
|
device: mi355_dpx
|
||||||
timeout_in_minutes: 75
|
timeout_in_minutes: 75
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-amd
|
- image-build-amd
|
||||||
|
|||||||
@@ -123,6 +123,7 @@ steps:
|
|||||||
|
|
||||||
- label: ":nvidia: (L4) PyTorch Compilation Passes"
|
- label: ":nvidia: (L4) PyTorch Compilation Passes"
|
||||||
key: pytorch-compilation-passes-unit-tests
|
key: pytorch-compilation-passes-unit-tests
|
||||||
|
automatic_shard: true
|
||||||
device: l4
|
device: l4
|
||||||
num_devices: 1
|
num_devices: 1
|
||||||
timeout_in_minutes: 45
|
timeout_in_minutes: 45
|
||||||
@@ -159,6 +160,7 @@ steps:
|
|||||||
amd:
|
amd:
|
||||||
label: ':amd: (MI300) PyTorch Compilation Passes'
|
label: ':amd: (MI300) PyTorch Compilation Passes'
|
||||||
dind: false
|
dind: false
|
||||||
|
automatic_shard: true
|
||||||
device: mi300_1
|
device: mi300_1
|
||||||
timeout_in_minutes: 80
|
timeout_in_minutes: 80
|
||||||
working_dir: /vllm-workspace/tests
|
working_dir: /vllm-workspace/tests
|
||||||
|
|||||||
@@ -2,26 +2,27 @@ group: Quantization
|
|||||||
depends_on:
|
depends_on:
|
||||||
- image-build
|
- image-build
|
||||||
steps:
|
steps:
|
||||||
- label: ":nvidia: (H200 MIG 35GB) Quantization Shard %N"
|
- label: ":nvidia: (H200 MIG 35GB) Quantization"
|
||||||
device: h200_35gb
|
device: h200_35gb
|
||||||
key: quantization
|
key: quantization
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 40
|
timeout_in_minutes: 40
|
||||||
parallelism: 4
|
|
||||||
env:
|
|
||||||
VLLM_USE_V2_MODEL_RUNNER: "0"
|
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- csrc/
|
- csrc/
|
||||||
- vllm/model_executor/layers/quantization
|
- vllm/model_executor/layers/quantization
|
||||||
|
- vllm/models/deepseek_v41/quant_config.py
|
||||||
|
- vllm/utils/humming.py
|
||||||
- tests/quantization
|
- tests/quantization
|
||||||
commands:
|
commands:
|
||||||
# Pin torchao to the version compatible with the CI PyTorch and CUDA stack.
|
# Pin torchao to the version compatible with the CI PyTorch and CUDA stack.
|
||||||
- uv pip install --system torchao==0.17.0 --index-url https://download.pytorch.org/whl/cu130
|
- uv pip install --system torchao==0.18.0 --index-url https://download.pytorch.org/whl/cu130
|
||||||
- uv pip install --system conch-triton-kernels
|
- uv pip install --system conch-triton-kernels
|
||||||
# The SM90-only checkpoint currently contains a removed weight_chan_scale
|
# The SM90-only checkpoint currently contains a removed weight_chan_scale
|
||||||
# parameter. It was not exercised by the previous L4 job.
|
# parameter. It was not exercised by the previous L4 job.
|
||||||
- VLLM_TEST_FORCE_LOAD_FORMAT=auto pytest -v -s quantization/ --ignore quantization/test_blackwell_moe.py --ignore quantization/test_rocm_moe.py -k 'not test_compressed_tensors_w4a8_fp8' --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
|
- VLLM_TEST_FORCE_LOAD_FORMAT=auto pytest -v -s quantization/ --ignore quantization/test_blackwell_moe.py --ignore quantization/test_rocm_moe.py -k 'not test_compressed_tensors_w4a8_fp8'
|
||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
|
parallelism: 4
|
||||||
label: ":amd: (MI300) Quantization Shard %N"
|
label: ":amd: (MI300) Quantization Shard %N"
|
||||||
dind: false
|
dind: false
|
||||||
device: mi300_1
|
device: mi300_1
|
||||||
@@ -40,8 +41,6 @@ steps:
|
|||||||
- tests/rocm/test_moe_weight_replay.py
|
- tests/rocm/test_moe_weight_replay.py
|
||||||
- tests/rocm/test_moe_padding.py
|
- tests/rocm/test_moe_padding.py
|
||||||
commands:
|
commands:
|
||||||
# Use the ROCm default instead of the NVIDIA runner override.
|
|
||||||
- unset VLLM_USE_V2_MODEL_RUNNER
|
|
||||||
- uv pip install --system torchao==0.17.0
|
- uv pip install --system torchao==0.17.0
|
||||||
- uv pip install --system conch-triton-kernels
|
- uv pip install --system conch-triton-kernels
|
||||||
- VLLM_TEST_FORCE_LOAD_FORMAT=auto pytest -v -s quantization/ --ignore quantization/test_blackwell_moe.py --ignore quantization/test_rocm_moe.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
|
- VLLM_TEST_FORCE_LOAD_FORMAT=auto pytest -v -s quantization/ --ignore quantization/test_blackwell_moe.py --ignore quantization/test_rocm_moe.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
|
||||||
@@ -79,6 +78,7 @@ steps:
|
|||||||
|
|
||||||
- label: ":nvidia: (B200) Quantized MoE"
|
- label: ":nvidia: (B200) Quantized MoE"
|
||||||
key: quantized-moe-test-b200
|
key: quantized-moe-test-b200
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 120
|
timeout_in_minutes: 120
|
||||||
working_dir: "/vllm-workspace/"
|
working_dir: "/vllm-workspace/"
|
||||||
device: b200-k8s
|
device: b200-k8s
|
||||||
@@ -126,9 +126,8 @@ steps:
|
|||||||
- label: ":nvidia: (H200 MIG 35GB) Quantized Models"
|
- label: ":nvidia: (H200 MIG 35GB) Quantized Models"
|
||||||
device: h200_35gb
|
device: h200_35gb
|
||||||
key: quantized-models-test
|
key: quantized-models-test
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 65
|
timeout_in_minutes: 65
|
||||||
env:
|
|
||||||
VLLM_USE_V2_MODEL_RUNNER: "0"
|
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- vllm/model_executor/layers/quantization
|
- vllm/model_executor/layers/quantization
|
||||||
- tests/models/quantization
|
- tests/models/quantization
|
||||||
@@ -138,6 +137,7 @@ steps:
|
|||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI355 DPX) Quantized Models"
|
label: ":amd: (MI355 DPX) Quantized Models"
|
||||||
dind: false
|
dind: false
|
||||||
|
automatic_shard: true
|
||||||
device: mi355_dpx
|
device: mi355_dpx
|
||||||
timeout_in_minutes: 80
|
timeout_in_minutes: 80
|
||||||
working_dir: "/vllm-workspace/tests"
|
working_dir: "/vllm-workspace/tests"
|
||||||
@@ -150,6 +150,4 @@ steps:
|
|||||||
- vllm/platforms/rocm.py
|
- vllm/platforms/rocm.py
|
||||||
- vllm/model_executor/model_loader/
|
- vllm/model_executor/model_loader/
|
||||||
commands:
|
commands:
|
||||||
# Use the ROCm default instead of the NVIDIA runner override.
|
|
||||||
- unset VLLM_USE_V2_MODEL_RUNNER
|
|
||||||
- pytest -v -s models/quantization
|
- pytest -v -s models/quantization
|
||||||
|
|||||||
@@ -0,0 +1,25 @@
|
|||||||
|
group: RL
|
||||||
|
depends_on:
|
||||||
|
- image-build
|
||||||
|
steps:
|
||||||
|
- label: ":nvidia: (H200 MIG 35GB) RL Entrypoints"
|
||||||
|
device: h200_35gb
|
||||||
|
key: rl-entrypoints-tests
|
||||||
|
timeout_in_minutes: 40
|
||||||
|
working_dir: "/vllm-workspace/tests"
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/
|
||||||
|
- "!vllm/distributed/kv_transfer/"
|
||||||
|
- tests/entrypoints/rl
|
||||||
|
commands:
|
||||||
|
- pytest -v -s entrypoints/rl/weight_transfer
|
||||||
|
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
||||||
|
- pytest -v -s entrypoints/rl --ignore=entrypoints/rl/weight_transfer
|
||||||
|
mirror:
|
||||||
|
amd:
|
||||||
|
label: ":amd: (MI355 DPX) RL Entrypoints"
|
||||||
|
dind: false
|
||||||
|
device: mi355_dpx
|
||||||
|
timeout_in_minutes: 50
|
||||||
|
depends_on:
|
||||||
|
- image-build-amd
|
||||||
@@ -82,7 +82,6 @@ steps:
|
|||||||
- tests/entrypoints/scale_out/token_in_token_out/test_serving_tokens.py
|
- tests/entrypoints/scale_out/token_in_token_out/test_serving_tokens.py
|
||||||
- tests/entrypoints/serve/instrumentator/test_basic.py
|
- tests/entrypoints/serve/instrumentator/test_basic.py
|
||||||
- tests/entrypoints/serve/instrumentator/test_metrics.py
|
- tests/entrypoints/serve/instrumentator/test_metrics.py
|
||||||
# - tests/entrypoints/serve/dev/test_sleep.py
|
|
||||||
- tests/entrypoints/serve/tokenize/test_tokenization.py
|
- tests/entrypoints/serve/tokenize/test_tokenization.py
|
||||||
commands:
|
commands:
|
||||||
- export VLLM_USE_RUST_FRONTEND=1
|
- export VLLM_USE_RUST_FRONTEND=1
|
||||||
@@ -93,7 +92,6 @@ steps:
|
|||||||
# test_generate_logprobs expects Python-style top_logprobs truncation (dedup sampled + cap at max(k, 1)).
|
# test_generate_logprobs expects Python-style top_logprobs truncation (dedup sampled + cap at max(k, 1)).
|
||||||
- pytest -v -s entrypoints/scale_out/token_in_token_out/test_serving_tokens.py -k "not stream and not lora and not test_generate_logprobs and not stop_string_workflow"
|
- pytest -v -s entrypoints/scale_out/token_in_token_out/test_serving_tokens.py -k "not stream and not lora and not test_generate_logprobs and not stop_string_workflow"
|
||||||
- pytest -v -s entrypoints/serve/instrumentator/test_metrics.py -k "text and not show and not run_batch and not test_metrics_counts and not test_metrics_exist"
|
- pytest -v -s entrypoints/serve/instrumentator/test_metrics.py -k "text and not show and not run_batch and not test_metrics_counts and not test_metrics_exist"
|
||||||
# - pytest -v -s entrypoints/serve/dev/test_sleep.py
|
|
||||||
# /tokenizer_info is not implemented in the Rust frontend (the CLI flag is accepted as a no-op).
|
# /tokenizer_info is not implemented in the Rust frontend (the CLI flag is accepted as a no-op).
|
||||||
- pytest -v -s entrypoints/serve/tokenize/test_tokenization.py -k "not tokenizer_info"
|
- pytest -v -s entrypoints/serve/tokenize/test_tokenization.py -k "not tokenizer_info"
|
||||||
mirror:
|
mirror:
|
||||||
|
|||||||
@@ -14,16 +14,6 @@ steps:
|
|||||||
- .buildkite/scripts/run-rust-frontend-cargo-ci.sh
|
- .buildkite/scripts/run-rust-frontend-cargo-ci.sh
|
||||||
commands:
|
commands:
|
||||||
- .buildkite/scripts/run-rust-frontend-cargo-ci.sh style-clippy
|
- .buildkite/scripts/run-rust-frontend-cargo-ci.sh style-clippy
|
||||||
mirror:
|
|
||||||
amd:
|
|
||||||
label: ":amd: (MI250) Rust Frontend Cargo Style + Clippy"
|
|
||||||
dind: false
|
|
||||||
device: mi250_1
|
|
||||||
no_gpu: true
|
|
||||||
working_dir: "/vllm-workspace"
|
|
||||||
timeout_in_minutes: 35
|
|
||||||
depends_on:
|
|
||||||
- image-build-amd
|
|
||||||
|
|
||||||
- label: ":computer: (CPU) Rust Frontend Cargo"
|
- label: ":computer: (CPU) Rust Frontend Cargo"
|
||||||
key: rust-frontend-cargo-tests
|
key: rust-frontend-cargo-tests
|
||||||
@@ -38,13 +28,3 @@ steps:
|
|||||||
- .buildkite/scripts/run-rust-frontend-cargo-ci.sh
|
- .buildkite/scripts/run-rust-frontend-cargo-ci.sh
|
||||||
commands:
|
commands:
|
||||||
- .buildkite/scripts/run-rust-frontend-cargo-ci.sh test
|
- .buildkite/scripts/run-rust-frontend-cargo-ci.sh test
|
||||||
mirror:
|
|
||||||
amd:
|
|
||||||
label: ":amd: (MI250) Rust Frontend Cargo"
|
|
||||||
dind: false
|
|
||||||
device: mi250_1
|
|
||||||
no_gpu: true
|
|
||||||
working_dir: "/vllm-workspace"
|
|
||||||
timeout_in_minutes: 35
|
|
||||||
depends_on:
|
|
||||||
- image-build-amd
|
|
||||||
|
|||||||
@@ -5,6 +5,7 @@ steps:
|
|||||||
- label: ":nvidia: (H200 MIG 35GB) V1 Spec Decode"
|
- label: ":nvidia: (H200 MIG 35GB) V1 Spec Decode"
|
||||||
device: h200_35gb
|
device: h200_35gb
|
||||||
key: v1-spec-decode
|
key: v1-spec-decode
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 40
|
timeout_in_minutes: 40
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- vllm/config/
|
- vllm/config/
|
||||||
@@ -27,6 +28,7 @@ steps:
|
|||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI300) V1 Spec Decode"
|
label: ":amd: (MI300) V1 Spec Decode"
|
||||||
dind: false
|
dind: false
|
||||||
|
automatic_shard: true
|
||||||
device: mi300_1
|
device: mi300_1
|
||||||
timeout_in_minutes: 50
|
timeout_in_minutes: 50
|
||||||
depends_on:
|
depends_on:
|
||||||
@@ -135,9 +137,9 @@ steps:
|
|||||||
- pytest -v -s v1/e2e/spec_decode/speculators/
|
- pytest -v -s v1/e2e/spec_decode/speculators/
|
||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI300) Spec Decode Speculators"
|
label: ":amd: (MI355 DPX) Spec Decode Speculators"
|
||||||
dind: false
|
dind: false
|
||||||
device: mi300_1
|
device: mi355_dpx
|
||||||
timeout_in_minutes: 40
|
timeout_in_minutes: 40
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-amd
|
- image-build-amd
|
||||||
@@ -165,9 +167,9 @@ steps:
|
|||||||
- pytest -v -s v1/e2e/spec_decode/mtp/gemma4/
|
- pytest -v -s v1/e2e/spec_decode/mtp/gemma4/
|
||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI300) Spec Decode MTP Gemma4"
|
label: ":amd: (MI355 DPX) Spec Decode MTP Gemma4"
|
||||||
dind: false
|
dind: false
|
||||||
device: mi300_1
|
device: mi355_dpx
|
||||||
timeout_in_minutes: 40
|
timeout_in_minutes: 40
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-amd
|
- image-build-amd
|
||||||
@@ -196,9 +198,9 @@ steps:
|
|||||||
- pytest -v -s v1/e2e/spec_decode/mtp/mimo/
|
- pytest -v -s v1/e2e/spec_decode/mtp/mimo/
|
||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI300) Spec Decode MTP DeepSeek + MiMo"
|
label: ":amd: (MI355 DPX) Spec Decode MTP DeepSeek + MiMo"
|
||||||
dind: false
|
dind: false
|
||||||
device: mi300_1
|
device: mi355_dpx
|
||||||
timeout_in_minutes: 40
|
timeout_in_minutes: 40
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-amd
|
- image-build-amd
|
||||||
@@ -226,9 +228,9 @@ steps:
|
|||||||
- pytest -v -s v1/e2e/spec_decode/mtp/qwen3_5/
|
- pytest -v -s v1/e2e/spec_decode/mtp/qwen3_5/
|
||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI300) Spec Decode MTP Qwen3.5"
|
label: ":amd: (MI355 DPX) Spec Decode MTP Qwen3.5"
|
||||||
dind: false
|
dind: false
|
||||||
device: mi300_1
|
device: mi355_dpx
|
||||||
timeout_in_minutes: 40
|
timeout_in_minutes: 40
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-amd
|
- image-build-amd
|
||||||
@@ -385,9 +387,9 @@ steps:
|
|||||||
- pytest -v -s v1/spec_decode/test_speculators_correctness.py -m slow_test
|
- pytest -v -s v1/spec_decode/test_speculators_correctness.py -m slow_test
|
||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI300) Speculators Correctness Nightly"
|
label: ":amd: (MI355 DPX) Speculators Correctness Nightly"
|
||||||
dind: false
|
dind: false
|
||||||
device: mi300_1
|
device: mi355_dpx
|
||||||
timeout_in_minutes: 40
|
timeout_in_minutes: 40
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-amd
|
- image-build-amd
|
||||||
@@ -450,9 +452,9 @@ steps:
|
|||||||
- pytest -v -s v1/e2e/spec_decode/acceptance_rates/dflash/ -k "not dflash2"
|
- pytest -v -s v1/e2e/spec_decode/acceptance_rates/dflash/ -k "not dflash2"
|
||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI300) Spec Decode AL DFlash Nightly"
|
label: ":amd: (MI355 DPX) Spec Decode AL DFlash Nightly"
|
||||||
dind: false
|
dind: false
|
||||||
device: mi300_1
|
device: mi355_dpx
|
||||||
timeout_in_minutes: 120
|
timeout_in_minutes: 120
|
||||||
commands:
|
commands:
|
||||||
- pytest -v -s v1/e2e/spec_decode/acceptance_rates/dflash/ -k "not dflash2"
|
- pytest -v -s v1/e2e/spec_decode/acceptance_rates/dflash/ -k "not dflash2"
|
||||||
@@ -529,9 +531,9 @@ steps:
|
|||||||
- pytest -v -s v1/e2e/spec_decode/acceptance_rates/dspark/
|
- pytest -v -s v1/e2e/spec_decode/acceptance_rates/dspark/
|
||||||
mirror:
|
mirror:
|
||||||
amd:
|
amd:
|
||||||
label: ":amd: (MI300) Spec Decode AL DSpark Nightly"
|
label: ":amd: (MI355 DPX) Spec Decode AL DSpark Nightly"
|
||||||
dind: false
|
dind: false
|
||||||
device: mi300_1
|
device: mi355_dpx
|
||||||
timeout_in_minutes: 90
|
timeout_in_minutes: 90
|
||||||
depends_on:
|
depends_on:
|
||||||
- image-build-amd
|
- image-build-amd
|
||||||
@@ -593,7 +595,6 @@ steps:
|
|||||||
- vllm/model_executor/models/gemma4_mtp.py
|
- vllm/model_executor/models/gemma4_mtp.py
|
||||||
- vllm/model_executor/models/llama.py
|
- vllm/model_executor/models/llama.py
|
||||||
- vllm/model_executor/models/llama_eagle3.py
|
- vllm/model_executor/models/llama_eagle3.py
|
||||||
- vllm/model_executor/models/medusa.py
|
|
||||||
- vllm/model_executor/models/registry.py
|
- vllm/model_executor/models/registry.py
|
||||||
- tests/evals/gsm8k/
|
- tests/evals/gsm8k/
|
||||||
- tests/utils.py
|
- tests/utils.py
|
||||||
|
|||||||
+1
@@ -0,0 +1 @@
|
|||||||
|
../../.agents/skills/model-microbenchmark
|
||||||
Symlink
+1
@@ -0,0 +1 @@
|
|||||||
|
../../.agents/skills/model-recipes
|
||||||
+1
@@ -0,0 +1 @@
|
|||||||
|
../../.agents/skills/transformers-upgrade
|
||||||
+56
-26
@@ -3,12 +3,14 @@
|
|||||||
|
|
||||||
# This lists cover the "core" components of vLLM that require careful review
|
# This lists cover the "core" components of vLLM that require careful review
|
||||||
/vllm/compilation @zou3519 @youkaichao @ProExpertProg @BoyuanFeng
|
/vllm/compilation @zou3519 @youkaichao @ProExpertProg @BoyuanFeng
|
||||||
|
/vllm/compilation/breakable_cudagraph.py @ZJY0516
|
||||||
/vllm/distributed/kv_transfer @NickLucche @ApostaC @orozery @xuechendi @ivanium @wzhao18
|
/vllm/distributed/kv_transfer @NickLucche @ApostaC @orozery @xuechendi @ivanium @wzhao18
|
||||||
|
/vllm/distributed/kv_transfer/kv_connector/v1/hisparse @MatthewBonanni @LucasWilkinson
|
||||||
/vllm/lora @jeejeelee
|
/vllm/lora @jeejeelee
|
||||||
/vllm/model_executor/layers/attention @LucasWilkinson @MatthewBonanni
|
/vllm/model_executor/layers/attention @LucasWilkinson @MatthewBonanni
|
||||||
/vllm/model_executor/layers/fused_moe @mgoin @pavanimajety @zyongye @wzhao18
|
/vllm/model_executor/layers/fused_moe @mgoin @pavanimajety @zyongye @wzhao18 @bnellnm
|
||||||
/vllm/model_executor/layers/quantization @mgoin @robertgshaw2-redhat @tlrmchlsmth @yewentao256 @pavanimajety @zyongye
|
/vllm/model_executor/layers/quantization @mgoin @robertgshaw2-redhat @tlrmchlsmth @yewentao256 @pavanimajety @zyongye
|
||||||
/vllm/model_executor/layers/mamba @tdoublep @tomeras91
|
/vllm/model_executor/layers/mamba @tdoublep @tomeras91 @ZJY0516
|
||||||
/vllm/model_executor/layers/mamba/gdn/qwen_gdn_linear_attn.py @tdoublep @ZJY0516 @vadiklyutiy
|
/vllm/model_executor/layers/mamba/gdn/qwen_gdn_linear_attn.py @tdoublep @ZJY0516 @vadiklyutiy
|
||||||
/vllm/model_executor/model_loader @22quinn
|
/vllm/model_executor/model_loader @22quinn
|
||||||
/vllm/model_executor/determinism/ @yewentao256
|
/vllm/model_executor/determinism/ @yewentao256
|
||||||
@@ -25,7 +27,7 @@
|
|||||||
# Any change to the VllmConfig changes can have a large user-facing impact,
|
# Any change to the VllmConfig changes can have a large user-facing impact,
|
||||||
# so spam a lot of people
|
# so spam a lot of people
|
||||||
/vllm/config @WoosukKwon @youkaichao @robertgshaw2-redhat @mgoin @tlrmchlsmth @houseroad @yewentao256 @ProExpertProg
|
/vllm/config @WoosukKwon @youkaichao @robertgshaw2-redhat @mgoin @tlrmchlsmth @houseroad @yewentao256 @ProExpertProg
|
||||||
/vllm/config/cache.py @heheda12345 @ivanium
|
/vllm/config/cache.py @heheda12345 @ivanium @ZJY0516
|
||||||
|
|
||||||
# Config utils
|
# Config utils
|
||||||
/vllm/config/utils.py @hmellor
|
/vllm/config/utils.py @hmellor
|
||||||
@@ -33,23 +35,48 @@
|
|||||||
/vllm/utils/argparse_utils.py
|
/vllm/utils/argparse_utils.py
|
||||||
|
|
||||||
# Entrypoints
|
# Entrypoints
|
||||||
/vllm/entrypoints/anthropic @mgoin @DarkLight1337
|
/vllm/entrypoints/anthropic @chaunceyjiang @mgoin @DarkLight1337
|
||||||
|
/vllm/entrypoints/cohere @DarkLight1337
|
||||||
/vllm/entrypoints/cli @hmellor @mgoin @DarkLight1337
|
/vllm/entrypoints/cli @hmellor @mgoin @DarkLight1337
|
||||||
/vllm/entrypoints/mcp @heheda12345
|
/vllm/entrypoints/mcp @heheda12345
|
||||||
/vllm/entrypoints/openai @aarnphm @chaunceyjiang @DarkLight1337
|
/vllm/entrypoints/openai/chat_completion @chaunceyjiang @DarkLight1337
|
||||||
/vllm/entrypoints/speech_to_text/realtime @njhill
|
/vllm/entrypoints/openai/completion @chaunceyjiang @DarkLight1337
|
||||||
|
/vllm/entrypoints/openai/models @chaunceyjiang @DarkLight1337
|
||||||
|
/vllm/entrypoints/openai/parser @aarnphm @chaunceyjiang @sfeng33
|
||||||
|
/vllm/entrypoints/openai/responses @aarnphm @chaunceyjiang @sfeng33
|
||||||
|
/vllm/entrypoints/pooling @noooop @DarkLight1337
|
||||||
|
/vllm/entrypoints/rl @aoshen02 @njhill
|
||||||
|
/vllm/entrypoints/scale_out @aoshen02 @noooop @DarkLight1337
|
||||||
/vllm/entrypoints/speech_to_text @NickLucche
|
/vllm/entrypoints/speech_to_text @NickLucche
|
||||||
/vllm/entrypoints/pooling @noooop
|
/vllm/entrypoints/speech_to_text/realtime @njhill @NickLucche
|
||||||
/vllm/entrypoints/serve/sagemaker @DarkLight1337
|
|
||||||
/vllm/entrypoints/serve @njhill
|
/vllm/entrypoints/serve @njhill
|
||||||
/vllm/entrypoints/*.py @njhill
|
/vllm/entrypoints/serve/sagemaker @DarkLight1337
|
||||||
/vllm/entrypoints/chat_utils.py @DarkLight1337
|
/vllm/entrypoints/common @DarkLight1337
|
||||||
/vllm/entrypoints/offline_utils.py @DarkLight1337
|
|
||||||
/vllm/entrypoints/llm.py @DarkLight1337
|
/vllm/entrypoints/llm.py @DarkLight1337
|
||||||
|
|
||||||
|
/tests/entrypoints @robertgshaw2-redhat @aarnphm @NickLucche @AndreasKaratzas
|
||||||
|
/tests/entrypoints/anthropic @mgoin @DarkLight1337
|
||||||
|
/tests/entrypoints/cohere @DarkLight1337
|
||||||
|
/tests/entrypoints/cli @hmellor @mgoin @DarkLight1337
|
||||||
|
/tests/entrypoints/openai/chat_completion @chaunceyjiang @DarkLight1337
|
||||||
|
/tests/entrypoints/openai/completion @chaunceyjiang @DarkLight1337
|
||||||
|
/tests/entrypoints/openai/models @chaunceyjiang @DarkLight1337
|
||||||
|
/tests/entrypoints/openai/parser @aarnphm @chaunceyjiang @sfeng33
|
||||||
|
/tests/entrypoints/openai/responses @aarnphm @chaunceyjiang @sfeng33
|
||||||
|
/tests/entrypoints/pooling @noooop @DarkLight1337
|
||||||
|
/tests/entrypoints/rl @aoshen02 @njhill
|
||||||
|
/tests/entrypoints/scale_out @noooop @DarkLight1337
|
||||||
|
/tests/entrypoints/speech_to_text @NickLucche
|
||||||
|
/tests/entrypoints/speech_to_text/realtime @njhill @NickLucche
|
||||||
|
/tests/entrypoints/serve @njhill
|
||||||
|
/tests/entrypoints/serve/sagemaker @DarkLight1337
|
||||||
|
/tests/entrypoints/llm @DarkLight1337
|
||||||
|
/tests/entrypoints/llm/test_struct_output_generate.py @mgoin @aarnphm @arpera
|
||||||
|
|
||||||
# Rust Frontend
|
# Rust Frontend
|
||||||
/rust/ @BugenZhao @njhill
|
/rust/ @BugenZhao @njhill
|
||||||
/rust/src/bench @esmeetu
|
/rust/src/bench @esmeetu
|
||||||
|
/rust/src/server/src/routes/inference @aoshen02 @BugenZhao @njhill
|
||||||
/tools/build_rust.sh @BugenZhao @njhill
|
/tools/build_rust.sh @BugenZhao @njhill
|
||||||
/rust-toolchain.toml @BugenZhao @njhill
|
/rust-toolchain.toml @BugenZhao @njhill
|
||||||
/.buildkite/test_areas/rust* @BugenZhao @njhill
|
/.buildkite/test_areas/rust* @BugenZhao @njhill
|
||||||
@@ -63,6 +90,12 @@
|
|||||||
/vllm/tool_parsers @aarnphm @chaunceyjiang @sfeng33 @bbrowning
|
/vllm/tool_parsers @aarnphm @chaunceyjiang @sfeng33 @bbrowning
|
||||||
/vllm/parser @aarnphm @chaunceyjiang @sfeng33 @bbrowning
|
/vllm/parser @aarnphm @chaunceyjiang @sfeng33 @bbrowning
|
||||||
|
|
||||||
|
/tests/tokenizers_ @DarkLight1337 @njhill
|
||||||
|
/tests/renderers @DarkLight1337 @njhill
|
||||||
|
/tests/reasoning @aarnphm @chaunceyjiang @sfeng33 @bbrowning
|
||||||
|
/tests/tool_parsers @aarnphm @chaunceyjiang @sfeng33 @bbrowning
|
||||||
|
/tests/tool_use @aarnphm @chaunceyjiang @sfeng33 @bbrowning
|
||||||
|
|
||||||
# vLLM V1
|
# vLLM V1
|
||||||
/vllm/v1/attention @LucasWilkinson @MatthewBonanni
|
/vllm/v1/attention @LucasWilkinson @MatthewBonanni
|
||||||
/vllm/v1/attention/backend.py @WoosukKwon @zhuohan123 @youkaichao @alexm-redhat @njhill
|
/vllm/v1/attention/backend.py @WoosukKwon @zhuohan123 @youkaichao @alexm-redhat @njhill
|
||||||
@@ -70,16 +103,18 @@
|
|||||||
/vllm/v1/attention/backends/flashinfer.py @mgoin @pavanimajety @vadiklyutiy @wzhao18
|
/vllm/v1/attention/backends/flashinfer.py @mgoin @pavanimajety @vadiklyutiy @wzhao18
|
||||||
/vllm/v1/attention/backends/triton_attn.py @tdoublep
|
/vllm/v1/attention/backends/triton_attn.py @tdoublep
|
||||||
/vllm/v1/attention/backends/gdn_attn.py @ZJY0516 @vadiklyutiy
|
/vllm/v1/attention/backends/gdn_attn.py @ZJY0516 @vadiklyutiy
|
||||||
/vllm/v1/core @WoosukKwon @robertgshaw2-redhat @njhill @ywang96 @alexm-redhat @heheda12345 @ApostaC @orozery @ivanium
|
/vllm/v1/core @WoosukKwon @robertgshaw2-redhat @njhill @ywang96 @alexm-redhat @heheda12345 @ApostaC @orozery @ivanium @ZJY0516
|
||||||
/vllm/v1/sample @22quinn @houseroad @njhill
|
/vllm/v1/sample @22quinn @houseroad @njhill
|
||||||
/vllm/v1/spec_decode @benchislett @luccafong @MatthewBonanni
|
/vllm/v1/spec_decode @benchislett @luccafong @MatthewBonanni
|
||||||
/vllm/v1/structured_output @mgoin @aarnphm @benchislett @arpera
|
/vllm/v1/structured_output @mgoin @aarnphm @benchislett @arpera
|
||||||
/vllm/v1/kv_cache_interface.py @heheda12345 @ivanium
|
/vllm/v1/kv_cache_interface.py @heheda12345 @ivanium @ZJY0516
|
||||||
/vllm/v1/kv_offload @ApostaC @orozery
|
/vllm/v1/kv_offload @ApostaC @orozery
|
||||||
/vllm/v1/simple_kv_offload @ivanium
|
/vllm/v1/simple_kv_offload @ivanium
|
||||||
|
/vllm/v1/hisparse @MatthewBonanni @LucasWilkinson
|
||||||
/vllm/v1/engine @njhill
|
/vllm/v1/engine @njhill
|
||||||
/vllm/v1/executor @njhill
|
/vllm/v1/executor @njhill
|
||||||
/vllm/v1/worker @njhill
|
/vllm/v1/worker @njhill
|
||||||
|
/vllm/v1/worker/mamba_utils.py @njhill @ZJY0516
|
||||||
/vllm/v1/worker/kv_connector_model_runner_mixin.py @orozery @NickLucche @ivanium
|
/vllm/v1/worker/kv_connector_model_runner_mixin.py @orozery @NickLucche @ivanium
|
||||||
/vllm/v1/worker/encoder_cudagraph.py @shen-shanshan
|
/vllm/v1/worker/encoder_cudagraph.py @shen-shanshan
|
||||||
/vllm/v1/worker/encoder_cudagraph_defs.py @shen-shanshan
|
/vllm/v1/worker/encoder_cudagraph_defs.py @shen-shanshan
|
||||||
@@ -87,6 +122,7 @@
|
|||||||
# Model runner V2
|
# Model runner V2
|
||||||
/vllm/v1/worker/gpu @WoosukKwon @njhill @yewentao256
|
/vllm/v1/worker/gpu @WoosukKwon @njhill @yewentao256
|
||||||
/vllm/v1/worker/gpu/kv_connector.py @orozery
|
/vllm/v1/worker/gpu/kv_connector.py @orozery
|
||||||
|
/vllm/v1/worker/gpu/model_states/mamba_hybrid.py @WoosukKwon @njhill @yewentao256 @ZJY0516
|
||||||
|
|
||||||
# CI & building
|
# CI & building
|
||||||
/.buildkite @Harry-Chen @khluu
|
/.buildkite @Harry-Chen @khluu
|
||||||
@@ -99,27 +135,23 @@
|
|||||||
/tests/distributed/test_multi_node_assignment.py @youkaichao
|
/tests/distributed/test_multi_node_assignment.py @youkaichao
|
||||||
/tests/distributed/test_pipeline_parallel.py @youkaichao
|
/tests/distributed/test_pipeline_parallel.py @youkaichao
|
||||||
/tests/distributed/test_same_node.py @youkaichao
|
/tests/distributed/test_same_node.py @youkaichao
|
||||||
/tests/entrypoints @DarkLight1337 @robertgshaw2-redhat @aarnphm @NickLucche @AndreasKaratzas
|
/tests/evals @mgoin @vadiklyutiy @AndreasKaratzas @ZJY0516
|
||||||
/tests/evals @mgoin @vadiklyutiy @AndreasKaratzas
|
|
||||||
/tests/kernels @mgoin @tlrmchlsmth @WoosukKwon @yewentao256 @zyongye @AndreasKaratzas
|
/tests/kernels @mgoin @tlrmchlsmth @WoosukKwon @yewentao256 @zyongye @AndreasKaratzas
|
||||||
/tests/kernels/ir @ProExpertProg @tjtanaa
|
/tests/kernels/ir @ProExpertProg @tjtanaa
|
||||||
|
/tests/kernels/moe @bnellnm
|
||||||
/tests/models @DarkLight1337 @ywang96 @AndreasKaratzas
|
/tests/models @DarkLight1337 @ywang96 @AndreasKaratzas
|
||||||
/tests/multimodal @DarkLight1337 @ywang96 @NickLucche @shen-shanshan
|
/tests/multimodal @DarkLight1337 @ywang96 @NickLucche @shen-shanshan
|
||||||
/tests/multimodal/media @Isotr0py
|
/tests/multimodal/media @Isotr0py
|
||||||
/tests/quantization @mgoin @robertgshaw2-redhat @yewentao256 @pavanimajety @zyongye @AndreasKaratzas
|
/tests/quantization @mgoin @robertgshaw2-redhat @yewentao256 @pavanimajety @zyongye @AndreasKaratzas
|
||||||
/tests/entrypoints/llm/test_struct_output_generate.py @mgoin @aarnphm @arpera
|
|
||||||
/tests/v1/structured_output @mgoin @aarnphm @arpera
|
/tests/v1/structured_output @mgoin @aarnphm @arpera
|
||||||
/tests/v1/core @WoosukKwon @robertgshaw2-redhat @njhill @ywang96 @alexm-redhat @heheda12345 @ApostaC @orozery @ivanium
|
/tests/v1/core @WoosukKwon @robertgshaw2-redhat @njhill @ywang96 @alexm-redhat @heheda12345 @ApostaC @orozery @ivanium @ZJY0516
|
||||||
/tests/lora @jeejeelee
|
/tests/lora @jeejeelee
|
||||||
/tests/models/language/generation/test_hybrid.py @tdoublep @tomeras91
|
/tests/models/language/generation/test_hybrid.py @tdoublep @tomeras91 @ZJY0516
|
||||||
/tests/v1/kv_connector/nixl_integration @NickLucche
|
/tests/v1/kv_connector/nixl_integration @NickLucche
|
||||||
/tests/v1/kv_connector @ApostaC @orozery @ivanium @wzhao18
|
/tests/v1/kv_connector @ApostaC @orozery @ivanium @wzhao18
|
||||||
/tests/v1/kv_offload @ApostaC @orozery
|
/tests/v1/kv_offload @ApostaC @orozery
|
||||||
/tests/v1/simple_kv_offload @ivanium
|
/tests/v1/simple_kv_offload @ivanium
|
||||||
/tests/v1/determinism @yewentao256
|
/tests/v1/determinism @yewentao256
|
||||||
/tests/reasoning @aarnphm @chaunceyjiang @sfeng33 @bbrowning
|
|
||||||
/tests/tool_parsers @aarnphm @chaunceyjiang @sfeng33 @bbrowning
|
|
||||||
/tests/tool_use @aarnphm @chaunceyjiang @sfeng33 @bbrowning
|
|
||||||
|
|
||||||
# Transformers modeling backend
|
# Transformers modeling backend
|
||||||
/vllm/model_executor/models/transformers @hmellor
|
/vllm/model_executor/models/transformers @hmellor
|
||||||
@@ -133,6 +165,9 @@
|
|||||||
.readthedocs.yaml @hmellor
|
.readthedocs.yaml @hmellor
|
||||||
mkdocs.yaml @hmellor
|
mkdocs.yaml @hmellor
|
||||||
|
|
||||||
|
# Model recipes
|
||||||
|
/recipes @esmeetu
|
||||||
|
|
||||||
# Linting
|
# Linting
|
||||||
/tools/pre_commit/.markdownlint.yaml @hmellor
|
/tools/pre_commit/.markdownlint.yaml @hmellor
|
||||||
.pre-commit-config.yaml @hmellor
|
.pre-commit-config.yaml @hmellor
|
||||||
@@ -221,19 +256,14 @@ mkdocs.yaml @hmellor
|
|||||||
/examples/pooling @noooop
|
/examples/pooling @noooop
|
||||||
/docs/models/pooling_models @noooop
|
/docs/models/pooling_models @noooop
|
||||||
/tests/models/*/pooling* @noooop
|
/tests/models/*/pooling* @noooop
|
||||||
/tests/entrypoints/pooling @noooop
|
|
||||||
/vllm/config/pooler.py @noooop
|
/vllm/config/pooler.py @noooop
|
||||||
/vllm/model_executor/layers/pooler @noooop
|
/vllm/model_executor/layers/pooler @noooop
|
||||||
|
|
||||||
# Reinforcement learning
|
# Reinforcement learning
|
||||||
/vllm/distributed/weight_transfer @aoshen02
|
/vllm/distributed/weight_transfer @aoshen02
|
||||||
/vllm/entrypoints/serve/dev/rlhf @njhill @aoshen02
|
|
||||||
/tests/distributed/test_weight_transfer.py @aoshen02
|
/tests/distributed/test_weight_transfer.py @aoshen02
|
||||||
/tests/entrypoints/weight_transfer @DarkLight1337 @robertgshaw2-redhat @aarnphm @NickLucche @AndreasKaratzas @aoshen02
|
|
||||||
/tests/entrypoints/serve/dev/rlhf @DarkLight1337 @robertgshaw2-redhat @aarnphm @NickLucche @AndreasKaratzas @aoshen02
|
|
||||||
/tests/v1/worker/test_gpu_worker_weight_transfer.py @aoshen02
|
/tests/v1/worker/test_gpu_worker_weight_transfer.py @aoshen02
|
||||||
/examples/rl @aoshen02
|
/examples/rl @aoshen02
|
||||||
/examples/features/pause_resume @aoshen02
|
|
||||||
/docs/training/rlhf.md @aoshen02
|
/docs/training/rlhf.md @aoshen02
|
||||||
/docs/training/async_rl.md @aoshen02
|
/docs/training/async_rl.md @aoshen02
|
||||||
/docs/training/weight_transfer @aoshen02
|
/docs/training/weight_transfer @aoshen02
|
||||||
|
|||||||
+1
-6
@@ -494,8 +494,7 @@ pull_request_rules:
|
|||||||
- files~=^tests/v1/e2e/spec_decode/
|
- files~=^tests/v1/e2e/spec_decode/
|
||||||
- files~=^examples/features/speculative_decoding/
|
- files~=^examples/features/speculative_decoding/
|
||||||
- files~=^vllm/model_executor/models/.*eagle.*\.py
|
- files~=^vllm/model_executor/models/.*eagle.*\.py
|
||||||
- files=vllm/model_executor/models/mlp_speculator.py
|
- files~=^vllm/transformers_utils/configs/eagle\.py
|
||||||
- files~=^vllm/transformers_utils/configs/(eagle|medusa|mlp_speculator)\.py
|
|
||||||
actions:
|
actions:
|
||||||
label:
|
label:
|
||||||
add:
|
add:
|
||||||
@@ -549,8 +548,6 @@ pull_request_rules:
|
|||||||
- label != stale
|
- label != stale
|
||||||
- or:
|
- or:
|
||||||
- files~=tpu.py
|
- files~=tpu.py
|
||||||
- files~=_tpu
|
|
||||||
- files~=tpu_
|
|
||||||
- files~=/tpu/
|
- files~=/tpu/
|
||||||
actions:
|
actions:
|
||||||
label:
|
label:
|
||||||
@@ -564,8 +561,6 @@ pull_request_rules:
|
|||||||
- label != stale
|
- label != stale
|
||||||
- and:
|
- and:
|
||||||
- -files~=tpu.py
|
- -files~=tpu.py
|
||||||
- -files~=_tpu
|
|
||||||
- -files~=tpu_
|
|
||||||
- -files~=/tpu/
|
- -files~=/tpu/
|
||||||
actions:
|
actions:
|
||||||
label:
|
label:
|
||||||
|
|||||||
@@ -279,7 +279,6 @@ jobs:
|
|||||||
"speculative-decoding": {
|
"speculative-decoding": {
|
||||||
keywords: [
|
keywords: [
|
||||||
{ term: "eagle", searchIn: "title" },
|
{ term: "eagle", searchIn: "title" },
|
||||||
{ term: "medusa", searchIn: "title" },
|
|
||||||
],
|
],
|
||||||
substrings: [
|
substrings: [
|
||||||
{ term: "speculative decoding", searchIn: "title" },
|
{ term: "speculative decoding", searchIn: "title" },
|
||||||
|
|||||||
@@ -0,0 +1,28 @@
|
|||||||
|
name: Recipes
|
||||||
|
|
||||||
|
# Validate recipe changes against the renderer that publishes them
|
||||||
|
# (recipes.vllm.ai). The check logic lives in vllm-project/recipes and tracks
|
||||||
|
# its main branch, so a PR is held to the same validation that runs when
|
||||||
|
# vllm-project/recipes picks up this directory after merge.
|
||||||
|
|
||||||
|
on:
|
||||||
|
pull_request:
|
||||||
|
paths:
|
||||||
|
- 'recipes/**'
|
||||||
|
- '.github/workflows/recipes.yml'
|
||||||
|
|
||||||
|
concurrency:
|
||||||
|
group: ${{ github.workflow }}-${{ github.ref }}
|
||||||
|
cancel-in-progress: true
|
||||||
|
|
||||||
|
permissions:
|
||||||
|
contents: read
|
||||||
|
|
||||||
|
jobs:
|
||||||
|
validate:
|
||||||
|
name: Recipes
|
||||||
|
if: github.repository_owner == 'vllm-project'
|
||||||
|
uses: vllm-project/recipes/.github/workflows/validate-recipes.yml@main
|
||||||
|
with:
|
||||||
|
source: vllm
|
||||||
|
path: recipes
|
||||||
@@ -18,22 +18,8 @@ jobs:
|
|||||||
if: >-
|
if: >-
|
||||||
github.repository_owner == 'vllm-project' &&
|
github.repository_owner == 'vllm-project' &&
|
||||||
github.event.issue.pull_request &&
|
github.event.issue.pull_request &&
|
||||||
(github.event.comment.body == '/ci run' ||
|
(startsWith(github.event.comment.body, '/ci') ||
|
||||||
github.event.comment.body == '/ci run all' ||
|
startsWith(github.event.comment.body, '/amd-ci'))
|
||||||
github.event.comment.body == '/ci run nightly' ||
|
|
||||||
github.event.comment.body == '/ci run --allow-stale' ||
|
|
||||||
github.event.comment.body == '/ci run all --allow-stale' ||
|
|
||||||
github.event.comment.body == '/ci run nightly --allow-stale' ||
|
|
||||||
github.event.comment.body == '/ci retry' ||
|
|
||||||
github.event.comment.body == '/ci cancel' ||
|
|
||||||
github.event.comment.body == '/amd-ci run' ||
|
|
||||||
github.event.comment.body == '/amd-ci run all' ||
|
|
||||||
github.event.comment.body == '/amd-ci run nightly' ||
|
|
||||||
github.event.comment.body == '/amd-ci run --allow-stale' ||
|
|
||||||
github.event.comment.body == '/amd-ci run all --allow-stale' ||
|
|
||||||
github.event.comment.body == '/amd-ci run nightly --allow-stale' ||
|
|
||||||
github.event.comment.body == '/amd-ci retry' ||
|
|
||||||
github.event.comment.body == '/amd-ci cancel')
|
|
||||||
runs-on: [self-hosted, linux, x64, vllm-runners]
|
runs-on: [self-hosted, linux, x64, vllm-runners]
|
||||||
steps:
|
steps:
|
||||||
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
|
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
|
||||||
@@ -53,4 +39,16 @@ jobs:
|
|||||||
BUILDKITE_ORGANIZATION: vllm
|
BUILDKITE_ORGANIZATION: vllm
|
||||||
BUILDKITE_PIPELINE: ci
|
BUILDKITE_PIPELINE: ci
|
||||||
CI_TRUSTED_USERS: ${{ vars.CI_TRUSTED_USERS }}
|
CI_TRUSTED_USERS: ${{ vars.CI_TRUSTED_USERS }}
|
||||||
|
GH_BRANCH_UPDATE_TOKEN: ${{ secrets.CI_BRANCH_UPDATE_TOKEN }}
|
||||||
GH_TOKEN: ${{ github.token }}
|
GH_TOKEN: ${{ github.token }}
|
||||||
|
- name: Report failure on the PR
|
||||||
|
if: failure()
|
||||||
|
uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
|
||||||
|
with:
|
||||||
|
script: |
|
||||||
|
const runUrl = `${context.serverUrl}/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}`;
|
||||||
|
await github.rest.issues.createComment({
|
||||||
|
...context.repo,
|
||||||
|
issue_number: context.issue.number,
|
||||||
|
body: `❌ @${context.payload.comment.user.login}, your CI command failed with an unexpected error, so CI may not have started. See the [workflow run](${runUrl}) for details.`,
|
||||||
|
});
|
||||||
|
|||||||
@@ -58,9 +58,12 @@ AMD_CI_COMMANDS = frozenset(
|
|||||||
RETRY_COMMANDS = frozenset({COMMAND_RETRY_FAILED, COMMAND_RETRY_AMD_FAILED})
|
RETRY_COMMANDS = frozenset({COMMAND_RETRY_FAILED, COMMAND_RETRY_AMD_FAILED})
|
||||||
CANCEL_COMMANDS = frozenset({COMMAND_CANCEL_CI, COMMAND_CANCEL_AMD_CI})
|
CANCEL_COMMANDS = frozenset({COMMAND_CANCEL_CI, COMMAND_CANCEL_AMD_CI})
|
||||||
ALL_CI_COMMANDS = UPSTREAM_CI_COMMANDS | AMD_CI_COMMANDS
|
ALL_CI_COMMANDS = UPSTREAM_CI_COMMANDS | AMD_CI_COMMANDS
|
||||||
|
CI_COMMAND_PREFIXES = frozenset({"/ci", "/amd-ci"})
|
||||||
CI_AUTHORIZED_COMMENT_MARKER = "<!-- vllm-ci-authorized -->"
|
CI_AUTHORIZED_COMMENT_MARKER = "<!-- vllm-ci-authorized -->"
|
||||||
READY_LABELS = {"ready", "ready-run-all-tests"}
|
READY_LABELS = {"ready", "ready-run-all-tests"}
|
||||||
TRUSTED_PERMISSIONS = {"admin", "maintain", "write"}
|
TRUSTED_PERMISSIONS = {"admin", "maintain", "write"}
|
||||||
|
BRANCH_UPDATE_POLL_SECONDS = 3
|
||||||
|
BRANCH_UPDATE_POLL_ATTEMPTS = 40
|
||||||
ACTIVE_BUILD_STATES = {
|
ACTIVE_BUILD_STATES = {
|
||||||
"blocked",
|
"blocked",
|
||||||
"creating",
|
"creating",
|
||||||
@@ -258,6 +261,13 @@ class GitHubClient:
|
|||||||
raise ApiError(None, "GitHub returned an invalid commits-behind count.")
|
raise ApiError(None, "GitHub returned an invalid commits-behind count.")
|
||||||
return behind
|
return behind
|
||||||
|
|
||||||
|
def update_branch(self, number: int, expected_head_sha: str) -> None:
|
||||||
|
self._request(
|
||||||
|
self._repo_path(f"/pulls/{number}/update-branch"),
|
||||||
|
body={"expected_head_sha": expected_head_sha},
|
||||||
|
method="PUT",
|
||||||
|
)
|
||||||
|
|
||||||
def list_pulls_for_commit(self, commit: str) -> list[dict[str, Any]]:
|
def list_pulls_for_commit(self, commit: str) -> list[dict[str, Any]]:
|
||||||
commit = urllib.parse.quote(commit, safe="")
|
commit = urllib.parse.quote(commit, safe="")
|
||||||
response = self._request(self._repo_path(f"/commits/{commit}/pulls"))
|
response = self._request(self._repo_path(f"/commits/{commit}/pulls"))
|
||||||
@@ -461,11 +471,17 @@ class BuildkiteClient:
|
|||||||
|
|
||||||
|
|
||||||
def parse_command(body: str) -> str | None:
|
def parse_command(body: str) -> str | None:
|
||||||
|
body = body.strip()
|
||||||
if body in ALL_CI_COMMANDS:
|
if body in ALL_CI_COMMANDS:
|
||||||
return body
|
return body
|
||||||
return None
|
return None
|
||||||
|
|
||||||
|
|
||||||
|
def is_ci_command_attempt(body: str) -> bool:
|
||||||
|
words = body.split(maxsplit=1)
|
||||||
|
return bool(words) and words[0].casefold() in CI_COMMAND_PREFIXES
|
||||||
|
|
||||||
|
|
||||||
def pipeline_for_command(
|
def pipeline_for_command(
|
||||||
command: str,
|
command: str,
|
||||||
*,
|
*,
|
||||||
@@ -605,6 +621,16 @@ def blocks_new_run(command: str, build: Mapping[str, Any]) -> bool:
|
|||||||
return is_active_build(build)
|
return is_active_build(build)
|
||||||
|
|
||||||
|
|
||||||
|
def list_commit_builds(
|
||||||
|
buildkite: BuildkiteClient, command: str, commit: str
|
||||||
|
) -> list[dict[str, Any]]:
|
||||||
|
builds = buildkite.list_builds(commit)
|
||||||
|
if command not in AMD_CI_COMMANDS:
|
||||||
|
return builds
|
||||||
|
# bootstrap-amd.sh exits before uploading any test steps for PR webhook builds.
|
||||||
|
return [build for build in builds if build.get("source") != "webhook"]
|
||||||
|
|
||||||
|
|
||||||
def select_latest_build(
|
def select_latest_build(
|
||||||
builds: Sequence[dict[str, Any]],
|
builds: Sequence[dict[str, Any]],
|
||||||
pr_number: int,
|
pr_number: int,
|
||||||
@@ -771,10 +797,11 @@ def notify_authorized(
|
|||||||
(
|
(
|
||||||
f"✅ @{author}, CI is now available for this PR.\n\n"
|
f"✅ @{author}, CI is now available for this PR.\n\n"
|
||||||
"- `/ci run` starts upstream CI; `/amd-ci run` starts AMD CI only.\n"
|
"- `/ci run` starts upstream CI; `/amd-ci run` starts AMD CI only.\n"
|
||||||
"- Your branch must contain every commit currently on its upstream "
|
"- Run commands test your branch with every commit currently on its "
|
||||||
"target branch. Merge or rebase onto the latest target branch, then "
|
"upstream target branch. If it is behind, the bot merges the target "
|
||||||
"rerun the command. Append `--allow-stale` to a run command to test "
|
"branch into it first (pull before pushing again). Append "
|
||||||
"an outdated branch at your own risk.\n"
|
"`--allow-stale` to a run command to test an outdated branch as is, "
|
||||||
|
"at your own risk.\n"
|
||||||
"- `/ci retry` retries failed jobs in the CI build for the current "
|
"- `/ci retry` retries failed jobs in the CI build for the current "
|
||||||
"PR head. If the current head has no CI build, it starts a new CI "
|
"PR head. If the current head has no CI build, it starts a new CI "
|
||||||
"build for the current head containing only jobs that failed in "
|
"build for the current head containing only jobs that failed in "
|
||||||
@@ -822,10 +849,65 @@ def resolve_workflow_run_pr(
|
|||||||
return find_matching_pr(github.list_pulls_for_commit(head_sha))
|
return find_matching_pr(github.list_pulls_for_commit(head_sha))
|
||||||
|
|
||||||
|
|
||||||
|
def merge_base_into_pr(
|
||||||
|
github: GitHubClient,
|
||||||
|
branch_updater: GitHubClient,
|
||||||
|
pr: Mapping[str, Any],
|
||||||
|
command: str,
|
||||||
|
lag: str,
|
||||||
|
) -> tuple[dict[str, Any], str]:
|
||||||
|
base_ref = pr["base"]["ref"]
|
||||||
|
|
||||||
|
def merge_failed(reason: str) -> CiPreparationError:
|
||||||
|
return CiPreparationError(
|
||||||
|
f"{lag} The bot could not merge upstream `{base_ref}` into this "
|
||||||
|
f"branch ({reason}). No new CI build was started. Either merge or "
|
||||||
|
f"rebase onto the latest `{base_ref}` yourself and rerun `{command}`, "
|
||||||
|
f"or use `{command}{ALLOW_STALE_SUFFIX}` to test this branch as is."
|
||||||
|
)
|
||||||
|
|
||||||
|
try:
|
||||||
|
branch_updater.update_branch(pr["number"], pr["head"]["sha"])
|
||||||
|
for _ in range(BRANCH_UPDATE_POLL_ATTEMPTS):
|
||||||
|
time.sleep(BRANCH_UPDATE_POLL_SECONDS)
|
||||||
|
current_pr = github.get_pr(pr["number"])
|
||||||
|
if current_pr["head"]["sha"] == pr["head"]["sha"]:
|
||||||
|
continue
|
||||||
|
try:
|
||||||
|
behind = github.get_commits_behind_base(
|
||||||
|
base_ref, current_pr["head"]["sha"]
|
||||||
|
)
|
||||||
|
except ApiError as error:
|
||||||
|
# A fork's new head is briefly unknown to the base repository.
|
||||||
|
if error.status == 404:
|
||||||
|
continue
|
||||||
|
raise
|
||||||
|
break
|
||||||
|
else:
|
||||||
|
raise merge_failed("the merge commit did not appear in time")
|
||||||
|
if (
|
||||||
|
current_pr["state"] != "open"
|
||||||
|
or current_pr["base"]["ref"] != base_ref
|
||||||
|
or behind
|
||||||
|
):
|
||||||
|
raise merge_failed("the PR changed during the merge")
|
||||||
|
except ApiError as error:
|
||||||
|
raise merge_failed(str(error)) from error
|
||||||
|
|
||||||
|
note = (
|
||||||
|
f"ℹ️ {lag} Merged upstream `{base_ref}` into this branch as "
|
||||||
|
f"`{current_pr['head']['sha'][:12]}` before starting CI. "
|
||||||
|
"Pull the branch before pushing more changes."
|
||||||
|
)
|
||||||
|
print(note)
|
||||||
|
return current_pr, note
|
||||||
|
|
||||||
|
|
||||||
def prepare_pr_for_ci(
|
def prepare_pr_for_ci(
|
||||||
github: GitHubClient,
|
github: GitHubClient,
|
||||||
pr: Mapping[str, Any],
|
pr: Mapping[str, Any],
|
||||||
command: str,
|
command: str,
|
||||||
|
branch_updater: GitHubClient | None = None,
|
||||||
) -> tuple[dict[str, Any], str]:
|
) -> tuple[dict[str, Any], str]:
|
||||||
base_ref = pr["base"]["ref"]
|
base_ref = pr["base"]["ref"]
|
||||||
no_action = "No new CI build was started."
|
no_action = "No new CI build was started."
|
||||||
@@ -861,6 +943,8 @@ def prepare_pr_for_ci(
|
|||||||
print(warning)
|
print(warning)
|
||||||
return current_pr, warning
|
return current_pr, warning
|
||||||
|
|
||||||
|
if behind and branch_updater is not None:
|
||||||
|
return merge_base_into_pr(github, branch_updater, current_pr, command, lag)
|
||||||
if behind:
|
if behind:
|
||||||
raise CiPreparationError(
|
raise CiPreparationError(
|
||||||
f"{lag} Your branch must contain every commit currently on upstream "
|
f"{lag} Your branch must contain every commit currently on upstream "
|
||||||
@@ -880,6 +964,8 @@ def handle_run_ci(
|
|||||||
command: str,
|
command: str,
|
||||||
github: GitHubClient,
|
github: GitHubClient,
|
||||||
pr: Mapping[str, Any],
|
pr: Mapping[str, Any],
|
||||||
|
branch_updater: GitHubClient | None = None,
|
||||||
|
allow_repeat_run: bool = False,
|
||||||
) -> str:
|
) -> str:
|
||||||
ci_name = ci_name_for_command(command)
|
ci_name = ci_name_for_command(command)
|
||||||
duplicate_builds = buildkite.list_builds(
|
duplicate_builds = buildkite.list_builds(
|
||||||
@@ -892,7 +978,7 @@ def handle_run_ci(
|
|||||||
f"{ci_name} was already requested by this comment: {duplicate['web_url']}"
|
f"{ci_name} was already requested by this comment: {duplicate['web_url']}"
|
||||||
)
|
)
|
||||||
|
|
||||||
current_builds = buildkite.list_builds(pr["head"]["sha"])
|
current_builds = list_commit_builds(buildkite, command, pr["head"]["sha"])
|
||||||
active_build = next(
|
active_build = next(
|
||||||
(
|
(
|
||||||
build
|
build
|
||||||
@@ -906,7 +992,19 @@ def handle_run_ci(
|
|||||||
f"{ci_name} is already running for this commit: {active_build['web_url']}"
|
f"{ci_name} is already running for this commit: {active_build['web_url']}"
|
||||||
)
|
)
|
||||||
|
|
||||||
current_pr, warning = prepare_pr_for_ci(github, pr, command)
|
tested_build = select_latest_build(
|
||||||
|
[build for build in current_builds if build.get("state") != "canceled"],
|
||||||
|
pr["number"],
|
||||||
|
)
|
||||||
|
if tested_build and not allow_repeat_run:
|
||||||
|
raise CiPreparationError(
|
||||||
|
f"{ci_name} already ran on this commit: {tested_build['web_url']}. "
|
||||||
|
"No new CI build was started. Push new changes to run CI again, use "
|
||||||
|
f"`{retry_command_for_command(command)}` to rerun failed jobs, or ask "
|
||||||
|
"a reviewer with write access to rerun it."
|
||||||
|
)
|
||||||
|
|
||||||
|
current_pr, warning = prepare_pr_for_ci(github, pr, command, branch_updater)
|
||||||
|
|
||||||
build = buildkite.create_build(
|
build = buildkite.create_build(
|
||||||
create_build_payload(
|
create_build_payload(
|
||||||
@@ -935,7 +1033,7 @@ def handle_retry_failed(
|
|||||||
ci_name = ci_name_for_command(command)
|
ci_name = ci_name_for_command(command)
|
||||||
run_command = run_command_for_command(command)
|
run_command = run_command_for_command(command)
|
||||||
retry_command = retry_command_for_command(command)
|
retry_command = retry_command_for_command(command)
|
||||||
builds = buildkite.list_builds(pr["head"]["sha"])
|
builds = list_commit_builds(buildkite, command, pr["head"]["sha"])
|
||||||
build = select_latest_build(builds, pr["number"])
|
build = select_latest_build(builds, pr["number"])
|
||||||
if build:
|
if build:
|
||||||
metadata = build.get("meta_data") or {}
|
metadata = build.get("meta_data") or {}
|
||||||
@@ -1086,11 +1184,34 @@ def handle_cancel_ci(
|
|||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
|
def reply_unrecognized_command(
|
||||||
|
event: Mapping[str, Any],
|
||||||
|
github: GitHubClient,
|
||||||
|
) -> None:
|
||||||
|
if "pull_request" not in event["issue"]:
|
||||||
|
return
|
||||||
|
issue_number = event["issue"]["number"]
|
||||||
|
comment_id = event["comment"]["id"]
|
||||||
|
actor = event["comment"]["user"]["login"]
|
||||||
|
if is_already_handled(github, issue_number, comment_id):
|
||||||
|
print(f"Comment {comment_id} was already handled.")
|
||||||
|
return
|
||||||
|
add_reaction_safely(github, comment_id, "-1")
|
||||||
|
commands = ", ".join(f"`{command}`" for command in sorted(ALL_CI_COMMANDS))
|
||||||
|
github.add_comment(
|
||||||
|
issue_number,
|
||||||
|
f"❌ @{actor}, that is not a recognized CI command, so no CI was "
|
||||||
|
"started. Post a new comment containing only one of: "
|
||||||
|
f"{commands}.\n\n{command_comment_marker(comment_id)}",
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
def run(
|
def run(
|
||||||
event: Mapping[str, Any],
|
event: Mapping[str, Any],
|
||||||
github: GitHubClient,
|
github: GitHubClient,
|
||||||
buildkite: BuildkiteClient,
|
buildkite: BuildkiteClient,
|
||||||
trusted_users_value: str = "",
|
trusted_users_value: str = "",
|
||||||
|
branch_updater: GitHubClient | None = None,
|
||||||
) -> None:
|
) -> None:
|
||||||
command = parse_command(event["comment"]["body"])
|
command = parse_command(event["comment"]["body"])
|
||||||
if not command or "pull_request" not in event["issue"]:
|
if not command or "pull_request" not in event["issue"]:
|
||||||
@@ -1153,6 +1274,8 @@ def run(
|
|||||||
command=command,
|
command=command,
|
||||||
github=github,
|
github=github,
|
||||||
pr=pr,
|
pr=pr,
|
||||||
|
branch_updater=branch_updater,
|
||||||
|
allow_repeat_run=is_trusted_permission(permission),
|
||||||
)
|
)
|
||||||
elif command in RETRY_COMMANDS:
|
elif command in RETRY_COMMANDS:
|
||||||
message = handle_retry_failed(
|
message = handle_retry_failed(
|
||||||
@@ -1217,8 +1340,11 @@ def main() -> None:
|
|||||||
)
|
)
|
||||||
return
|
return
|
||||||
|
|
||||||
command = parse_command(event["comment"]["body"])
|
body = event["comment"]["body"]
|
||||||
|
command = parse_command(body)
|
||||||
if not command:
|
if not command:
|
||||||
|
if is_ci_command_attempt(body):
|
||||||
|
reply_unrecognized_command(event, github)
|
||||||
return
|
return
|
||||||
|
|
||||||
pipeline = pipeline_for_command(
|
pipeline = pipeline_for_command(
|
||||||
@@ -1231,11 +1357,15 @@ def main() -> None:
|
|||||||
os.environ.get("BUILDKITE_ORGANIZATION", "vllm"),
|
os.environ.get("BUILDKITE_ORGANIZATION", "vllm"),
|
||||||
pipeline,
|
pipeline,
|
||||||
)
|
)
|
||||||
|
branch_update_token = os.environ.get("GH_BRANCH_UPDATE_TOKEN", "")
|
||||||
run(
|
run(
|
||||||
event,
|
event,
|
||||||
github,
|
github,
|
||||||
buildkite,
|
buildkite,
|
||||||
os.environ.get("CI_TRUSTED_USERS", ""),
|
os.environ.get("CI_TRUSTED_USERS", ""),
|
||||||
|
GitHubClient(branch_update_token, os.environ["GITHUB_REPOSITORY"])
|
||||||
|
if branch_update_token
|
||||||
|
else None,
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
@@ -32,10 +32,12 @@ from run_ci_command import (
|
|||||||
has_trusted_approval,
|
has_trusted_approval,
|
||||||
is_active_build,
|
is_active_build,
|
||||||
is_build_for_pr,
|
is_build_for_pr,
|
||||||
|
is_ci_command_attempt,
|
||||||
notify_authorized,
|
notify_authorized,
|
||||||
parse_command,
|
parse_command,
|
||||||
parse_trusted_users,
|
parse_trusted_users,
|
||||||
pipeline_for_command,
|
pipeline_for_command,
|
||||||
|
reply_unrecognized_command,
|
||||||
resolve_workflow_run_pr,
|
resolve_workflow_run_pr,
|
||||||
run,
|
run,
|
||||||
select_latest_build,
|
select_latest_build,
|
||||||
@@ -142,6 +144,23 @@ class FakeGitHub:
|
|||||||
self.comments.append(body)
|
self.comments.append(body)
|
||||||
|
|
||||||
|
|
||||||
|
class FakeBranchUpdater:
|
||||||
|
def __init__(self, github: FakeGitHub, error: ApiError | None = None) -> None:
|
||||||
|
self.calls: list[tuple[int, str]] = []
|
||||||
|
self.error = error
|
||||||
|
self.github = github
|
||||||
|
|
||||||
|
def update_branch(self, number: int, expected_head_sha: str) -> None:
|
||||||
|
self.calls.append((number, expected_head_sha))
|
||||||
|
if self.error:
|
||||||
|
raise self.error
|
||||||
|
self.github.prs[number] = {
|
||||||
|
**self.github.prs[number],
|
||||||
|
"head": {**self.github.prs[number]["head"], "sha": "merge-commit-sha"},
|
||||||
|
}
|
||||||
|
self.github.behind = 0
|
||||||
|
|
||||||
|
|
||||||
class FakeBuildkite:
|
class FakeBuildkite:
|
||||||
def __init__(
|
def __init__(
|
||||||
self,
|
self,
|
||||||
@@ -340,14 +359,46 @@ class RunCiCommandTest(unittest.TestCase):
|
|||||||
self.assertIsNone(parse_command("/ci run please"))
|
self.assertIsNone(parse_command("/ci run please"))
|
||||||
self.assertIsNone(parse_command("/ci run all please"))
|
self.assertIsNone(parse_command("/ci run all please"))
|
||||||
self.assertIsNone(parse_command("/ci cancel please"))
|
self.assertIsNone(parse_command("/ci cancel please"))
|
||||||
self.assertIsNone(parse_command(" /ci run"))
|
|
||||||
self.assertIsNone(parse_command("/amd-ci run please"))
|
self.assertIsNone(parse_command("/amd-ci run please"))
|
||||||
self.assertIsNone(parse_command("/amd-ci retry "))
|
|
||||||
self.assertIsNone(parse_command("/AMD-CI run"))
|
self.assertIsNone(parse_command("/AMD-CI run"))
|
||||||
self.assertIsNone(parse_command("/amdci run"))
|
self.assertIsNone(parse_command("/amdci run"))
|
||||||
self.assertIsNone(parse_command("/ci run --allow-stale all"))
|
self.assertIsNone(parse_command("/ci run --allow-stale all"))
|
||||||
self.assertIsNone(parse_command("/amd-ci run --allow-stale please"))
|
self.assertIsNone(parse_command("/amd-ci run --allow-stale please"))
|
||||||
|
|
||||||
|
def test_surrounding_whitespace_is_ignored(self) -> None:
|
||||||
|
self.assertEqual(parse_command("/ci run\r\n"), COMMAND_RUN_CI)
|
||||||
|
self.assertEqual(parse_command(" /ci run "), COMMAND_RUN_CI)
|
||||||
|
self.assertEqual(parse_command("/amd-ci retry\n"), COMMAND_RETRY_AMD_FAILED)
|
||||||
|
|
||||||
|
def test_ci_command_attempts_are_detected(self) -> None:
|
||||||
|
for body in ("/ci", "/ci rn", "/CI run", "/amd-ci run please", " /ci\nrun"):
|
||||||
|
with self.subTest(body=body):
|
||||||
|
self.assertTrue(is_ci_command_attempt(body))
|
||||||
|
for body in ("", "LGTM", "/cifoo", "/amdci run", "please /ci run"):
|
||||||
|
with self.subTest(body=body):
|
||||||
|
self.assertFalse(is_ci_command_attempt(body))
|
||||||
|
|
||||||
|
def test_unrecognized_command_gets_feedback(self) -> None:
|
||||||
|
github = FakeGitHub()
|
||||||
|
|
||||||
|
reply_unrecognized_command(make_event("/ci rn", actor="author"), github)
|
||||||
|
|
||||||
|
self.assertEqual(github.reactions, ["-1"])
|
||||||
|
self.assertEqual(len(github.comments), 1)
|
||||||
|
self.assertIn(
|
||||||
|
"@author, that is not a recognized CI command", github.comments[0]
|
||||||
|
)
|
||||||
|
self.assertIn(f"`{COMMAND_RUN_CI}`", github.comments[0])
|
||||||
|
self.assertIn("<!-- vllm-ci-command:99 -->", github.comments[0])
|
||||||
|
|
||||||
|
def test_unrecognized_command_feedback_is_not_repeated(self) -> None:
|
||||||
|
github = FakeGitHub(comments=["❌ earlier\n\n<!-- vllm-ci-command:99 -->"])
|
||||||
|
|
||||||
|
reply_unrecognized_command(make_event("/ci rn"), github)
|
||||||
|
|
||||||
|
self.assertEqual(len(github.comments), 1)
|
||||||
|
self.assertEqual(github.reactions, [])
|
||||||
|
|
||||||
def test_commands_select_only_their_configured_pipeline(self) -> None:
|
def test_commands_select_only_their_configured_pipeline(self) -> None:
|
||||||
cases = (
|
cases = (
|
||||||
(COMMAND_RUN_CI, "ci"),
|
(COMMAND_RUN_CI, "ci"),
|
||||||
@@ -582,6 +633,82 @@ class RunCiCommandTest(unittest.TestCase):
|
|||||||
)
|
)
|
||||||
self.assertIn(command, github.comments[0])
|
self.assertIn(command, github.comments[0])
|
||||||
|
|
||||||
|
def test_run_merges_base_into_outdated_branch_before_building(self) -> None:
|
||||||
|
github = FakeGitHub(behind=5)
|
||||||
|
updater = FakeBranchUpdater(github)
|
||||||
|
buildkite = FakeBuildkite([[], []])
|
||||||
|
|
||||||
|
with patch("run_ci_command.time.sleep"):
|
||||||
|
run(make_event(COMMAND_RUN_CI), github, buildkite, "", updater)
|
||||||
|
|
||||||
|
self.assertEqual(updater.calls, [(42, "0123456789abcdef")])
|
||||||
|
self.assertEqual(buildkite.created_builds[0]["commit"], "merge-commit-sha")
|
||||||
|
self.assertTrue(github.comments[0].startswith("✅ "))
|
||||||
|
self.assertIn("5 commits behind", github.comments[0])
|
||||||
|
self.assertIn("Merged upstream `main`", github.comments[0])
|
||||||
|
|
||||||
|
def test_only_committers_can_rerun_a_commit_that_already_ran_ci(self) -> None:
|
||||||
|
finished_build = {
|
||||||
|
"created_at": "2026-07-28T01:00:00Z",
|
||||||
|
"pull_request": {"id": 42},
|
||||||
|
"state": "failed",
|
||||||
|
"web_url": "https://buildkite.example/builds/122",
|
||||||
|
}
|
||||||
|
for actor, permission, command, allowed in (
|
||||||
|
("author", "read", COMMAND_RUN_CI, False),
|
||||||
|
("author", "read", f"{COMMAND_RUN_CI} --allow-stale", False),
|
||||||
|
("reviewer", "write", COMMAND_RUN_CI, True),
|
||||||
|
):
|
||||||
|
with self.subTest(actor=actor, command=command):
|
||||||
|
github = FakeGitHub(
|
||||||
|
behind=5,
|
||||||
|
permission=permission,
|
||||||
|
pr=make_pr(labels=[{"name": "ready"}]),
|
||||||
|
)
|
||||||
|
updater = FakeBranchUpdater(github)
|
||||||
|
buildkite = FakeBuildkite([[], [finished_build]])
|
||||||
|
|
||||||
|
with patch("run_ci_command.time.sleep"):
|
||||||
|
run(make_event(command, actor), github, buildkite, "", updater)
|
||||||
|
|
||||||
|
self.assertEqual(bool(buildkite.created_builds), allowed)
|
||||||
|
if not allowed:
|
||||||
|
self.assertEqual(updater.calls, [])
|
||||||
|
self.assertIn("CI already ran on this commit", github.comments[0])
|
||||||
|
self.assertIn("`/ci retry`", github.comments[0])
|
||||||
|
|
||||||
|
def test_run_waits_for_fork_merge_commit_to_reach_base_repo(self) -> None:
|
||||||
|
github = FakeGitHub(behind=5)
|
||||||
|
updater = FakeBranchUpdater(github)
|
||||||
|
buildkite = FakeBuildkite([[], []])
|
||||||
|
|
||||||
|
with (
|
||||||
|
patch("run_ci_command.time.sleep"),
|
||||||
|
patch.object(
|
||||||
|
github,
|
||||||
|
"get_commits_behind_base",
|
||||||
|
side_effect=[5, ApiError(404, "Not Found"), 0],
|
||||||
|
),
|
||||||
|
):
|
||||||
|
run(make_event(COMMAND_RUN_CI), github, buildkite, "", updater)
|
||||||
|
|
||||||
|
self.assertEqual(buildkite.created_builds[0]["commit"], "merge-commit-sha")
|
||||||
|
self.assertTrue(github.comments[0].startswith("✅ "))
|
||||||
|
|
||||||
|
def test_run_reports_failed_merge_without_building(self) -> None:
|
||||||
|
github = FakeGitHub(behind=5)
|
||||||
|
updater = FakeBranchUpdater(github, error=ApiError(422, "merge conflict"))
|
||||||
|
buildkite = FakeBuildkite([[], []])
|
||||||
|
|
||||||
|
run(make_event(COMMAND_RUN_CI), github, buildkite, "", updater)
|
||||||
|
|
||||||
|
self.assertEqual(buildkite.created_builds, [])
|
||||||
|
self.assertTrue(github.comments[0].startswith("❌ "))
|
||||||
|
self.assertIn("could not merge upstream `main`", github.comments[0])
|
||||||
|
self.assertIn("merge conflict", github.comments[0])
|
||||||
|
self.assertIn("No new CI build was started.", github.comments[0])
|
||||||
|
self.assertIn("`/ci run --allow-stale`", github.comments[0])
|
||||||
|
|
||||||
def test_allow_stale_preserves_author_permissions_and_run_configuration(
|
def test_allow_stale_preserves_author_permissions_and_run_configuration(
|
||||||
self,
|
self,
|
||||||
) -> None:
|
) -> None:
|
||||||
@@ -756,6 +883,42 @@ class RunCiCommandTest(unittest.TestCase):
|
|||||||
self.assertEqual(buildkite.created_builds, [])
|
self.assertEqual(buildkite.created_builds, [])
|
||||||
self.assertIn("AMD CI is already running", github.comments[0])
|
self.assertIn("AMD CI is already running", github.comments[0])
|
||||||
|
|
||||||
|
def test_amd_run_ignores_finished_webhook_build_for_author(self) -> None:
|
||||||
|
webhook_build = {
|
||||||
|
"created_at": "2026-08-18T01:00:00Z",
|
||||||
|
"meta_data": {},
|
||||||
|
"number": 122,
|
||||||
|
"pull_request": {"id": 42},
|
||||||
|
"source": "webhook",
|
||||||
|
"state": "passed",
|
||||||
|
"web_url": "https://buildkite.example/amd-ci/builds/122",
|
||||||
|
}
|
||||||
|
ui_build = {**webhook_build, "source": "ui"}
|
||||||
|
command_build = {
|
||||||
|
**webhook_build,
|
||||||
|
"meta_data": {"github-comment-id": "98"},
|
||||||
|
"source": "api",
|
||||||
|
}
|
||||||
|
for build, allowed in (
|
||||||
|
(webhook_build, True),
|
||||||
|
(ui_build, False),
|
||||||
|
(command_build, False),
|
||||||
|
):
|
||||||
|
with self.subTest(source=build["source"]):
|
||||||
|
github = FakeGitHub(
|
||||||
|
permission="read",
|
||||||
|
pr=make_pr(labels=[{"name": "ready"}]),
|
||||||
|
)
|
||||||
|
buildkite = FakeBuildkite([[], [build]])
|
||||||
|
|
||||||
|
run(make_event(COMMAND_RUN_AMD_CI, "author"), github, buildkite)
|
||||||
|
|
||||||
|
self.assertEqual(bool(buildkite.created_builds), allowed)
|
||||||
|
if not allowed:
|
||||||
|
self.assertIn(
|
||||||
|
"AMD CI already ran on this commit", github.comments[0]
|
||||||
|
)
|
||||||
|
|
||||||
def test_run_all_sets_buildkite_environment(self) -> None:
|
def test_run_all_sets_buildkite_environment(self) -> None:
|
||||||
github = FakeGitHub()
|
github = FakeGitHub()
|
||||||
buildkite = FakeBuildkite([[], []])
|
buildkite = FakeBuildkite([[], []])
|
||||||
@@ -1102,6 +1265,29 @@ class RunCiCommandTest(unittest.TestCase):
|
|||||||
)
|
)
|
||||||
self.assertIn("Use `/amd-ci run`", github.comments[0])
|
self.assertIn("Use `/amd-ci run`", github.comments[0])
|
||||||
|
|
||||||
|
def test_amd_ci_retry_ignores_webhook_build_for_the_current_head(self) -> None:
|
||||||
|
github = FakeGitHub(
|
||||||
|
permission="read",
|
||||||
|
pr=make_pr(labels=[{"name": "ready"}]),
|
||||||
|
)
|
||||||
|
webhook_build = {
|
||||||
|
"created_at": "2026-08-18T01:00:00Z",
|
||||||
|
"meta_data": {},
|
||||||
|
"number": 122,
|
||||||
|
"pull_request": {"id": 42},
|
||||||
|
"source": "webhook",
|
||||||
|
"state": "passed",
|
||||||
|
"web_url": "https://buildkite.example/amd-ci/builds/122",
|
||||||
|
}
|
||||||
|
buildkite = FakeBuildkite([[webhook_build]])
|
||||||
|
|
||||||
|
run(make_event(COMMAND_RETRY_AMD_FAILED, "author"), github, buildkite)
|
||||||
|
|
||||||
|
self.assertEqual(buildkite.retry_calls, [])
|
||||||
|
self.assertIn(
|
||||||
|
"No AMD CI build exists for the current PR head", github.comments[0]
|
||||||
|
)
|
||||||
|
|
||||||
def test_ci_retry_creates_filtered_build_for_new_head(self) -> None:
|
def test_ci_retry_creates_filtered_build_for_new_head(self) -> None:
|
||||||
github = FakeGitHub(
|
github = FakeGitHub(
|
||||||
behind=100,
|
behind=100,
|
||||||
|
|||||||
@@ -237,9 +237,6 @@ benchmarks/**/*.json
|
|||||||
actionlint
|
actionlint
|
||||||
shellcheck*/
|
shellcheck*/
|
||||||
|
|
||||||
# Ignore moe/marlin_moe gen code
|
|
||||||
csrc/libtorch_stable/moe/marlin_moe_wna16/kernel_*
|
|
||||||
|
|
||||||
# Ignore ep_kernels_workspace folder
|
# Ignore ep_kernels_workspace folder
|
||||||
ep_kernels_workspace/
|
ep_kernels_workspace/
|
||||||
|
|
||||||
|
|||||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user