 TJian
|
599e75f432
|
[ROCm] [Bugfix] Fix DeepSeek V4 Functionality and Accuracy (#42810)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
|
2026-05-17 12:18:50 -04:00 |
|
|
Taneem Ibrahim
|
1c8e9c0399
|
Refactor: Pass num_labels explicitly to PoolerClassify instead of reading from global config (#42851)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
|
2026-05-17 14:40:21 +00:00 |
|
|
Artem PerevedentsevandVadim Gimpelson
|
0867497368
|
[CI/Build] Bump flashinfer to v0.6.11.post2 (#41711)
Signed-off-by: Artem Perevedentsev <aperevedents@nvidia.com>
Co-authored-by: Vadim Gimpelson <156319763+vadiklyutiy@users.noreply.github.com>
|
2026-05-16 14:55:12 -07:00 |
|
|
Taneem Ibrahim
|
787bc0d031
|
Add unit tests for pooler activation functions (#42824)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
|
2026-05-16 14:58:16 -04:00 |
|
|
Jiangyun Zhu
|
8a56da3845
|
[Experimental] Breakable CUDA graph (#42304)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
|
2026-05-16 22:04:12 +08:00 |
|
|
Michael Goin
|
852f567444
|
[Bugfix] Respect explicit --kv-cache-dtype over checkpoint kv_cache_scheme (#42782)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-05-15 17:15:52 -07:00 |
|
|
|
06d020bb6e
|
[Bugfix] Fix SM121 (DGX Spark) exclusion from Marlin/CUTLASS FP8 paths (#35568)
Signed-off-by: Blake Ledden <blake@secondnaturecomputing.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Pavani Majety <pmajety@nvidia.com>
|
2026-05-15 10:59:00 -07:00 |
|
|
Wentao Ye
|
491e8d8539
|
[Perf] Optimize MLA attention _v_up_proj bmm by removing additional copy (#42561)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-05-15 08:14:26 -07:00 |
|
|
L.B.R.andL.B.R.
|
d792d993c1
|
[ROCm] Widen OAI Triton MoE capability range to include gfx12 (RDNA4) (#37826)
Signed-off-by: L.B.R. <lbr@mmonad.com>
Co-authored-by: L.B.R. <lbr@mmonad.com>
|
2026-05-15 07:59:57 -07:00 |
|
|
bobofang_amdandTJian
|
ccde9540be
|
DeepSeekV4-Pro enable cuda graph full and piecewise mode (#42604)
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
|
2026-05-15 01:45:30 -07:00 |
|
|
|
fa2a33b893
|
[Quant] Consolidate GPTQ: rename gptq_marlin.py to auto_gptq.py (#38288)
Signed-off-by: Chengyi Nie <cnie@roblox.com>
Co-authored-by: Chengyi Nie <cnie@roblox.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-05-15 08:25:52 +08:00 |
|
|
Yongye ZhuandClaude
|
f8848b2f2d
|
[Bugfix] Add swiglu limits to deepgemm fp8 methods (#41986)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-05-14 15:43:13 -07:00 |
|
|
Charlie Fu
|
4cfcc0866f
|
[CI][ROCm] Remove unsupported cases in test_fusion.py (#38680)
Signed-off-by: charlifu <charlifu@amd.com>
|
2026-05-14 17:37:18 -04:00 |
|
|
TresandCursor
|
f887aa1a53
|
[Aiter][ROCm] RMSNormGated+GroupedQuantFP8 fusion (#40710)
Signed-off-by: Tres Popp <tres.popp@amd.com>
Signed-off-by: Tres Popp <trespopp@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-05-14 15:37:09 -04:00 |
|
|
Matthew Bonanni
|
9898f94abe
|
[Attention] Remove deprecated MLA prefill arguments (#42555)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
|
2026-05-14 10:34:06 -07:00 |
|
|
|
c7560af424
|
[RFC] Replace shared-memory routed experts with ModelRunnerOutput transfer and HTTP support (#39568)
Signed-off-by: xhx1022 <1737006628@qq.com>
Signed-off-by: arlenxu <arlenxu@tencent.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: arlenxu <arlenxu@tencent.com>
Co-authored-by: Junjie Zhang <junj.jay.zhang@gmail.com>
|
2026-05-14 14:12:30 +00:00 |
|
|
|
0a65d46628
|
[DSV4] Fuse norm and router for low latency scenario (#41263)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: jeejeelee <jeejeelee@verda-b300-05.datacrunch.io>
Co-authored-by: jeejeelee <jeejeelee@verda-b300-05.datacrunch.io>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-05-14 05:11:02 -07:00 |
|
|
Zhenzhong Xu
|
1ea9401364
|
[Quantization][Autoround][Toolkit] Add W4A16 Support (#39778)
Signed-off-by: Zhenzhong1 <zhenzhong.xu@intel.com>
Signed-off-by: Zhenzhong Xu <zhenzhong.xu@intel.com>
|
2026-05-14 19:18:49 +08:00 |
|
|
rasmith
|
768f4a6f26
|
[CI][AMD][BugFix] Prevent triton compiler error when running test_moe_layer with use_ep = True on ROCm (#40857)
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
|
2026-05-14 08:44:22 +00:00 |
|
|
aoshen02
|
8c79ad6580
|
Revert "[Core] Replace routing replay with device cache and async D2H pipeline" (#39917) (#42434)
Signed-off-by: aoshen02 <aoshen@inferact.ai>
|
2026-05-13 23:49:01 -07:00 |
|
|
Yongye ZhuandRoger Wang
|
0d2732dd91
|
[MLA Attention Backend] Add TOKENSPEED_MLA backend for DSR1/Kimi K25 prefill + decode on Blackwell (#41778)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
|
2026-05-13 23:48:02 -07:00 |
|
|
Rebecca Lee
|
fd7d858c8a
|
Use hidden_pad and intermediate_pad from vLLM #34301 (#42098)
Signed-off-by: Rebecca Lee <Rebecca.Lee@amd.com>
|
2026-05-14 14:21:04 +08:00 |
|
|
Kunshang Ji
|
751b9f14bd
|
[XPU][CT] Support mxfp8 moe model (#41918)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-05-14 09:47:10 +08:00 |
|
|
liangel-02
|
6b5c389ee3
|
expose flex block size for batch invariant mode (#41252)
Signed-off-by: Angel Li <liangel@meta.com>
|
2026-05-13 14:11:57 -07:00 |
|
|
Michael Goin
|
8efd508204
|
[Quantization] Rework quantization_config to use QuantKey and allow for activation override (#41566)
|
2026-05-13 16:58:32 -04:00 |
|
|
Wentao Ye
|
3f611f6106
|
[CI] Fix pre-commit issue (#42563)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-05-13 12:37:26 -07:00 |
|
|
fxmarty-amdandKyle Sayers
|
40330967ab
|
[Quark] Support loading Quark NVFP4 checkpoints in vLLM (#35859)
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
Signed-off-by: fxmarty-amd <felmarty@amd.com>
Co-authored-by: Kyle Sayers <kylesayrs@gmail.com>
|
2026-05-13 11:17:36 -07:00 |
|
|
TJianandYongye Zhu
|
a8887c208f
|
[Bugfix] [ROCm] [DSV4] [Perf] Add aiter mhc support (#41946)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
|
2026-05-13 21:43:15 +08:00 |
|
|
PikaPikachu
|
3b1ef03be4
|
[Bugfix][Quark] Fix W8A8 INT8 garbage outputs on Step-3.5-Flash (and other 3-key fused-MoE Quark exports) (#41892)
Signed-off-by: kangletian <kangletian@hotmail.com>
|
2026-05-13 11:59:49 +00:00 |
|
|
bnellnm
|
18f6bf5a21
|
[MoE Refactor] Add sequence parallel tests to test_moe_layer.py (#41299)
Signed-off-by: Bill Nell <bnell@redhat.com>
|
2026-05-12 21:52:19 -04:00 |
|
|
Wentao Ye
|
3d635c58c0
|
[Perf] Optimize MLA compute_prefill_context memory allocation (#42460)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-05-12 16:23:46 -07:00 |
|
|
bnellnmandRobert Shaw
|
d9b4990783
|
[MoE Refactor] EPLB refactoring for FusedMoE (#41055)
Signed-off-by: Bill Nell <bnell@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
|
2026-05-12 14:16:31 -04:00 |
|
|
|
4d591db470
|
[MoE Refactor] Introduce RoutedExperts alias for FusedMoE and don't store SharedExperts in MK (#40735)
Signed-off-by: Bill Nell <bnell@redhat.com>
Signed-off-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Signed-off-by: Robert Shaw <robertgshaw2@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Robert Shaw <robertgshaw2@gmail.com>
|
2026-05-12 13:37:44 -04:00 |
|
|
Jonathan MamouandWentao Ye
|
c8a6e272e0
|
[CPU] Fix rotary embedding for CPU without flash-attn ops (#42225)
Signed-off-by: jmamou <jonathan.mamou@intel.com>
Signed-off-by: Jonathan Mamou <jonathan.mamou@intel.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2026-05-12 15:05:35 +00:00 |
|
|
bnellnm
|
6427603ae8
|
[MoE Refactor] Move remaining experts classes to experts directory (#42334)
Signed-off-by: Bill Nell <bnell@redhat.com>
|
2026-05-12 09:19:46 -04:00 |
|
|
|
206eaed08d
|
[MoE Refactor] Move expert map related code into ExpertMapManager class (#41046)
Signed-off-by: Bill Nell <bnell@redhat.com>
Signed-off-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Signed-off-by: Robert Shaw <robertgshaw2@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Robert Shaw <robertgshaw2@gmail.com>
|
2026-05-12 09:18:27 -04:00 |
|
|
Thomas ParnellandClaude Opus 4.6
|
8f89381fc6
|
[Hybrid] Warmup Mamba2 SSD kernel (#39822)
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
|
2026-05-12 12:46:22 +00:00 |
|
|
Dipika Sikka
|
a7b801e26d
|
[MXFP4] Support for linear layers + compressed-tensors integration (#41664)
|
2026-05-12 07:49:33 -04:00 |
|
|
amitz-nv
|
ef34592a1a
|
[Bugfix] Fix double reduce in flashinfer_nvlink_two_sided and flashinfer_nvlink_one_sided backends (#41382)
Signed-off-by: amitz-nv <203509407+amitz-nv@users.noreply.github.com>
|
2026-05-12 07:47:47 +00:00 |
|
|
Nick Hillandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
bbee532988
|
[Perf][1/n] Eliminate various GPU<->CPU syncs (#41429)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-05-11 20:36:03 +00:00 |
|
|
Jee Jee LiandYongye Zhu
|
53181384e0
|
[Bugfix] Fix DSV4 swiglu_limit on marlin backend (#42287)
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
|
2026-05-11 13:03:56 -07:00 |
|
|
Vensenandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
6fdb49392e
|
[Bugfix] Fix int32 overflow in DeepGEMM SiLU/mul FP8 Triton kernel (#42201)
Signed-off-by: vensen <vensenmu@gmail.com>
Signed-off-by: Vensen <vensenmu@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
2026-05-11 14:52:31 -04:00 |
|
|
Hexiang Wang
|
7863fff6e5
|
[ROCm][DSv4] implement flash sparse mla with triton kernels (#41812)
Signed-off-by: whx-sjtu <xiaowang990929@gmail.com>
|
2026-05-11 09:27:11 -07:00 |
|
|
Wentao Ye
|
0d453e2336
|
[Perf] Batch invariance with Cutlass fp8 support, 28.9% E2E latency improvement (#40408)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2026-05-11 12:20:58 -04:00 |
|
|
Vadim Gimpelson
|
a2e776d716
|
[Bugfix] Accept canonicalized modelopt_* quant_method in _extract_modelopt_quant_algo (#42181)
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
|
2026-05-11 11:10:57 -04:00 |
|
|
Wentao Ye
|
4b64fc2cbf
|
[Refactor] Cleanup batch invariant dead code (#41993)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-05-11 10:48:39 -04:00 |
|
|
Rohan PotdarandElizaWszola
|
a51376b3f0
|
[Performance][DSR1]: Fused RoPE+KVCache+q_concat for MLA (#40392)
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
Signed-off-by: Rohan Potdar <66227218+Rohan138@users.noreply.github.com>
Co-authored-by: ElizaWszola <ewszola@redhat.com>
|
2026-05-11 14:10:50 +00:00 |
|
|
wangxiyuan
|
5536fc0c01
|
[Misc] Replace mamba_type string literals with MambaAttentionBackendEnum (#41188)
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
|
2026-05-11 03:59:36 +00:00 |
|
|
gnovackandgeorge
|
171019ab19
|
add fused mhc_post_pre kernel (#41536)
Signed-off-by: george <george@inferact.ai>
Co-authored-by: george <george@inferact.ai>
|
2026-05-10 19:56:52 -07:00 |
|
|
|
1b57eb41f2
|
[MoE] Move various experts classes to fused_moe/experts/ (#41979)
Signed-off-by: Jackmin801 <ongjackm@gmail.com>
Signed-off-by: Robert Shaw <robertgshaw2@gmail.com>
Signed-off-by: Jackmin801 <56836461+Jackmin801@users.noreply.github.com>
Signed-off-by: Bill Nell <bnell@redhat.com>
Co-authored-by: Jackmin801 <ongjackm@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Robert Shaw <robertgshaw2@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Jackmin801 <56836461+Jackmin801@users.noreply.github.com>
|
2026-05-11 07:54:33 +08:00 |
|