|
d33872dfeb
|
[Feat] Structured decisions endpoint (/v1/systemone) (#59299)
Signed-off-by: Matt Mastracci <matthew@mastracci.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Francisco Javier Arceo <4163062+franciscojavierarceo@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Francisco Javier Arceo <4163062+franciscojavierarceo@users.noreply.github.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
|
2026-10-08 14:48:12 +00:00 |
|
|
yhcheong (vllmellm)
|
273e099693
|
[Bugfix][ROCm] Select page-aligned kernel blocks for pooled indexers so the block table addresses storage pages (GLM-5.3-Flash) (#59412)
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
|
2026-10-08 14:44:58 +00:00 |
|
|
zzaebok
|
2f7f05c256
|
[Bugfix][MoRIIO] Prevent remote KV reload after decoder preemption (#53250)
Signed-off-by: Jaebok Lee <jaebok9541@naver.com>
|
2026-10-08 22:28:16 +08:00 |
|
|
|
daa9085143
|
[KV Connector][NIXL] Register HiSparse host pool under single TP Rank (#60161)
Signed-off-by: Pravein Govindan Kannan <pravein.govindan.kannan@ibm.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-08 07:25:02 -07:00 |
|
|
Matthew BonanniandClaude Opus 5.5
|
4ed4c4433b
|
[Bugfix][HiSparse] Drop the unaccounted, write-only prefill mirror staging buffer (#60429)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-08 14:00:49 +00:00 |
|
|
Vineeth Sai VarikuntlaandHarry Mellor
|
194da61de1
|
[Bugfix] Reject negative --device-ids indices instead of selecting the wrong device (#49053)
Signed-off-by: Vineeth Sai <vineethsai4444@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-10-08 13:01:25 +00:00 |
|
|
|
458ba2edf8
|
[ROCm][Kimi-K3] Fuse AttnRes output with per-token FP8 input quantization (#59069)
Signed-off-by: whx-sjtu <xiaowang990929@gmail.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: Fangzhou Ai <31551580+Fangzhou-Ai@users.noreply.github.com>
|
2026-10-08 12:01:47 +00:00 |
|
|
|
73c742b09c
|
[Bugfix] Make disable_any_whitespace actually disable whitespace on xgrammar (#58067)
Signed-off-by: Stu Cao <stu@primeintellect.ai>
Signed-off-by: Artem Perevedentsev <aperevedents@nvidia.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Artem Perevedentsev <aperevedents@nvidia.com>
|
2026-10-08 14:41:14 +03:00 |
|
|
devshah-cohereandBugen Zhao
|
b49c921a27
|
[Bugfix][Rust Frontend] Always include token_ids in completion stream choices (#60286)
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Signed-off-by: devshah-cohere <dev.shah@cohere.com>
|
2026-10-08 19:11:55 +08:00 |
|
|
Andy Lo
|
ba77c4c130
|
[Bugfix][Attention] Preserve small FP8 softmax weights in Triton attention (#60156)
Signed-off-by: Andy Lo <andy@mistral.ai>
|
2026-10-08 12:35:22 +02:00 |
|
|
Nicolò Lucchesi
|
e161a0798c
|
[Perf][Core] Reduce free KV cache queue overhead (#60269)
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
|
2026-10-08 10:17:11 +00:00 |
|
|
wang.yuqi
|
459764104d
|
[Frontend] Move offline_utils.py to entrypoints/common. (#58052)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
|
2026-10-08 09:56:05 +00:00 |
|
|
Muhammad Usman MateenandMisha Goin
|
e73895a5df
|
[Bugfix] Make suppress_stdout redirect fd 1 instead of sys.stdout.fileno() (#59336)
Signed-off-by: usmanmateen <usmanmateen255@gmail.com>
Co-authored-by: Misha Goin <mgoin64@gmail.com>
|
2026-10-08 09:52:50 +00:00 |
|
|
Chaojun Zhang
|
dfaabf91ac
|
[XPU] [CI] Fix stale ignore path for weight_transfer_metrics tests on Intel CI (#60558)
Signed-off-by: Chaojun Zhang <chaojun.zhang@intel.com>
|
2026-10-08 17:48:47 +08:00 |
|
|
Kevin H. LuuandClaude Opus 5.5
|
24be8c0bca
|
[CI] Remove dead in-tree TPU (torch_xla) CI scripts (#60591)
Signed-off-by: khluu <khluu000@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-08 02:42:07 -07:00 |
|
|
Jiangyun ZhuandClaude Opus 5.5
|
e265b77982
|
[CI][Mamba] Use well-conditioned prompts for FlashInfer ReplaySSM parity tests (#60515)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-08 17:39:56 +08:00 |
|
|
|
7816afdb25
|
[Bugfix][Core] Drain async KV loads in pause(mode="wait"), and pause the drain test only once a request is in flight (#60572)
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Signed-off-by: Stefan Koncarevic <Stefan.Koncarevic@amd.com>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-08 09:33:41 +00:00 |
|
|
Kevin H. LuuandClaude Opus 5.5
|
c4cd88d9fe
|
[CI] Make (H100) Distributed DP + EP optional (#60540)
Signed-off-by: khluu <khluu000@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-08 02:31:13 -07:00 |
|
|
Harry MellorandClaude Opus 5.5
|
21d9758459
|
Remove Python 3.10 support now that it is EOL (#60402)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-08 02:30:52 -07:00 |
|
|
liuzhenweiandKunshang Ji
|
0004536dd0
|
[XPU][Graph] Replace boolean-mask assignment with torch.where (#60529)
Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-10-08 17:13:48 +08:00 |
|
|
Nicolò Lucchesi
|
70bdce6133
|
[Model][GLM-5.3-Flash] Warm up the DCP top-k merge kernels for the kpool indexer (#60032)
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
|
2026-10-08 11:05:52 +02:00 |
|
|
|
7d47ac2ddb
|
[CI] Enroll five steps in automatic sharding (#60492)
Signed-off-by: Thang Nguyen <thangnguyenvn647@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: khluu <khluu000@gmail.com>
|
2026-10-08 01:52:59 -07:00 |
|
|
Paweł Mańczak
|
4cf1307e72
|
[XPU] Add tuned Mamba SSU configs for 2 more B70 shapes (#57565)
Signed-off-by: pmanczak <pawel.manczak@intel.com>
|
2026-10-08 16:36:05 +08:00 |
|
|
Ting SUN
|
0f112d1800
|
[Bugfix][Pooling] Preserve cache_salt for chunked embeddings (#47696)
Signed-off-by: Ting Sun <suntcrick@gmail.com>
|
2026-10-08 07:33:28 +00:00 |
|
|
Alec
|
29ae81fe83
|
[Rust Frontend] Preserve explicit zero sampling values in gRPC requests (#60115)
Signed-off-by: Alec Flowers <aflowers@nvidia.com>
|
2026-10-08 07:27:47 +00:00 |
|
|
Rehan KhanandBob
|
fd0216d3b5
|
[Bugfix][CPU] Fix fused Gumbel-max wrapping-window bias (#60221)
Signed-off-by: Rehan Khan <Rehan.Khan7@ibm.com>
Co-authored-by: Bob <bob@ibm.com>
|
2026-10-08 15:15:53 +08:00 |
|
|
ARAVINDHAN Tandlinitra24
|
e58f8dde7f
|
[Bugfix] Use FusedMoEWithLoRA for shared MoE LoRAs on 3D models (#60098)
Signed-off-by: ARAVINDHAN T <arvindhant01@gmail.com>
Co-authored-by: linitra24 <renshuang.zhou@daocloud.io>
|
2026-10-08 15:04:32 +08:00 |
|
|
xiangdong
|
032d39e9b4
|
[XPU][CI] Split Intel jobs to improve B50 utilization (#58817)
Signed-off-by: zengxian <xiangdong.zeng@intel.com>
Signed-off-by: xiangdong <40376367+zxd1997066@users.noreply.github.com>
|
2026-10-08 14:53:37 +08:00 |
|
|
stefankoncarevicandAndreas Karatzas
|
814301b268
|
[Bugfix][Quant] Read safetensors headers of checkpoints with other file names (#60411)
Signed-off-by: Stefan Koncarevic <Stefan.Koncarevic@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-10-08 01:38:41 -05:00 |
|
|
Vadim GimpelsonandClaude
|
ee406adf0c
|
[Bugfix] Fix ZeroDivisionError in Qwen3-VL video sampling when the source fps is unknown (#60501)
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-10-08 06:28:44 +00:00 |
|
|
|
f226af0e11
|
[Bugfix] Eliminate frontend ZMQ port TOCTOU with inherited listeners (#54113)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-08 06:25:27 +00:00 |
|
|
|
fb2ac82458
|
[ROCm][DSv4.1][Perf] Replace the Torch prefill combine with the shared combine_topk_swa_indices kernel (#56638)
Signed-off-by: JohnQinAMD <yanyuan.qin@amd.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Ren Yuzhou <54501155+yuzhouo7@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Douglas Lehr <91553416+dllehr-amd@users.noreply.github.com>
|
2026-10-08 14:15:18 +08:00 |
|
|
Shanshan Shen
|
95307ac6d4
|
[Doc] Update ViT CUDA graph design doc (#60519)
Signed-off-by: Shanshan Shen <87969357+shen-shanshan@users.noreply.github.com>
|
2026-10-08 14:00:58 +08:00 |
|
|
Jiahan Chang (Cyrus)
|
816173ca9d
|
[Kernel] Remove WAR for LL CuTeDSL BF16 GEMM (#60434)
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
|
2026-10-08 05:38:07 +00:00 |
|
|
|
81198e97ba
|
[Refactor] Abstract DeepGemm MegaMOE backend (#58053)
Signed-off-by: Hui Shi <kalinshi@tencent.com>
Co-authored-by: LuneExplorer <liyihan23@mails.tsinghua.edu.cn>
Co-authored-by: ArmageddonKnight <bojian@cs.toronto.edu>
|
2026-10-08 05:05:39 +00:00 |
|
|
|
4ac0179f8a
|
[ROCm][Perf] Use native merge_attn_states kernel on gfx942/gfx950 (#60159)
Signed-off-by: mghanimi <mghanimi@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Douglas Lehr <91553416+dllehr-amd@users.noreply.github.com>
|
2026-10-08 04:49:49 +00:00 |
|
|
|
775792f2d5
|
[Bugfix] Reland #53020: tie lm_head.weight for Nemotron Parse when checkpoint omits it (#60272)
Signed-off-by: Anish Kumar <aniskumar@nvidia.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
|
2026-10-08 04:40:55 +00:00 |
|
|
|
4187ade7b8
|
[Frontend] Consolidate rl entrypoints. (#57849)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-07 21:37:11 -07:00 |
|
|
|
1fbbfa1657
|
[Bugfix][Kimi-K3] Declare max_tp_shards on the DSpark MLA KV cache spec (#59733)
Signed-off-by: hyukjlee <hyukjlee@amd.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Summer Yang <girasoleyang@gmail.com>
|
2026-10-08 00:33:32 -04:00 |
|
|
MattandClaude Opus 5.5
|
5dd4a628dd
|
[ROCm][Bugfix] Map sleep-mode cuMem memory for the host (#60367)
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
|
2026-10-08 04:26:12 +00:00 |
|
|
Isotr0pyandShanshan Shen
|
8352b2427f
|
[Multimodal] Optimize encoder cudagraph padding logic (#58925)
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Shanshan Shen <467638484@qq.com>
|
2026-10-08 03:38:09 +00:00 |
|
|
Simon DanielssonandDouglas Lehr
|
87d9996abe
|
[ROCm][Perf][GLM-5.3-Flash] BF16 splitk kernel for sparse MLA decode (#58584)
Signed-off-by: simondanielsson <simon.danielsson99@hotmail.com>
Co-authored-by: Douglas Lehr <91553416+dllehr-amd@users.noreply.github.com>
|
2026-10-07 21:37:51 -05:00 |
|
|
bnkaiteamandFlora Feng
|
3722645539
|
[Bugfix][Frontend] Accept successful 2xx responses for batch output uploads (#60507)
Signed-off-by: bnkaiteam <bnkaiteam@gmail.com>
Co-authored-by: Flora Feng <4florafeng@gmail.com>
|
2026-10-08 02:32:35 +00:00 |
|
|
|
caff2b44cb
|
[BugFix] Pick the DP world-group port at bind time via the coordination store (#51018)
Signed-off-by: aoshen02 <aoshen02@users.noreply.github.com>
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: aoshen02 <aoshen02@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-10-08 02:30:35 +00:00 |
|
|
wangxiyuanandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
a4b14e57b6
|
[Platform] Allow BackendEnum dynamic register (#41091)
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-10-08 09:56:19 +08:00 |
|
|
MattandClaude Opus 5.5
|
9dba339d07
|
[Bugfix][ROCm] Keep MLA derived weights in place on weight reload (#60389)
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
|
2026-10-07 20:38:06 -05:00 |
|
|
Nicolò Lucchesi
|
8733a21d55
|
[Core] Bound execute_dummy_batch RPC waits by the execute-model timeout (#60398)
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
|
2026-10-08 01:22:04 +00:00 |
|
|
Junyi Yaoandsfeng33
|
fdfc171a74
|
[Bugfix][ToolParser] Stream every tool call when one delta completes several (#60354)
Signed-off-by: Junyi Yao <j.yao@wustl.edu>
Signed-off-by: sfeng33 <4florafeng@gmail.com>
Co-authored-by: sfeng33 <4florafeng@gmail.com>
|
2026-10-08 01:07:35 +00:00 |
|
|
|
2dd887426e
|
[Bugfix][Frontend] Do not modify caller params in LLM.score() (#59959)
Signed-off-by: 叮当猫 <2756823972@qq.com>
Signed-off-by: apex-mochen <2756823972@qq.com>
Co-authored-by: DeepSeek Harness <noreply@deepseek.com>
Co-authored-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-10-08 09:03:08 +08:00 |
|
|
|
9e3e37cb3c
|
[TEST][XPU][CI] disable tests of unsupported quantization (#60383)
Signed-off-by: microslaw <you@example.com>
Co-authored-by: microslaw <you@example.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-10-08 08:56:28 +08:00 |
|