Ning Xie and Simon Mo
a0f28d73a8
[sharded state loader] support pp in sharded state loader ( #52110 )
...
Signed-off-by: Andy Xie <andy.xning@gmail.com >
Co-authored-by: Simon Mo <simon.mo@hey.com >
2026-10-09 11:08:31 -07:00
premsurawut and Claude Opus 5.5
c811943137
[Bugfix][Frontend] Reject beam search with echo and logprobs in /v1/completions ( #60876 )
...
Signed-off-by: surawut.j <surawut.jirasaktavee@gmail.com >
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com >
2026-10-09 18:06:26 +00:00
1a3a7a8f01
[Bugfix] Treat max_tokens as output upper bound, not input-space reservation ( #57035 )
...
Signed-off-by: YuvrajSinghBhadoria2 <245782664+YuvrajSinghBhadoria2@users.noreply.github.com >
Signed-off-by: YuvrajSinghBhadoria2 <yuvrajsinghbhado2030@gmail.com >
Signed-off-by: Yuvraj Singh Bhadoria <yuvrajsinghbhado2030@gmail.com >
Co-authored-by: YuvrajSinghBhadoria2 <245782664+YuvrajSinghBhadoria2@users.noreply.github.com >
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk >
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com >
2026-10-10 01:15:22 +08:00
Andrey Talman and Andrey Talman
89ac8d971b
[CI][Test] Allow 10% ngram acceptance drop under preemption on CUDA in test_async_scheduling_accuracy ( #60715 )
...
pre-commit / pre-run-check (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Signed-off-by: Andrey Talman <atalman@users.noreply.github.com >
Co-authored-by: Andrey Talman <atalman@users.noreply.github.com >
2026-10-09 16:59:17 +00:00
stefankoncarevic
b74233860d
[CI][ROCm] Wait for VRAM to settle before building LLM in test_full_graph ( #60872 )
...
Signed-off-by: Stefan Koncarevic <Stefan.Koncarevic@amd.com >
2026-10-09 16:48:43 +00:00
Taewoong Kim and Cyrus Leung
75e3b17c05
[Frontend] Add cache salt support to generative scoring ( #60841 )
...
Signed-off-by: Taewoong Kim <ktw2172@gmail.com >
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk >
2026-10-09 16:07:50 +00:00
90ba2f34b5
[Build] Find compatible published wheels for precompiled installs ( #58871 )
...
Signed-off-by: greg pereira <grpereir@redhat.com >
Signed-off-by: mgoin <mgoin64@gmail.com >
Co-authored-by: mgoin <mgoin64@gmail.com >
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com >
2026-10-09 08:05:54 -07:00
Juan Pérez de Algaba and mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
3d52578e13
[Security] Do not retain Phi-4 MM audio attention matrices ( #60614 )
...
Signed-off-by: Juan Pérez de Algaba <jperezde@redhat.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-10-09 22:23:35 +08:00
Mikko Tukiainen and Cursor
81c993658e
[ROCm][Perf] Fuse main QK-norm/RoPE/gate and KV-cache write into the AMD QSA prepare launch ( #59732 )
...
Signed-off-by: Mikko Tukiainen <Mikko.Tukiainen@amd.com >
Co-authored-by: Cursor <cursoragent@cursor.com >
2026-10-09 21:14:49 +08:00
Suraj Sharan and linitra24
1ee69dde9c
[Bugfix][LoRA] Reject PEFT adapter features vLLM does not implement ( #60225 )
...
Signed-off-by: suraj <surajsharan85@gmail.com >
Co-authored-by: linitra24 <renshuang.zhou@daocloud.io >
2026-10-09 16:39:58 +04:00
Luca Motz and Claude Opus 5.5
83ed0c7c09
[Bugfix][NIXL] Fix receive post-process for different P/D block sizes ( #58860 )
...
Signed-off-by: Luca Motz <luca.motz@icloud.com >
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com >
2026-10-09 19:30:11 +08:00
Shreyansh Jain and Artem Perevedentsev
28d76f3bad
[Bugfix][Structured Output] Reject unsupported regex inside groups ( #60359 )
...
Signed-off-by: Shreyansh Jain <shreyanshjain646@gmail.com >
Signed-off-by: Artem Perevedentsev <aperevedents@nvidia.com >
Co-authored-by: Artem Perevedentsev <aperevedents@nvidia.com >
2026-10-09 14:16:13 +03:00
Chaojun Zhang
b027ac8312
[XPU] Support register KV offload mmap region as pinned host memory on XPU ( #51956 )
...
Signed-off-by: Chaojun Zhang <chaojun.zhang@intel.com >
2026-10-09 18:58:07 +08:00
Yan Ma
4e318ac563
[XPU] fix online fp8_per_channel quantization ( #56027 )
...
Signed-off-by: Yan Ma <yan.ma@intel.com >
2026-10-09 18:38:01 +08:00
Damien Laine and Cyrus Leung
2186b89a9a
[Bugfix][Model] Voxtral realtime: fix boot OOM and engine crash at max_model_len ( #45022 )
...
Signed-off-by: Damien Laine <damien.laine@gmail.com >
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk >
2026-10-09 17:40:29 +08:00
Harry Mellor and Claude Opus 5.5
2c99ee9333
[Chore] Remove vendored code made redundant by Transformers 5.16.1 ( #60623 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com >
2026-10-09 09:29:03 +00:00
Taewoong Kim and Chauncey
18c19eaf23
[Frontend] Add cache salt and tracing to structured decisions ( #60786 )
...
Signed-off-by: Taewoong Kim <ktw2172@gmail.com >
Co-authored-by: Chauncey <chaunceyjiang@gmail.com >
2026-10-09 08:53:50 +00:00
a6f43e57d6
[ROCm] Enable the cuMem CUDA-graph pool offload on ROCm ( #59523 )
...
Signed-off-by: aoshen02 <aoshen@inferact.ai >
Signed-off-by: indianspeedster <cspandey016@gmail.com >
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com >
Co-authored-by: indianspeedster <cspandey016@gmail.com >
2026-10-09 08:29:55 +00:00
Sriram Kumar
560fae64cd
[ROCm][Bugfix] Pass per-sequence context lengths to the AITER paged MQA-logits kernels ( #59420 )
...
Signed-off-by: Sriram Kumar <sriramkumar.kishorekumar@amd.com >
2026-10-09 08:16:20 +00:00
Maroon Ayoub and Claude
8a03ccf7b3
[Frontend] Add return_mm_kwargs to render requests ( #60728 )
...
Signed-off-by: Maroon Ayoub <mayoub@redhat.com >
Co-authored-by: Claude <noreply@anthropic.com >
2026-10-09 08:14:13 +00:00
f43e4c39e3
[Structured Output] Allow propertyNames with additionalProperties on xgrammar ( #57594 )
...
Signed-off-by: errmakov <ide404@gmail.com >
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 >
2026-10-09 10:49:47 +03:00
efaca9547d
[Perf][DSv4.1] Exchange packed FP8 Engram rows across DP and feed wkv MXFP8 ( #59923 )
...
Signed-off-by: Juntian Liu <Juntianl777@gmail.com >
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-10-09 15:30:18 +08:00
19c0bed584
[Fusion] Support 3D activation quantization fusion and enable it for Pixtral ( #59612 )
...
Signed-off-by: Jakub Zakrzewski <jzakrzewski@nvidia.com >
Co-authored-by: Codex <noreply@openai.com >
Co-authored-by: Misha Goin <mgoin64@gmail.com >
2026-10-09 15:12:03 +08:00
ad73a4740d
[Perf][DSv4.1] Trim the last KV-source layer in decoder replay ( #59894 )
...
Signed-off-by: Canlin <canlinguosdu@gmail.com >
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com >
Co-authored-by: Juntian Liu <Juntianl777@gmail.com >
2026-10-09 06:07:49 +00:00
8cbd5d0300
[Frontend] structured decisions: noul and score question types ( #60696 )
...
Signed-off-by: Matt Mastracci <matthew@mastracci.com >
Co-authored-by: DeepSeek <noreply@deepseek.com >
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com >
Co-authored-by: Misha Goin <mgoin64@gmail.com >
2026-10-09 04:48:16 +00:00
Rohan Potdar and Claude Opus 5.5
88a419649e
[ROCm][Kimi-K3] Use vLLM's FP8 max in the fused AttnRes quantization ( #60717 )
...
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com >
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com >
2026-10-09 04:45:13 +00:00
fa312090cb
[Frontend] Accept each connection on the least loaded API worker ( #60723 )
...
Signed-off-by: hao-aaron <aaronhao@inferact.ai >
Co-authored-by: aoshen02 <aoshen02@users.noreply.github.com >
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com >
2026-10-09 04:40:13 +00:00
e31b823bf5
[Bugfix][Tool Parser] Use LongCat tags in the LongCat structural tag ( #60747 )
...
Signed-off-by: hpdkhoa <hpdkhoa2311@gmail.com >
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com >
Co-authored-by: Flora Feng <4florafeng@gmail.com >
2026-10-08 21:20:54 -07:00
9824159d94
[Bugfix] Fix InternLM2 tool parser dropping characters from streamed arguments ( #60709 )
...
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com >
Co-authored-by: Claude <noreply@anthropic.com >
Co-authored-by: Flora Feng <4florafeng@gmail.com >
2026-10-08 21:20:49 -07:00
Vineeth Sai Varikuntla and Flora Feng
112a282915
[Bugfix][Frontend] Keep streamed completion text_offset in step with tokens ( #60668 )
...
Signed-off-by: Vineeth Sai <vineethsai4444@gmail.com >
Co-authored-by: Flora Feng <4florafeng@gmail.com >
2026-10-08 21:20:43 -07:00
Rémi Delhaye
a1cd0ec650
[Model] Add zerank-2 reranker ( #60415 )
...
Signed-off-by: rdlhio <contact@rdlh.io >
2026-10-09 03:01:51 +00:00
zzaebok and mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
702ce313f4
[Perf][Multimodal] Sort multimodal encoder inputs by modality ( #60196 )
...
Signed-off-by: Jaebok Lee <jaebok9541@naver.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-10-09 10:55:36 +08:00
Mia Ojeda and Lucas Wilkinson
4611c2c3d2
[BugFix][DiffusionGemma][CPU] Copy async output snapshots instead of aliasing reused buffers ( #59829 )
...
Signed-off-by: ojeda-e <eojeda@league.com >
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com >
2026-10-08 19:16:51 -07:00
201e537d98
[Bugfix][LoRA] Validate incompatible MoE adapter formats ( #59924 )
...
Signed-off-by: Brian Weston <brianweston@gmail.com >
Co-authored-by: Codex <noreply@openai.com >
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com >
Co-authored-by: linitra24 <renshuang.zhou@daocloud.io >
2026-10-09 09:49:13 +08:00
Nishant Revur and Claude
581692cc0f
[Bugfix][Spec Decode] Fix multimodal embedding merge in Llama 4 and Mistral Large 3 EAGLE drafters ( #57633 )
...
Signed-off-by: Nishant Revur <kumrfni@amazon.com >
Co-authored-by: Claude <noreply@anthropic.com >
2026-10-09 01:44:50 +00:00
DGlan
4274ae956c
[Bugfix][EC Connector] Release shared memory on NIXL setup failure ( #59875 )
...
Signed-off-by: DGlan <162426117+DGlan@users.noreply.github.com >
2026-10-08 17:38:16 -07:00
Kamran and Codex
8d10c38b73
[Perf] Reduce fallback decode CPU by 69% at 32K ( #60497 )
...
Signed-off-by: spa5k <79936503+spa5k@users.noreply.github.com >
Co-authored-by: Codex <codex@openai.com >
2026-10-08 21:42:56 +00:00
Yifan Qiao and Claude Opus 5.5
240785b82c
[Bugfix] Keep the GLM-5.3 kpool tail and Qwen4 QSA ring out of the null block ( #59528 )
...
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai >
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com >
2026-10-08 20:44:04 +00:00
sungbin1015 and Flora Feng
2ddde19e8e
[Frontend] Support min_p in the Responses API ( #48084 )
...
Signed-off-by: sungbin1015 <sbin@solbox.com >
Co-authored-by: Flora Feng <4florafeng@gmail.com >
2026-10-08 20:38:17 +00:00
ae9adec905
[Frontend] Expose /v1/systemone without an opt-in flag ( #60677 )
...
Signed-off-by: Francisco Javier Arceo <4163062+franciscojavierarceo@users.noreply.github.com >
Co-authored-by: Codex <noreply@openai.com >
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk >
2026-10-08 20:21:05 +00:00
72d59adc2c
[Bugfix][KV Connector][NIXL] Transfer the whole PLE short-conv page in disaggregated P/D ( #59997 )
...
Signed-off-by: Alberto Massidda <amassidda@nvidia.com >
Co-authored-by: Alberto Massidda <amassidda@nvidia.com >
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com >
Co-authored-by: Artem Perevedentsev <aperevedents@nvidia.com >
2026-10-08 23:58:13 +04:00
Matthew Bonanni and Claude Opus 5.5
1afb029839
[Bugfix][HiSparse] Route by swap-row capacity, not the index-group workspace ( #60682 )
...
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com >
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com >
2026-10-08 19:45:44 +00:00
c23ca06b6d
[Bugfix][Structured Output] Feed the token that implicitly ends reasoning to the grammar ( #59627 )
...
Signed-off-by: Simon Veitner <sveitner@redhat.com >
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com >
Co-authored-by: Misha Goin <mgoin64@gmail.com >
Co-authored-by: Yifan Zong <263738792+yzong-rh@users.noreply.github.com >
2026-10-08 19:38:33 +00:00
dingdangmao and Flora Feng
bab0ac61f8
[Bugfix][Frontend] Forward the reasoning wiring to the engine for batch chat completions ( #59263 )
...
Signed-off-by: apex-mochen <2756823972@qq.com >
Signed-off-by: sfeng33 <4florafeng@gmail.com >
Co-authored-by: Flora Feng <4florafeng@gmail.com >
2026-10-08 19:32:46 +00:00
Misha Goin and Claude
e3a29aa9b3
[Bugfix][MoE] Size the permute scratch from its inputs ( #60447 )
...
Signed-off-by: mgoin <mgoin64@gmail.com >
Co-authored-by: Claude <noreply@anthropic.com >
2026-10-08 15:32:07 -04:00
SeongJun Lee and Misha Goin
fff10d2072
[Attention] Allow an NVFP4 KV cache on SM90 with fa2 ( #60620 )
...
Signed-off-by: lesj0610 <lesj0610@gmail.com >
Co-authored-by: Misha Goin <mgoin64@gmail.com >
2026-10-08 12:16:22 -07:00
Kevin Li and Misha Goin
fc494822ea
[Test][Quantization] Gate CUTLASS W4A8 kernel tests to SM90 ( #58878 )
...
Signed-off-by: Kevin Li <kevinbean99@gmail.com >
Co-authored-by: Misha Goin <mgoin64@gmail.com >
2026-10-08 19:14:35 +00:00
Divakar Verma and Andreas Karatzas
18751bc6a7
[ROCm][CI] Add coverage for AiterExperts token padding: inf/nan garbage rows ( #59334 )
...
Signed-off-by: Divakar Verma <divakar.verma@amd.com >
Co-authored-by: Andreas Karatzas <akaratza@amd.com >
2026-10-08 19:11:45 +00:00
Aarushi Jain and Andreas Karatzas
9bbc581560
[Bugfix] Close MessageQueue zmq resources via finalizer to avoid exit ( #60472 )
...
Signed-off-by: aarushjain29 <aarushi.jain2@amd.com >
Co-authored-by: Andreas Karatzas <akaratza@amd.com >
2026-10-08 13:53:00 -05:00
Yeonwoo Sung and Flora Feng
56e6da2c47
[Bugfix][Frontend] Honor stop_token_ids on the Responses API ( #56592 )
...
Signed-off-by: YeonwooSung <neos960518@gmail.com >
Signed-off-by: sfeng33 <4florafeng@gmail.com >
Co-authored-by: Flora Feng <4florafeng@gmail.com >
2026-10-08 18:47:30 +00:00
