biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
14,451 Commits 2 Branches 140 Tags
1659b2e05804ff5c8a5b8dc3feaa4e66945592f4
Commit Graph

14451 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
aykoppol
25e02647c2 [Core] Add optional flags to check for repetitive token patterns in engine output (#35451) 
Signed-off-by: aykoppol <aykoppol+git@gmail.com>
 2026-03-03 12:23:25 +08:00
Woosuk Kwon
a0a5178ab4 [Model Runner V2] Use ModelState.prepare_attn() for cuda graph capture [5/N] (#35774) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-03-02 20:06:27 -08:00
Isotr0py
8ea8ba275e [V0 deprecation] Remove Swin model (#35821) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2026-03-02 20:03:41 -08:00
Woosuk Kwon
4f85bae9d6 [Docs][Model Runner V2] Add Design Docs (#35819) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-03-02 19:58:14 -08:00
Andy Lo
0a7165fd71 [ModelRunnerV2] Rename sampler functions and variables for clarity (#35459) 
Signed-off-by: Andy Lo <andy@mistral.ai>
 2026-03-02 19:48:56 -08:00
Robert Shaw
6521ccf286 [CI] Temporarily Disable Nightly Failures (#35770) 
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Signed-off-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
 2026-03-03 01:49:13 +00:00
Martin Vit
8ebd872f50 [Tool Parser] Fix Qwen3Coder streaming parameter loss with speculative decode (#35615) 
Signed-off-by: Martin Vit <martin@voipmonitor.org>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-03 09:40:37 +08:00
zhrrr
168ee03e1c [Model Runner V2][Perf] align dummy_run tokens to uniform decode for dp cudagraph (#35376) 
Signed-off-by: zhuhaoran <zhuhaoran.zhr@alibaba-inc.com>
 2026-03-02 17:10:47 -08:00
liuzhenwei
9dd656f0ea [XPU][NIXL] Add GPUDirect RDMA support for XPU (#35270) 
Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
 2026-03-03 08:42:49 +08:00
Jakub Zakrzewski
c8b678e53e [Model] Add support for nvidia/llama-nemotron-rerank-vl-1b-v2 (#35735) 
Signed-off-by: Jakub Zakrzewski <jzakrzewski@nvidia.com>
 2026-03-03 08:32:14 +08:00
Andreas Karatzas
18c29c746b [ROCm][CI] Fix backslash-continuation in pytest marker re-quoting and treat exit code 5 as success (#35798) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
 2026-03-02 16:07:51 -08:00
Hanjie Qiu
96fc09503a [All Reduce] Change default backend of Flashinfer All Reduce to trtllm (#35793) 
Signed-off-by: hjjq <hanjieq@nvidia.com>
 2026-03-02 18:57:38 -05:00
Roger Wang
1b82b433fc [Bugfix] Fix MM processor test for Qwen3.5 (#35797) 
Signed-off-by: Roger Wang <hey@rogerw.io>
 2026-03-02 23:05:08 +00:00
Robert Shaw
9319044ee9 [MoE][Perf] Wrap DSV3 QKVAProj GEMM in custom op for torch.compile (#35751) 
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
 2026-03-02 23:03:49 +00:00
Boyuan Feng
c42dc402c1 clean unused cudagraph_batch_sizes (#35552) 
Signed-off-by: Boyuan Feng <boyuan@meta.com>
 2026-03-02 22:00:16 +00:00
Ye (Charlotte) Qi
fa6a6be519 [Bugfix] Fix missing sequence_lengths in qwen3_omni_moe_thinker (#35741) 
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
 2026-03-02 21:11:56 +00:00
Aaron Hao
cad21918e3 [BUG] Fix rlhf_async example (#35788) 
Signed-off-by: ahao-anyscale <ahao@anyscale.com>
 2026-03-02 20:36:40 +00:00
Jeffrey Wang
53700bf49b [ci] Add Ray compatibility check informational CI job (#34672) 
Signed-off-by: Jeffrey Wang <jeffreywang@anyscale.com>
 2026-03-02 12:06:16 -08:00
Yashwant Bezawada
a13d8c03c9 [KVConnector] Auto-downgrade to PIECEWISE cudagraph mode for layerwise async ops (#31057) 
Signed-off-by: Yashwant Bezawada <yashwant_b@me.com>
 2026-03-02 15:04:47 -05:00
Fynn Schmitt-Ulms
9433acb8df [Spec Decode] Add hidden states extraction system (#33736) 
Signed-off-by: Fynn Schmitt-Ulms <fschmitt@redhat.com>
 2026-03-02 14:29:09 -05:00
Richard Zou
d1a6e96d9e [torch.compile] Improve cold and warm start compile tests (#35709) 
Signed-off-by: Richard Zou <zou3519@gmail.com>
 2026-03-02 19:27:06 +00:00
CSWYF3634076
2a9e3347e9 [BugFix][Model]Fix the garbled code in Ernie4.5-VL caused by fast_moe_cold_start (#35587) 
Signed-off-by: wangyafeng <wangyafeng@baidu.com>
 2026-03-02 18:56:33 +00:00
Isotr0py
cc0d565f40 [CI/Build] Enable Qwen3.5 tests on CI (#35763) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2026-03-02 17:43:53 +00:00
Patryk Wolsza
358e4d5ba7 [CI][HPU] Pin vllm commit compatible with vllm-gaudi - HPU tests (#35307) 
Signed-off-by: PatrykWo <patryk.wolsza@intel.com>
 2026-03-02 17:02:26 +00:00
Cyrus Leung
792a74b973 [Doc] Improve UX of --enable-log-requests (#35723) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2026-03-02 08:24:09 -08:00
Turner Jabbour
4034c3d32e [Core] Move test utility to test file (#35672) 
Signed-off-by: Turner Jabbour <doubleujabbour@gmail.com>
 2026-03-02 10:56:03 -05:00
Martin Hickey
7560d674c9 [CI] Fix mypy for vllm/device allocator (#35518) 
Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2026-03-02 15:53:18 +00:00
ElizaWszola
d9c7730877 [Performance] Extract kv update ops from MLA attention backends (#34627) 
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Di Wu <dw2761@nyu.edu>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
 2026-03-02 10:43:19 -05:00
Runkai Tao
ada4f4fadd [Fix Bug]num_active_loras always equals to zero (#34119) 
Signed-off-by: Runkai Tao <rt572@physics.rutgers.edu>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
 2026-03-02 23:17:46 +08:00
Harry Mellor
7e9149d9a9 [Docs] Add breadcrumbs for better UX (#35749) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2026-03-02 14:31:54 +00:00
Martin Hickey
87c98b0236 [MyPy][BugFix] Check profiler is assigned before calling start() on it (#35505) 
Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2026-03-02 13:23:42 +00:00
Tyler Michael Smith
de7dd634b9 Fix unresolved-import errors when using Astral's ty by removing src.root (#35681) 
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
 2026-03-02 10:26:47 +00:00
Chauncey
9a87b0578f [Feat] Supports Anthropic Messages count_tokens API (#35588) 
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
 2026-03-02 09:48:54 +00:00
wangxiyuan
510bc9e1df [Misc] Cleanup useless current_platform import (#35715) 
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
 2026-03-02 09:36:54 +00:00
Charles Ashby
cbd361fd46 [CPU][Distributed] Fix Enable _CPUSHMDistributed only when TP/PP ranks share the same SHM group name (#34169) 
Signed-off-by: Charles Ashby <charlesa.l@hotmail.com>
 2026-03-02 09:34:35 +00:00
Nicolò Lucchesi
c212202d93 [Misc] Bound NIXL upper bound version (#35495) 
Signed-off-by: NickLucche <nlucches@redhat.com>
 2026-03-02 16:57:07 +08:00
Andreas Karatzas
ec27b36b4b [CI] Defining extended V1 e2e + engine tests (#35580) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
 2026-03-02 08:10:54 +00:00
Charlie Fu
3fd1d4ec2c [Rocm][CI] Fix LM Eval Large Models (H100) test group (#34750) 
Signed-off-by: charlifu <charlifu@amd.com>
 2026-03-02 07:43:38 +00:00
EdalatiAli
cb21972a97 [Kernel] Integrate SM100 MXFP8 blockscaled grouped MM and quant kernels (#34448) 
Signed-off-by: EdalatiAli <aliedalati@cohere.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
 2026-03-01 23:31:19 -08:00
Andreas Karatzas
c34963f138 [ROCm][CI] Disable skinny GEMMs in language model standard tests to fix non-determinism (#35152) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
 2026-03-02 15:04:18 +08:00
Hongxia Yang
f26650d649 [ROCm] add amd-quark package in requirements for rocm to use quantized models (#35658) 
Signed-off-by: Hongxia Yang <hongxiay.yang@amd.com>
Co-authored-by: Hongxia Yang <hongxiay.yang@amd.com>
 2026-03-02 06:02:43 +00:00
Kunshang Ji
92f5d0f070 [XPU] fix mxfp4 activation type (#35691) 
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
 2026-03-02 11:48:39 +08:00
Jesse Cai
a60985b07e Fix deprecated v1 config tests (#35327) 
Signed-off-by: Jesse Cai <jessecai@fb.com>
 2026-03-01 20:32:03 -05:00
Lucas Wilkinson
8b5014d3dd [Attention] FA4 integration (#32974) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
 2026-03-01 23:44:57 +00:00
zhanqiuhu
57a96e26c9 Revert "[Bugfix] Disable TRTLLM attention with KV transfer enabled (#33192)" (#34832) 
Signed-off-by: Zhanqiu Hu <zh338@cornell.edu>
 2026-03-01 22:32:37 +00:00
Richard Zou
e82fbeec7b [torch.compile] Undo the fast_moe_cold_start hack in torch>=2.11 (#35475) 
Signed-off-by: Richard Zou <zou3519@gmail.com>
 2026-03-01 21:44:22 +00:00
haosdent
6290470843 [Bugfix] Fix dtype mismatch in RMSNormGated.forward_native() during torch.compile (#35256) 
Signed-off-by: haosdent <haosdent@gmail.com>
 2026-03-01 15:14:46 -05:00
Woosuk Kwon
72f4d16262 [Model Runner V2] Use block table apis for capture inputs (#35671) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-03-01 10:31:13 -08:00
Seungho Yoon
5a435507d8 fix(mxfp4): return is_monolithic=False when LoRA is enabled for Triton backend (#35382) 
Signed-off-by: Seungho Yoon <yoonsnowdev@gmail.com>
 2026-03-01 09:59:30 -05:00
Taneem Ibrahim
59d7af9c6c [MISC] Fixing a null reference by removing parallel_utils from mypy EXCLUDE (#35630) 
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
 2026-03-01 09:26:44 -05:00