biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
15,217 Commits 2 Branches 140 Tags
14771f715085f5026919d30048329c3e822d4b3c
Commit Graph

15217 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Kunshang Ji
14771f7150 [XPU] support MLA model on Intel GPU (#37143) 
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
 2026-03-25 17:43:42 +08:00
Gregory Shtrasberg
189ddefbfd [ROCm] Attention selector reordering (#36702) 
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
Co-authored-by: Micah Williamson <micah.williamson@amd.com>
 2026-03-25 17:42:56 +08:00
Chauncey
09c3dc9186 [Revert] Remove CUDA torch fallbacks for fp8_mqa_logits/fp8_paged_mqa_logits_torch function (#37968) 
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
 2026-03-25 06:19:37 +00:00
vllmellm
42e9547976 [ROCm][Test] Fix ROCM_AITER_UNIFIED_ATTN attn+quant fusion test (#37640) 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2026-03-25 05:06:15 +00:00
Chauncey
a32783bb35 [Bugfix] Fix IndexError when accessing prev_tool_call_arr in OpenAIToolParser (#37958) 
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
 2026-03-25 12:06:21 +08:00
Baorun (Lauren) Mu
9d0351c91d [Docs] Add Encoder (ViT) CUDA Graphs section to CUDA Graphs design doc (#37914) 
Signed-off-by: Baorun Mu <bmu@nvidia.com>
 2026-03-24 19:53:24 -07:00
Artem Perevedentsev
a93a53f8a1 [Performance] Auto-enable prefetch on NFS with RAM guard (#37673) 
Signed-off-by: Artem Perevedentsev <aperevedents@nvidia.com>
 2026-03-24 17:31:14 -07:00
Andreas Karatzas
679c6a3ecc [Bugfix][ROCm][MoE] Fix mxfp4 oracle regressions from #37128 (#37787) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
 2026-03-25 08:17:33 +08:00
Andreas Karatzas
8bbb7c7f20 [ROCm][CI][PD] Add Hybrid SSM integration tests to CI (#37924) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
 2026-03-25 07:58:39 +08:00
Kevin H. Luu
af945615b5 [release] Move the rest of release jobs to release queue (#38044) 
Signed-off-by: khluu <khluu000@gmail.com>
 2026-03-24 16:40:58 -07:00
Terry Gao
82580b10ac [Perf] Disable inductor runtime asserts by default for serving perfor… (#37485) 
Signed-off-by: tianrengao <terrygao87@gmail.com>
Co-authored-by: Tianren Gao <tianren@fb.com>
 2026-03-24 19:37:51 -04:00
Netanel Haber
a0d487b2e1 nano_nemotron_vl: suppress readonly torch.from_numpy() warning in image and video resize paths (#37903) 
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
 2026-03-24 23:25:56 +00:00
Junhao
b73b5b0629 Make microbatch optimization (DBO) work with general models (#37926) 
Signed-off-by: Junhao Li <junhao@ubicloud.com>
 2026-03-24 14:40:08 -07:00
Michael Goin
0f0e03890e [UX] Add flashinfer-cubin as CUDA default dep (#37233) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2026-03-24 14:13:08 -07:00
Woosuk Kwon
4b53740d7f [MRV2] Fix for DS v3.2 (#38030) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-03-24 14:03:24 -07:00
Nick Hill
4e824d1c83 [Model Runner V2][Minor] Simplify PP logic (#38031) 
Signed-off-by: Nick Hill <nickhill123@gmail.com>
 2026-03-24 13:57:17 -07:00
amey asgaonkar
0c1809c806 Add Ubuntu 24.04 support for Docker builds (#35386) 
Signed-off-by: aasgaonkar <aasgaonkar@nvidia.com>
 2026-03-24 13:34:44 -07:00
liangel-02
8c47fdfdb1 [FlexAttention] allow custom mask mod (#37692) 
Signed-off-by: Angel Li <liangel@meta.com>
 2026-03-24 16:03:24 -04:00
Javier De Jesus
54b0578ada [Bugfix] Pass hf_token through config loading paths for gated model support (#37920) 
Signed-off-by: javierdejesusda <javier.dejesusj9@gmail.com>
 2026-03-24 15:22:05 -04:00
Richard Zou
89f572dbc0 [BugFix] fix VLLM_USE_STANDALONE_COMPILE=0 (#38015) 
Signed-off-by: Richard Zou <zou3519@gmail.com>
 2026-03-24 19:08:26 +00:00
Richard Zou
71a4a2fbd0 [BugFix] Fix order of compile logging (#38012) 
Signed-off-by: Richard Zou <zou3519@gmail.com>
 2026-03-24 18:58:18 +00:00
Nick Cao
935c46dd9b [Model] Add Granite 4.0 1B speech to supported models (#38019) 
Signed-off-by: Nick Cao <ncao@redhat.com>
 2026-03-24 18:23:41 +00:00
Willy Hardy
057fc94cbd [Bugfix] Fix structured output crash on CPU due to pin_memory=True (#37706) 
Signed-off-by: Willy Hardy <whardy@redhat.com>
Signed-off-by: Will Hardy <whardy@redhat.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-24 17:44:17 +00:00
Vineeta Tiwari
b58c5f28aa docs: fix broken offline inference paths in documentation (#37998) 
Signed-off-by: Vineeta Tiwari <vineeta.tiwari2@ibm.com>
Signed-off-by: Vineeta Tiwari <vineetatiwari2000@gmail.com>
Co-authored-by: Vineeta Tiwari <vineeta.tiwari2@ibm.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2026-03-24 17:35:14 +00:00
Ming Yang
c07e2ca6e0 Fix Mamba state corruption from referencing stale block table entries (#37728) (#37728) (#37728) 2026-03-24 10:29:59 -07:00
Dhruv Singal
4df5fa7439 [Bugfix] Force continuous usage stats when CLI override is enabled (#37923) 
Signed-off-by: Your Name <you@example.com>
Co-authored-by: Your Name <you@example.com>
Co-authored-by: OpenCode <noreply@openai.com>
 2026-03-24 10:29:50 -07:00
sihao_li
a5416bc52e [XPU] Support Intel XPU hardware information collection in usage stats (#37964) 
Signed-off-by: sihao.li <sihao.li@intel.com>
 2026-03-24 10:29:17 -07:00
Harry Mellor
b3601da6e7 [Mypy] Fix mypy for vllm/model_executor (except vllm/model_executor/layers) (#37904) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2026-03-24 17:14:01 +00:00
Dan Blanaru
dc78c2c933 [Core] add option to schedule requests based on full ISL (#37307) 
Signed-off-by: Dan Blanaru <48605845+DanBlanaru@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
 2026-03-24 13:01:12 -04:00
Sungjae Lee
4731884796 [Feature] limit thinking tokens (hard limit) (#20859) 
Signed-off-by: Sungjae Lee <33976427+llsj14@users.noreply.github.com>
Signed-off-by: Sungjae Lee <sung-jae.lee@navercorp.com>
Signed-off-by: Chauncey <chaunceyjiang@gmail.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2026-03-24 09:53:07 -07:00
Harry Mellor
8de5261e69 Update new contributor message (#37999) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2026-03-24 16:01:41 +00:00
wang.yuqi
1b6cb920e6 [Deprecate] Deprecate pooling multi task support. (#37956) 
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
 2026-03-24 14:07:47 +00:00
Li, Jiang
352b90c4a4 [Bugfix] Add replacement of _compute_slot_mapping_kernel on CPU (#37987) 
Signed-off-by: jiang1.li <jiang1.li@intel.com>
 2026-03-24 07:00:20 -07:00
Sage
1c0aabdeb0 [Bugfix] Suppress spurious CPU KV cache warning in launch render (#37911) 
Signed-off-by: Sage Ahrac <sagiahrak@gmail.com>
 2026-03-24 12:36:18 +00:00
Ilya Markov
14acf429ac [EPLB] Remove main waits in case of slow EPLB (#36271) 
Signed-off-by: ilmarkov <markovilya197@gmail.com>
 2026-03-24 11:50:44 +00:00
Harry Mellor
ce57fd5557 [Docs] Fix build (#37991) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2026-03-24 03:20:49 -07:00
Flora Feng
2e67fa756d Fix tool_parser_cls type annotation from Callable to type[ToolParser] (#37957) 
Signed-off-by: sfeng33 <4florafeng@gmail.com>
 2026-03-23 22:58:27 -07:00
Ronen Schaffer
e3c6c10cad [KV Offload] Refactor CPU offloading: pluggable CachePolicy, remove Backend abstraction, restructure into cpu/ package (#37874) 
Signed-off-by: Ronen Schaffer <ronen.schaffer@ibm.com>
 2026-03-24 07:02:51 +02:00
jetxa
16a664df24 [Frontend][Bugfix] Pass default_chat_template_kwargs to AnthropicServingMessages (#37899) 
Signed-off-by: jetxa <jetxzhang@outlook.com>
 2026-03-24 05:00:12 +00:00
Kevin H. Luu
7281199a8c [release] Move agent queue to Release cluster queues (#37783) 
Signed-off-by: khluu <khluu000@gmail.com>
 2026-03-23 20:36:47 -07:00
Kevin H. Luu
b2dd75eb48 Downsize CPU jobs to use small queue (#37913) 
Signed-off-by: khluu <khluu000@gmail.com>
Signed-off-by: Kevin H. Luu <khluu000@gmail.com>
 2026-03-23 20:36:37 -07:00
Wentao Ye
c59a132f96 [V0 Deprecation] Refactor kv cache from list to element (#37487) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-03-23 20:10:11 -07:00
Andreas Karatzas
de99d91ece [ROCm][CI] Split Entrypoints Integration (API Server 1) into 3 jobs (#37906) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
 2026-03-24 09:48:37 +08:00
Wentao Ye
83c9d525b6 [CI] Add batch invariant test: Block FP8 + small MOE (#37895) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-03-23 21:16:14 -04:00
Giancarlo Delfin
8f4824b664 [Model Runner V2] Gather multimodal embeddings before draft model postprocess (#37932) 
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
 2026-03-23 18:14:13 -07:00
roikoren755
56777b5c89 [Test] E2E Nemotron-3-Super tests (#36803) 
Signed-off-by: Roi Koren <roik@nvidia.com>
 2026-03-23 17:49:56 -07:00
Kevin H. Luu
2488a82f89 [CI] Split V1 Others into 3 separate jobs (#37016) 
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-24 06:44:38 +08:00
Ranran
dc6908ac6a [Bugfix] Register VLLM_BATCH_INVARIANT in envs.py to fix spurious unknown env var warning (#35007) 
Signed-off-by: Ranran <1012869439@qq.com>
Signed-off-by: Ranran <hzz5361@psu.edu>
Signed-off-by: ran <hzz5361@psu.edu>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
 2026-03-23 18:31:14 -04:00
yzong-rh
e85f8f0932 [Bug][MoE] Strengthen _supports_current_device() checks in the TRTLLM FP8, NVFP4, and FlashInfer CuteDSL MoE experts (#36728) 
Signed-off-by: Yifan Zong <yzong@redhat.com>
 2026-03-23 17:02:57 -04:00
Robert Shaw
5bf3c42d4c [Bug][MoE] Fix TRTLLM NVFP4 Routing Kernel Precision (#36725) 
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
 2026-03-23 20:19:06 +00:00