biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
15,260 Commits 2 Branches 140 Tags
2bfbdca23c60536f43850c9bec07fcc2b8f8e810
Commit Graph

10873 Commits

Author SHA1 Message Date
Matej Rojec
2908094567 Add /v1/chat/completions/batch endpoint for batched chat completions (#38011) 
Signed-off-by: Matej Rojec <64556640+MatejRojec@users.noreply.github.com>
 2026-03-26 12:13:33 +08:00
BadrBasowid
e6bf9f15ec [Bugfix][CI] Fix Marlin FP8 Linear Kernel for Compressed Tensors Format (#38092) 
Signed-off-by: BadrBasowid <Badr.Basowid@gmail.com>
Signed-off-by: BadrBasowid <61441185+BadrBasowid@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2026-03-25 21:11:43 -07:00
Woosuk Kwon
144030c84e Relocate Encoder CUDA graph manager (#38116) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
 2026-03-25 20:52:12 -07:00
Flora Feng
e2db2b4234 [Tool Parser][1/3] Pass tools to ToolParser constructor (#38029) 
Signed-off-by: sfeng33 <4florafeng@gmail.com>
 2026-03-26 10:29:06 +08:00
Chauncey
87f05d6880 [Revert] Remove DeepGEMM availability check in DeepseekV32IndexerMetadataBuilder (#38076) 
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
 2026-03-26 01:43:51 +00:00
Andreas Karatzas
36f6aede23 [Misc] Optimized check to encapsulate both CUDA and ROCm platforms (#34549) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
 2026-03-26 09:43:07 +08:00
Xin Yang
9704a5c310 Disable dual stream execution of input projection for Qwen3 (#38152) 
Signed-off-by: Xin Yang <xyangx@amazon.com>
 2026-03-26 01:20:39 +00:00
Wei Zhao
74056039b7 Fix minimax m2.5 nvfp4 kv scales weight loading (#37214) 
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
 2026-03-26 00:48:06 +00:00
Jacob Platin
d7d51a7ee5 [Bugfix] Fix Qwen3.5-FP8 Weight Loading Error on TPU (#37348) 
Signed-off-by: Jacob Platin <jacobplatin@google.com>
 2026-03-26 00:46:01 +00:00
Harry Mellor
3c3c084240 Various Transformers v5 fixes (#38127) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2026-03-26 00:10:08 +00:00
Ekagra Ranjan
7b54f60db0 [Cohere] Enable Cohere-Transcribe (#38120) 
Signed-off-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com>
 2026-03-25 16:13:51 -07:00
Rohan Potdar
a0e8c74005 [ROCm]: Update rope+kvcache fusion conditions and disable custom op by default (#36716) 
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
 2026-03-25 20:58:44 +00:00
Guillaume Guy
70a2152830 [MultiModal] add support for numpy array embeddings (#38119) 
Signed-off-by: guillaume_guy <guillaume.guy@airbnb.com>
Signed-off-by: Guillaume Guy <guillaume.c.guy@gmail.com>
Co-authored-by: guillaume_guy <guillaume.guy@airbnb.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
 2026-03-25 20:13:04 +00:00
Sathish Sanjeevi
978fc18bf0 [ROCm] Utilize persistent MLA kernel from AITER (#36574) 
Signed-off-by: Sathish Sanjeevi <sathish.krishnan.p.s@gmail.com>
 2026-03-26 03:00:42 +08:00
Andreas Karatzas
7d6917bef5 [ROCm] Fix MoE kernel test failures on gfx950 (#37833) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: Matthew Wong <Matthew.Wong2@amd.com>
 2026-03-25 13:46:40 -05:00
Mark McLoughlin
e38817fadb [Core][KV Connector] Remove use of num_cached_tokens in error handling (#38096) 
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
 2026-03-25 18:20:48 +00:00
Nick Hill
72cad44d3c [Frontend] Move APIServerProcessManager target server fn (#38115) 
Signed-off-by: Nick Hill <nickhill123@gmail.com>
 2026-03-25 18:14:41 +00:00
Cyrus Leung
ba2f0acc2d [Misc] Reorganize inputs (#35182) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2026-03-25 10:22:54 -07:00
Yongye Zhu
678b3c99e8 [MoE Kernel] Flashinfer nvfp4 cutedsl moe kernel integration (#38050) 2026-03-25 10:16:40 -07:00
Wentao Ye
1bf2ddd0ee [Refactor] Rename WAITING_FOR_FSM to WAITING_FOR_STRUCTURED_OUTPUT_GRAMMAR (#38048) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-03-25 11:41:44 -04:00
Wentao Ye
d7e93e13fb [Feature] EPLB Support for GPU Model Runner v2 (#37488) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-03-25 08:16:39 -07:00
Andrii Skliar
cd7643015e [Feature] Support per-draft-model MoE backend via --speculative-config (#37880) 
Signed-off-by: Andrii Skliar <askliar@nvidia.com>
Signed-off-by: [Andrii Skliar] <askliar@nvidia.com>
Co-authored-by: Andrii Skliar <askliar@nvidia.com>
 2026-03-25 14:31:52 +00:00
yjz
b745e8b5d3 [KVTransfer][Mooncake] Add heterogeneous TP support for disaggregated P/D in MooncakeConnector (#36869) 
Signed-off-by: JianDan0212 <zhangyj0212@gmail.com>
 2026-03-25 14:24:07 +01:00
Harry Mellor
d215d1efca [Mypy] Better fixes for the mypy issues in vllm/config (#37902) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2026-03-25 06:14:43 -07:00
Fadi Arafeh
34d317dcec [CPU][UX][Perf] Enable tcmalloc by default (#37607) 
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
 2026-03-25 20:39:57 +08:00
grYe99
7ac48fd357 [Model] Add AutoWeightsLoader support for jais (#38074) 
Signed-off-by: grYe99 <guorongye99@gmail.com>
Co-authored-by: grYe99 <guorongye99@gmail.com>
 2026-03-25 12:38:40 +00:00
Harry Mellor
d6bb2a9d9a Fix Plamo 2/3 & LFM2 for Transformers v5 (#38090) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2026-03-25 12:29:49 +00:00
Harry Mellor
1e673a43ce Better weight tying check for multimodal models (#38035) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2026-03-25 12:07:23 +00:00
Matthias Gehre
a889b7f584 [Bugfix] Pass drafter quant_config to ParallelLMHead in Eagle3 (#37280) 
Signed-off-by: Matthias Gehre <matthias.gehre@amd.com>
 2026-03-25 11:42:58 +00:00
Andreas Karatzas
f262a62aa1 [ROCm][CI] Fix flaky Cohere/OpenAI embedding parity test (#37616) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
 2026-03-25 10:55:51 +00:00
Andreas Karatzas
9ac2fcafbb [CI] Fix realtime WebSocket timeout deadlock and unhandled model validation errors (#37483) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
 2026-03-25 11:24:33 +01:00
Kunshang Ji
e9ae3f8077 [Hardware][XPU] Align memory usage with cuda on xpu (#37029) 
Signed-off-by: Kunshang Ji <jikunshang95@gmail.com>
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
 2026-03-25 18:14:29 +08:00
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
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
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
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
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
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
Ming Yang
c07e2ca6e0 Fix Mamba state corruption from referencing stale block table entries (#37728) (#37728) (#37728) 2026-03-24 10:29:59 -07:00