biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
14,367 Commits 2 Branches 140 Tags
cbd361fd468c29af00a4443b4f88cc216c6dcfe7
Commit Graph

14367 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
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
Asaf Gardin
bbf81f9a92 [Mamba1] - Kernel Level Chunk Alignment for Prefix Caching (#34798) 
Signed-off-by: Josephasafg <ajgard7@gmail.com>
 2026-03-01 20:40:23 +08:00
Woosuk Kwon
da543d1abe [Model Runner V2] Minor refactoring for EncoderRunner (#35628) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-03-01 00:15:39 -08:00
Ryan Rock
87d319c52f [AMD][CI] Support Triton attention with ExampleConnector (#34931) 
Signed-off-by: Ryan Rock <ryan.rock@amd.com>
 2026-03-01 09:58:07 +02:00
lin-shh
a9ec392c86 Fix typo: implictly -> implicitly in isaac.py docstring (#35646) 2026-02-28 23:34:37 -08:00
lailoo
afd089f231 [Bugfix][Model] Fix Qwen3.5/Qwen3Next ignoring --dtype flag on older GPUs (#35617) 2026-03-01 03:27:37 +00:00
gnovack
3ecd0bf9fc Add TMA support to fused_moe_lora kernel (#32195) 
Signed-off-by: gnovack <gnovack@amazon.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
 2026-03-01 10:55:25 +08:00
Woosuk Kwon
e3eb146f7a [Model Runner V2] Add ModelStateInterface [4/N] (#35621) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-02-28 13:19:45 -08:00
Martin Vit
95a395dbec [Bugfix] Fix Anthropic API base64 image handling in Messages endpoint (#35557) 
Signed-off-by: Martin Vit <martin@voipmonitor.org>
 2026-02-28 20:57:08 +00:00
Isotr0py
e94b263bd6 [Chore] Cleanup BNB utilization dead code (#35620) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2026-02-28 19:22:41 +00:00
Wentao Ye
e113a30113 [Deprecation] Deprecate code in 0.17 as scheduled (#35441) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
 2026-02-28 17:32:37 +00:00
Cyrus Leung
1dafb29f91 [Benchmark] Avoid unnecessary video download in MMVU (#35618) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2026-02-28 09:07:02 -08:00
emricksini-h
49b9ae32e9 [Fix] Avoid sending image input to other PP ranks (#35405) 
Signed-off-by: emricksini-h <emrick.birivoutin@hcompany.ai>
Co-authored-by: Roger Wang <hey@rogerw.io>
 2026-03-01 00:14:29 +08:00
cwazai
63d7972f13 Fix Qwen3_5MTP packed_modules_mapping for gate_up_proj (#35581) 2026-02-28 14:50:55 +00:00
flutist
c68e69f144 custom dataset img support base64 (#35280) 
Signed-off-by: xjx <493337577@qq.com>
 2026-02-28 11:49:52 +00:00
Chauncey
7e08c22b8c [Feat] Add CUDA torch fallbacks for fp8_mqa_logits/fp8_paged_mqa_logits_torch function (#35271) 
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
 2026-02-28 10:12:00 +00:00
Augusto Yao
8e75d88554 add io_process_plugin for sparse embedding (#34214) 
Signed-off-by: augusto.yjh <augusto.yjh@antgroup.com>
Signed-off-by: Augusto Yao <augusto.yjh@antgroup.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
 2026-02-28 09:16:37 +00:00
Mario Hong
0892d1ab1f [Feature]Supports Anthropic Thinking Block (#33671) 
Signed-off-by: mariohong <mariohong128@gmail.com>
Co-authored-by: zetaohong <i-hongzetao@stepfun.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
 2026-02-28 09:02:33 +00:00
Hashem Hashemi
7600642eae Add padding support to wvSplitK solution for skinny GEMMs (#33762) 
Signed-off-by: Hashem Hashemi <hashem.hashemi@amd.com>
 2026-02-28 09:02:05 +00:00
Andreas Karatzas
1e69c04887 [ROCm][CI] Parametrize vision score tests across attention backends with per-backend tolerances (#35571) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
 2026-02-28 08:59:26 +00:00
Cyrus Leung
4292e3b807 [Benchmark] Improve UX of sweep scripts (#35600) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2026-02-28 00:36:02 -08:00
Cyrus Leung
24d6ea8afd [Benchmark] Rename SLA Finder to Workload Explorer (#35586) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2026-02-27 23:31:55 -08:00
Chauncey
57c86c0741 [Misc] Change logging level from info to debug for tool parser import (#35575) 
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
 2026-02-28 14:51:35 +08:00
Chauncey
06254d4cbb [CI] add trainer_send_weights for MockWeightTransferEngine (#35589) 
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
 2026-02-28 06:47:43 +00:00
Andreas Karatzas
f5d1281c9d [ROCm][CI] Expose tests to AMD production CI and fix amdsmi heap corruption (#35071) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
 2026-02-28 13:57:31 +08:00
Andreas Karatzas
94029ffaf0 [ROCm] Derive device capability from GCN arch string without CUDA init (#35069) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
 2026-02-28 13:55:28 +08:00
Andreas Karatzas
88e8525f2e [ROCm][CI] Adding infiniband mappings for moriio tests (#35170) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
 2026-02-28 13:53:28 +08:00
Ilya Markov
b2d8b422b2 [EPLB] Enforce sync eplb for NCCL-based all2all backend (#35212) 
Signed-off-by: ilmarkov <markovilya197@gmail.com>
 2026-02-28 05:47:12 +00:00
Umut Polat
1d5ab5d603 [Bugfix] Move chat completion response_format validation to Pydantic model_validator (#35510) 
Signed-off-by: umut-polat <52835619+umut-polat@users.noreply.github.com>
 2026-02-27 21:26:19 -08:00
Huy Do
7b346ba8ed [Bugfix] Propagate compilation_time from workers to main process for TP>1 (#35503) 
Signed-off-by: Huy Do <huydhn@gmail.com>
 2026-02-28 05:03:22 +00:00
Itay Alroy
dea268336f [1/N] Elastic EP Milestone 2 (#34861) 
Signed-off-by: Yongji Wu <wuyongji317@gmail.com>
Signed-off-by: Itay Alroy <ialroy@nvidia.com>
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Signed-off-by: Ron Tourgeman <rtourgeman@nvidia.com>
Co-authored-by: Yongji Wu <wuyongji317@gmail.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Ron Tourgeman <rtourgeman@nvidia.com>
 2026-02-28 04:46:42 +00:00
Ma Jian
90805ff464 [CI/Build] CPU release supports both of AVX2 and AVX512 (#35466) 
Signed-off-by: jiang1.li <jiang1.li@intel.com>
Co-authored-by: jiang1.li <jiang1.li@intel.com>
 2026-02-28 04:35:21 +00:00
Matthew Bonanni
2562e0271e [MTP] Validate that MTP weights are actually loaded (#35548) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
 2026-02-28 12:27:40 +08:00
Cyrus Leung
fd68cd132b [Bugfix] Fixes for SLA finder (#35537) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2026-02-27 20:20:55 -08:00
Micah Williamson
0edf101d2b [ROCm] Add stablelm Head Size 80 To Supported Head Sizes For ROCM_ATTN (#35527) 
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
 2026-02-28 12:16:34 +08:00