biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
13,533 Commits 2 Branches 140 Tags
4b3803d18044499962f331db0a1614b726110e2a
Commit Graph

3961 Commits

Author SHA1 Message Date
Patrick von Platen
5019c59dd2 [Voxtral Realtime] Introduce global log mel max (#33574) 
Signed-off-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2026-02-02 17:01:47 -05:00
Vasiliy Kuznetsov
0130223bd9 fix memory for online fp8 quantization with streaming weight load (#31914) 
Signed-off-by: vasiliy <vasiliy@fb.com>
 2026-02-02 14:17:42 -05:00
Yang Liu
199e3cb476 [Model] Use mm_position to compute mrope positions for GLM-4.xV (#33039) 
Signed-off-by: Yang <lymailforjob@gmail.com>
 2026-02-02 16:55:48 +00:00
Isotr0py
4061dcf4c5 [Bugfix] Enable Kimi k25 processor test (#33562) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2026-02-02 14:25:25 +00:00
danielafrimi
0aca8b8c62 [MoE] Enable Shared/Routed Overlap For Latent MoE (Nemotron-H) (#32790) 
Signed-off-by: dafrimi <dafrimi@nvidia.com>
 2026-02-02 09:18:50 -05:00
Cyrus Leung
b10d05b8a8 [Model] Use explicit types in get_generation_prompt (#33551) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2026-02-02 12:38:49 +00:00
Borushiki
b398e5c819 Update get_expert_mapping to include self parameter (#33525) 
Signed-off-by: Borushiki <38628261+Otsutsukii@users.noreply.github.com>
 2026-02-02 20:29:07 +08:00
Grzegorz K. Karch
78061ef584 Fix accessing hidden_act from model config (#32686) 
Signed-off-by: Grzegorz Karch <gkarch@nvidia.com>
 2026-02-02 11:11:33 +00:00
RED
808dd87b30 [Model] Support DeepSeek-OCR-2 (#33165) 
Signed-off-by: liuli <ll407707@alibaba-inc.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: liuli <ll407707@alibaba-inc.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2026-02-02 06:24:10 +00:00
csy0225
c3b40dc3e7 [Models] Step-3.5-Flash (#33523) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: i-zhangmingming <i-zhangmingming@stepfun.com>
Co-authored-by: xiewuxun <xiewuxun@stepfun.com>
Co-authored-by: zetaohong <i-hongzetao@stepfun.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
 2026-02-02 10:21:18 +08:00
will b.
46b4a02794 Fix DeepSeek V2 RoPE initialization error (#33501) 
Signed-off-by: Eduardo Salinas <edus@microsoft.com>
Signed-off-by: catswe <212922539+catswe@users.noreply.github.com>
Co-authored-by: Eduardo Salinas <edus@microsoft.com>
 2026-02-01 21:00:56 +00:00
shaharmor98
8869cd8ec1 Add MoE config for Super B200 TP2 (#33510) 2026-02-01 18:48:37 +00:00
JartX
cd86fff38f [BUGFIX] Fix hipErrorIllegalState in Qwen3-Omni during startup profiling allow inference Omni on ROCM (#33077) 
Signed-off-by: JartX <sagformas@epdcenter.es>
 2026-02-01 13:36:25 +00:00
Maral
b5f8c3092d [W8A8 Block Linear Refactor][1/N] Keep all quantization types into QuantFP8 class. (#33047) 
Signed-off-by: maral <maralbahari.98@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
 2026-02-01 09:28:01 +00:00
Eduardo Salinas
302ecf64ff [Models]: lfm2_siglip2 return intermediate encoder layers (#33370) 
Signed-off-by: Eduardo Salinas <edus@microsoft.com>
 2026-02-01 06:17:49 +00:00
René Honig
079781177a fix: Add SM120 (RTX Blackwell) support for FlashInfer CUTLASS NVFP4 MoE kernels (#33417) 
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
 2026-01-31 14:06:42 -08:00
Roy Wang
63c0889416 [Misc] Fix flashinfer related tests (#33462) 
Signed-off-by: esmeetu <jasonailu87@gmail.com>
 2026-01-31 16:10:24 -05:00
Cyrus Leung
88c3e114d8 [Refactor] Move MM data parsing outside processor (#33408) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2026-01-31 16:46:14 +00:00
Cyrus Leung
92924b2ddd [Deprecation] Remove deprecated items related to pooling (#33477) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2026-01-31 08:44:40 -08:00
ℍ𝕠𝕝𝕝𝕠𝕨 𝕄𝕒𝕟
13b842f271 [BugFix][Router Replay] Capture Logical Experts with EPLB (#33013) 
Signed-off-by: Hollow Man <hollowman@opensuse.org>
 2026-01-31 10:12:17 -05:00
Cyrus Leung
f0a1c8453a [Frontend] Use new Renderer for Completions and Tokenize API (#32863) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2026-01-31 04:51:15 -08:00
Jinwu
f68e3ea4e1 [BugFix] Add synchronize in CutlassW4A8LinearKernel to ensure data is ready for use. (#33078) 
Co-authored-by: jinwuguo <jinwuguo@tencent.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
 2026-01-31 08:14:54 +00:00
Fadi Arafeh
1618e25492 [CPU][Feat] Enable KleidiAI accelerated int4 dynamic quant with BF16 activations on Arm CPUs (#33122) 
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
 2026-01-31 07:16:22 +00:00
AutumnAurelium
f3888aca83 Add EAGLE3 support for AFMoE (#33111) 
Signed-off-by: AutumnAurelium <88015631+AutumnAurelium@users.noreply.github.com>
 2026-01-31 06:53:08 +00:00
Dimitrios Bariamis
f0bca83ee4 Add support for Mistral Large 3 inference with Flashinfer MoE (#33174) 
Signed-off-by: Dimitrios Bariamis <12195802+dbari@users.noreply.github.com>
Co-authored-by: Dimitrios Bariamis <12195802+dbari@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
 2026-01-30 22:48:27 -08:00
Matthias Gehre
73419abfae [Bugfix] Handle Asym W4A16 (ConchLinearKernel) for CT (#33200) 
Signed-off-by: Matthias Gehre <matthias.gehre@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-01-31 06:21:51 +00:00
Nicolò Lucchesi
e77f162cf5 [Bugfix] Fix Qwen3ASR language asr tag in output (#33410) 
Signed-off-by: NickLucche <nlucches@redhat.com>
 2026-01-31 05:24:49 +00:00
Patrick von Platen
15e0bb9c42 [Streaming -> Realtime] Rename all voxtral related classes, fn, files (#33415) 
Signed-off-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2026-01-31 04:49:00 +00:00
Matthew Bonanni
aaa901ad55 [Attention] Move MLA forward from backend to layer (#33284) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
 2026-01-30 19:30:00 -08:00
Wentao Ye
010ec0c30e [Deprecation] Deprecate seed_everything and scatter_mm_placeholders in v0.15 (#33362) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-01-31 02:54:16 +00:00
Gregory Shtrasberg
31aedfe7d6 [Bugfix][ROCm] Fixing the skinny gemm dispatch logic from #32831 (#33366) 
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
 2026-01-30 19:05:23 -06:00
Michael Goin
67ebaff528 Refactor NVFP4 Linear utils for ModelOpt and CT (#33201) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2026-01-30 16:37:42 -08:00
Pavani Majety
c3a9752b0c [Hardware][SM100] Add TRTLLM Kernel for INT4 W4A16 Kernel. (#32437) 
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
 2026-01-30 10:30:46 -08:00
xuebwang-amd
f451b4558b [Quantization][ROCm] Fix MoE weight loading to be robust (Qwen3_MoE/Qwen3_next as example models) (#33173) 
Signed-off-by: xuebwang-amd <xuebwang@amd.com>
 2026-01-30 17:50:23 +00:00
Vasiliy Kuznetsov
3f96fcf646 fix QERL attention import path (#33432) 
Signed-off-by: vasiliy <vasiliy@fb.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
 2026-01-30 09:29:09 -08:00
Michael Goin
fd0e377244 Support FP8 block quant for CompressedTensorsW8A16Fp8 (#33280) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2026-01-30 11:15:20 -05:00
Kyle Sayers
f857a03f6b [QeRL] Layerwise Reloading (#32133) 
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
 2026-01-30 08:50:05 -07:00
Frank Wang
8f5d51203b Disable Cascade Attention for Batch Invariance (#32561) 
Signed-off-by: frankwang28 <frank.wbb@hotmail.com>
Signed-off-by: Frank Wang <41319051+frankwang28@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
 2026-01-30 10:00:46 -05:00
Julien Denize
8e2ad97ad0 [BUGFIX] Pixtral cannot be loaded with --limit-mm-per-prompt 0 (#33406) 
Signed-off-by: juliendenize <julien.denize@mistral.ai>
 2026-01-30 02:52:02 -08:00
Patrick von Platen
10152d2194 [Realtime API] Adds minimal realtime API based on websockets (#33187) 
Signed-off-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
 2026-01-30 18:41:29 +08:00
杨朱 · Kiki
1a7894dbdf [Misc] Replace Optional[X] with X | None syntax (#33332) 
Signed-off-by: carlory <baofa.fan@daocloud.io>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-30 01:56:59 -08:00
tianshu-Michael-yu
f45870b53f fix: allow LFM2 MoE prefix caching (align) (#33376) 
Signed-off-by: Tianshu Yu <tianshuyu.formal@gmail.com>
 2026-01-30 08:23:14 +00:00
hujiaxin0
ba45bedfd1 [model] Add support for openPangu7B-VL (#32449) 
Signed-off-by: hujiaxin <524446785@qq.com>
Signed-off-by: Emilie1001 <79921183+Emilie1001@users.noreply.github.com>
Co-authored-by: Emilie1001 <79921183+Emilie1001@users.noreply.github.com>
 2026-01-30 15:54:27 +08:00
Harry Mellor
9432ed8c7e Explicitly set return_dict for apply_chat_template (#33372) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2026-01-30 07:27:04 +00:00
Isotr0py
8bfc8d5600 [Models] Refactor Kimi-K2.5 weight loading (#33346) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2026-01-30 05:31:20 +00:00
Wang Haoyu
c46b0cd0af [Model][Multimodal] Add explicit MusicFlamingo adapter (#32696) 
Signed-off-by: WangHaoyuuu <mailwhaoyu@gmail.com>
 2026-01-30 11:01:29 +08:00
Michael Goin
bfb9bdaf3f [Bugfix] Enable Triton MoE for FP8 per-tensor dynamic (#33300) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2026-01-29 12:15:17 -08:00
danisereb
8e2a469b3b Add Triton fused MoE config for B200 (Nemotron Nano) (#32804) 2026-01-29 19:21:33 +00:00
CarstyYou
23591e631e [Bugfix][Kernel] Fix negative memory offset in GDN Triton kernel (#33326) 
Signed-off-by: CarstyYou <186021327+CarstyYou@users.noreply.github.com>
 2026-01-29 10:40:11 -08:00
Linda
0493d897c4 [NVIDIA] [feat] Integrate flashinfer Trtllmgen bf16 moe (#32954) 
Signed-off-by: Linda-Stadter <57756729+Linda-Stadter@users.noreply.github.com>
 2026-01-29 10:00:13 -08:00