biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
14,087 Commits 2 Branches 140 Tags
5719a4e4e601fb91274294d25370b7aad656d629
Commit Graph

2299 Commits

Author SHA1 Message Date
Kata Coder
5719a4e4e6 [Frontend] Support multimodal inputs for late-interaction scoring (ColQwen3) + NewModel: nvidia/nemotron-colembed (#34574) 
Signed-off-by: craftsangjae <craftsangjae@gmail.com>
 2026-02-20 20:01:40 -08:00
pougetat
11be2c74dc [Realtime] Add Qwen3-ASR realtime streaming support (#34613) 
Signed-off-by: Thomas Pouget-Abadie <thomaspou@microsoft.com>
Co-authored-by: Thomas Pouget-Abadie <thomaspou@microsoft.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
 2026-02-20 19:59:42 -08:00
Lucas Wilkinson
0e22cd618b Revert "[Llama4,Quantization] Simplify and generalize logic for Q/K permutations in quantized self-attn layers " (#34997) 2026-02-20 17:19:19 -08:00
Wei Zhao
ea5f903f80 Bump Flashinfer Version and Re-enable DeepSeek NVFP4 AR+Norm Fusion (#34899) 
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
 2026-02-20 13:37:31 -08:00
tianshu-Michael-yu
ea37530b47 [Models] LFM2: Support LoRA (#34921) 
Co-authored-by: Piotr Mazurek <piotr635@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
 2026-02-19 22:07:23 -08:00
Wentao Ye
c683d11c94 [Refactor] Deprecate head_first for chunk_gated_delta_rule (#34263) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-02-19 13:23:49 -05:00
roikoren755
3eff45d793 Revert "[NemotronH] Do not force router to run in fp32 (#34582)" (#34808) 
Signed-off-by: Roi Koren <roik@nvidia.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
 2026-02-19 09:47:05 -08:00
Robert Shaw
4685a630a2 [Model Bash][DeepSeekR1] Remove Shared Expert Clone (#34344) 
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
 2026-02-19 07:56:14 -08:00
Eldar Kurtić
ee1d25f199 [Llama4,Quantization] Simplify and generalize logic for Q/K permutations in quantized self-attn layers (#34471) 
Signed-off-by: Your Name <you@example.com>
Co-authored-by: Your Name <you@example.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
 2026-02-19 07:55:41 -08:00
Linda
6fff24f30f [Bugfix] Qwen3.5 kv-scale weight remapping (#34719) 
Signed-off-by: Linda-Stadter <57756729+Linda-Stadter@users.noreply.github.com>
 2026-02-19 04:13:37 -08:00
Tal Nir
f75b61a9e9 [Voxtral Realtime] Fix engine crash on empty multimodal embeddings (#34862) 
Signed-off-by: Tal Nir <tal@nervexneurotech.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-18 23:21:47 -08:00
Wei Zhao
7f51e93864 [Bug] Fix DeepSeek V3 weight loading caused by incorrect prefix (#34876) 
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
 2026-02-18 23:20:30 -08:00
Alex Brooks
4611af1663 [Bugfix] Add Quant Config to Llava Next Projector (#34847) 
Signed-off-by: Alex Brooks <albrooks@redhat.com>
 2026-02-18 23:18:23 -08:00
Manrique Vargas
ad5aa6bd9f fix(docs): fix typos in comments and docstrings (#34836) 
Signed-off-by: machov <mv1742@nyu.edu>
 2026-02-18 23:17:41 -08:00
Isotr0py
c0bd8b13da [Bugfix] Redo Qwen3.5/Qwen3-Next GDN projector fusion (#34697) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: JJJYmmm <92386084+JJJYmmm@users.noreply.github.com>
 2026-02-18 09:46:53 -08:00
Robert Shaw
6874638bc4 [Model Bash] DeepSeek R1 BF16 Min Latency QKV A GEMM (0.5% E2E Speedup) (#34758) 
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
 2026-02-18 07:42:36 -08:00
Michael Goin
909b147197 [Bugfix] Fix prefix creation for Qwen3.5 (#34723) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2026-02-17 23:39:15 -08:00
Cyrus Leung
a0d8d944e2 [Renderer] Move MM Hash parsing into Renderer (#34711) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2026-02-17 19:18:55 -08:00
Cyrus Leung
574fe75245 [Renderer] Move InputPreprocessor into Renderer (2/2) (#34560) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2026-02-17 05:29:01 -08:00
Jiangyun Zhu
1d65283e95 Revert "[Models] Fuse Qwen3.5 GDN's qkvz_proj and ba_proj" (#34683) 2026-02-17 01:29:27 -08:00
roikoren755
3b30e61507 [NemotronH] Do not force router to run in fp32 (#34582) 
Signed-off-by: Roi Koren <roik@nvidia.com>
 2026-02-16 10:15:32 -08:00
Andreas Karatzas
03a8770a6d [ROCm][CI] Fix plugins test group; updating terratorch and dependencies (#34589) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
 2026-02-16 07:33:42 -08:00
Isotr0py
3bb4e4311c [Models] Fuse Qwen3.5 GDN's qkvz_proj and ba_proj (#34492) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2026-02-16 07:32:51 -08:00
Cyrus Leung
ec17bdd894 [Renderer] Move InputPreprocessor into Renderer (1.5/2) (#34598) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2026-02-15 23:46:33 -08:00
Isotr0py
91ac5d9bfd [CI/Build] Enable tests for recent day-0 new models (#34585) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2026-02-15 18:17:04 -08:00
Luka Govedič
23d825aba1 [torch.compile] Disable ar-rms fusion for ds3-fp4 & DP, fix CI test (#34392) 
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2026-02-15 06:33:57 -08:00
Isotr0py
71cd89264f [MM Encoder] Add Triton ViT attention backend (#32183) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2026-02-15 06:32:47 -08:00
Cyrus Leung
73391a1baa [Renderer] Move InputPreprocessor into Renderer (1/2) (#34510) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
 2026-02-14 10:14:21 -08:00
Kata Coder
d1ea65d0a1 [new model] add COLQwen3 code & Inference (#34398) 
Signed-off-by: craftsangjae <craftsangjae@gmail.com>
Signed-off-by: katacoder <craftsangjae@gmail.com>
 2026-02-14 12:15:19 +08:00
Andreas Karatzas
de42abb366 [CI] Heavy refactoring of Voxtral multimodal audio model tests (#34294) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
 2026-02-13 20:04:29 -08:00
Wei Zhao
b37b679770 [Feature][Perf] Support Selective CPU Weight Offloading (#34535) 
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
 2026-02-13 20:02:24 -08:00
Harry Huang
c027541eaf [Hybrid] Enable spec decoding in mamba cache align mode (#33705) 
Signed-off-by: huanghaoyan.hhy <huanghaoyan.hhy@alibaba-inc.com>
 2026-02-13 13:02:28 -08:00
Wei Zhao
59d53066d8 [Feature] Support CPU Offloading without Pytorch Pinned Memory that leads to doubled allocation (#32993) 
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
 2026-02-13 08:11:26 -08:00
LoganJane
4a9952ec1b [Bugfix] Add quant_config in ViT of Kimi-K2.5 (#34501) 
Signed-off-by: LoganJane <LoganJane73@hotmail.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2026-02-13 16:05:34 +00:00
Roger Wang
5885e330ef [Misc] Port Qwen3.5 Configs (#34512) 
Signed-off-by: Roger Wang <hey@rogerw.io>
 2026-02-13 05:24:25 -08:00
Ilya Boytsov
071d863e20 Extend ColBERT support to non-standard BERT backbones (#34170) 
Signed-off-by: Ilya Boytsov <ilya.boytsov@aleph-alpha.com>
 2026-02-13 09:53:09 +00:00
myselvess
bcf0731aa0 [New Model] support new model ovis2.6 (#34426) 
Signed-off-by: myselvess <23743269+myselvess@users.noreply.github.com>
 2026-02-13 00:12:45 -08:00
Roger Wang
eea3024f43 [Bugfix] Fix mamba state dtype setting for Qwen3-Next and Qwen3.5 (#34489) 
Signed-off-by: Roger Wang <hey@rogerw.io>
 2026-02-12 22:48:42 -08:00
haosdent
dcf6ee8592 [Bugfix] Fix encoder cache underestimation for GLM-4V/GLM-OCR single image (#34483) 
Signed-off-by: haosdent <haosdent@gmail.com>
 2026-02-12 21:04:06 -08:00
Cyrus Leung
372b2e762a [Bugfix] Standardize getting number of image patches/tokens (#34358) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2026-02-12 20:47:01 -08:00
LoganJane
62788f99a4 [Bugfix] Delete unused redundant code in Kimi-K2.5 (#34427) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2026-02-12 18:18:42 -08:00
Patrick von Platen
6c0baee610 [Voxtral Realtime] Refactor & Improve buffering logic (#34428) 
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>
 2026-02-12 09:46:43 -08:00
Patrick von Platen
1100a97621 [Voxstral Realtime] Enable tests (#33803) 
Signed-off-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2026-02-12 09:43:24 -08:00
Harry Mellor
679ca5d8d3 Fix MoE for the Transformers modelling backend (#34436) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2026-02-12 09:29:42 -08:00
AllenDou
386bfe5d08 [bugfix] refactor FunASR's _get_data_parser (#34397) 
Signed-off-by: zixiao <shunli.dsl@alibaba-inc.com>
Co-authored-by: zixiao <shunli.dsl@alibaba-inc.com>
 2026-02-12 07:26:49 +00:00
Yichuan Wang
80f2ba6ea6 Fix DeepSeek-OCR tensor validation for all size variants (#34085) 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-02-11 22:50:23 -08:00
Michael Goin
ff1f83b056 [Refactor] Replace activation: str with MoEActivation enum (#33843) 
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
 2026-02-11 17:29:32 -08:00
Raushan Turganbay
527ca32197 [Bugfix] Fix more multimodal tests for transformers V5 (#34334) 
Signed-off-by: raushan <raushan@huggingface.co>
 2026-02-11 22:02:05 +01:00
elvischenv
83e26c834e [GPT-OSS] Remove unnecessary contiguous (#34337) 
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
 2026-02-11 15:29:29 -05:00
Eldar Kurtić
11c7ace340 [Bugfix] Enable attn quantization of Llama-4 by correctly permuting scales for rope (int8, fp8) (#34243) 
Signed-off-by: Your Name <you@example.com>
Co-authored-by: Your Name <you@example.com>
 2026-02-11 13:24:22 -05:00