biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
14,061 Commits 2 Branches 140 Tags
ea37530b474fa738a99a53a8975af4e389b968c7
Commit Graph

14061 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Woosuk Kwon
0916e7960b [GDN] Use CPU tensors to build GDN metadata (#34498) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-02-13 01:24:45 -08:00
Wentao Ye
3d2a026fd0 [Feature] Pipeline Parallel Async send/recv, 2.9% E2E throughput improvement (#33368) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
 2026-02-13 16:38:16 +08:00
Aaron Hao
dddbff4624 [Core] Move pause and resume functions into engine (#34125) 
Signed-off-by: ahao-anyscale <ahao@anyscale.com>
Signed-off-by: Aaron Hao <ahao@anyscale.com>
Signed-off-by: hao-aaron <ahao@anyscale.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
 2026-02-13 00:15:10 -08:00
Martin Hickey
47e9b63e1a [KVConnector] Clean up redundant code in KV connectors (#34147) 
Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
 2026-02-13 00:14:30 -08:00
Matthias Gehre
934acddef9 [Perf] fused_moe: add int4_w4a16 benchmark support and tuning config (#34130) 
Signed-off-by: Matthias Gehre <matthias.gehre@amd.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
 2026-02-13 00:14:27 -08:00
Marek Michalowski
742d214d6e [Bugfix] fix the import path in moe test utils.py (#34245) 
Signed-off-by: Marek Michalowski <marek.michalowski@arm.com>
 2026-02-13 00:13:45 -08:00
haosdent
4137c5dfa7 [Bug Fix] Fix MambaManager.cache_blocks() crash on null blocks in align mode (#34418) 
Signed-off-by: haosdent <haosdent@gmail.com>
 2026-02-13 00:13:22 -08:00
Harry Huang
7a8a46ddcb [BugFix] Fix and optimize max_num_blocks_per_req calculation for MambaSpec (#34440) 
Signed-off-by: huanghaoyan.hhy <huanghaoyan.hhy@alibaba-inc.com>
 2026-02-13 00:13:14 -08:00
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
Cyrus Leung
ec090c2429 [Refactor] Call renderer for online IO processor request (#34490) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2026-02-12 22:48:45 -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
Cyrus Leung
2f308214c0 [Refactor] Pass full VllmConfig to Renderer (#34485) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2026-02-12 22:48:38 -08:00
Cyrus Leung
1b4e8e53f8 [CI/Build] Fix CUDA re-initialization error in distributed model tests (#34491) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2026-02-13 06:43:53 +00:00
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
Andreas Karatzas
6afa587d31 [ROCm][CI] Fix serving tokens test failures (#34047) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
 2026-02-13 11:27:53 +08:00
Cyrus Leung
94ed6cf6ea Add new sections to CODEOWNERS (#34309) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2026-02-12 18:39:28 -08:00
Harry Huang
bf37812ca7 [Hybrid] Fix and optimize block-aligned splitting in mamba cache align mode (#33706) 
Signed-off-by: huanghaoyan.hhy <huanghaoyan.hhy@alibaba-inc.com>
 2026-02-12 18:21:52 -08:00
Frank Wang
b86bf4417e [Bugfix] Fix Random Dataset Prefix Length Inaccuracy (#33907) 
Signed-off-by: frankwang28 <frank.wbb@hotmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
 2026-02-12 18:21:19 -08:00
Yanan Cao
de13dd781f [Kernel] [Helion] [5/N] Add Helion Autotuning infrastructure (#34025) 
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
 2026-02-12 18:21:05 -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
Cyrus Leung
ea5ff3a1f6 [Refactor] Simplify BOS/EOS token handling (#34435) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2026-02-12 18:18:24 -08:00
bnellnm
04ea31baab [Bugfix] Remove assert that's no longer valid (#34443) 
Signed-off-by: Bill Nell <bnell@redhat.com>
 2026-02-12 18:18:15 -08:00
Harry Huang
6f019e6e0a [BugFix] Add block_size validation for mamba cache align mode (#34445) 
Signed-off-by: huanghaoyan.hhy <huanghaoyan.hhy@alibaba-inc.com>
 2026-02-12 18:18:07 -08:00
Zhuohan Li
d707678dfb Fix num_logprobs parameter description in sampler.py (#34451) 
Signed-off-by: Zhuohan Li <zhuohan123@gmail.com>
 2026-02-12 18:18:03 -08:00
Cyrus Leung
fc22cae4ac [CI/Build] Update video URLs for testing (#34446) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2026-02-12 18:15:36 -08:00
Yanan Cao
96161fe978 [Kernel] [Helion] [4/N] Add silu_mul_fp8 Helion kernel (#33373) 
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
 2026-02-12 18:13:12 -08:00
Jaewon
4453ba8d9e [Core] Profiler improvements and lazy initialization (#33198) 
Signed-off-by: Jaewon Lee <jaewon@meta.com>
Co-authored-by: Lu Fang <30275821+houseroad@users.noreply.github.com>
 2026-02-12 16:16:38 -08:00
Jaewon
aa181c923b [Core] Add sleep level 0 mode with enqueue/wait pattern (#33195) 
Signed-off-by: Jaewon Lee <jaewon@meta.com>
Co-authored-by: Lu Fang <30275821+houseroad@users.noreply.github.com>
 2026-02-12 16:16:25 -08:00
Alec S
be7370daf3 [Frontend] Enable generic structured_outputs for responses API (#33709) 
Signed-off-by: Alec Solder <alecs@fb.com>
Co-authored-by: Alec Solder <alecs@fb.com>
 2026-02-12 16:15:48 -08:00
Mengtao (Martin) Yuan
9ea1f598ce Use paged_attention_v1 for sliding window decode in rocm_aiter_fa (#34378) 
Signed-off-by: Martin Yuan <myuan@meta.com>
Co-authored-by: Martin Yuan <myuan@meta.com>
 2026-02-12 16:14:43 -08:00
amitz-nv
f120bd42d3 [Kernel] Support Flashinfer trtllm fused MoE non gated FP8 & NVFP4 (#33506) 
Signed-off-by: amitz-nv <203509407+amitz-nv@users.noreply.github.com>
 2026-02-12 13:06:58 -08:00
Hashem Hashemi
fac4e96940 small adjustment to wvSplitKrc (#34410) 
Signed-off-by: Hashem Hashemi <hashem.hashemi@amd.com>
 2026-02-12 20:26:36 +00:00
Michael Goin
6d4e27ce29 [Bugfix] Enforce DeepGEMM when using sparse_attn_indexer on CUDA (#34374) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2026-02-12 12:08:06 -08:00
Andreas Karatzas
4c078fa546 [ROCm][CI] Pin TorchCodec to v0.10.0 for ROCm compatibility (#34447) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
 2026-02-12 18:47:34 +00:00
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
xuebwang-amd
766e167821 [ROCm][quantization] improve OCP weight quant parser robust (#34431) 
Signed-off-by: xuebwang-amd <xuebwang@amd.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
 2026-02-12 09:40:19 -08:00
Isotr0py
becbe24808 [Bugfix] Remove broken raw url GGUF model loading support (#34433) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2026-02-12 09:40:01 -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
Matthew Bonanni
f2c47886fd [Attention] Add FlashInfer Sparse MLA backend (#33451) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
 2026-02-12 17:21:54 +00:00
Nicolò Lucchesi
334c715e0f [Docs] Spec decoding docs warning removal (#34439) 
Signed-off-by: NickLucche <nlucches@redhat.com>
 2026-02-12 09:01:51 -08:00
Aaron Hao
7b5a8b4a9d [BUG] Reset running requests when clearing cache for pause/resume (#34382) 
Signed-off-by: hao-aaron <ahao@anyscale.com>
 2026-02-12 16:19:13 +00:00
danisereb
dea63512bb Add config file for fused MoE for Nemotron (TP4, B200) (#34411) 
Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>
 2026-02-12 06:09:55 -08:00
Douglas Lehr
8a798be929 [ROCm] Enable MXFP4 MoE weight pre-shuffling on gfx950 and update aiter (#34192) 
Signed-off-by: Doug Lehr <douglehr@amd.com>
Co-authored-by: Doug Lehr <douglehr@amd.com>
Co-authored-by: Gregory Shtrasberg <156009573+gshtras@users.noreply.github.com>
Co-authored-by: tjtanaavllm <tunjian.tan@amd.com>
 2026-02-12 05:06:33 -08:00
Cyrus Leung
fb455ed547 [V0 Deprecation] Remove code related to per-request logits processors (#34400) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2026-02-12 20:44:28 +08:00
baonudesifeizhai
f5897613fb Fix Mistral config remap to accept compressed-tensors quantization #34028 (#34104) 
Signed-off-by: baonudesifeizhai <baonudesifeizhai@gmail.com>
 2026-02-12 08:22:06 +00:00
Louie Tsai
55a1a9563a Vllm CPU benchmark suite improvement (#34128) 
Signed-off-by: louie-tsai <louie.tsai@intel.com>
 2026-02-12 16:04:44 +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
Kyle Sayers
e9cd691132 [Bugfix] Fix Sparse24 Compressed Tensors models (#33446) 
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
 2026-02-11 23:15:16 -08:00