biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
13,207 Commits 2 Branches 140 Tags
a8eb1182f172c616af99c1bfc5ba70b792793114
Commit Graph

495 Commits

Author SHA1 Message Date
Andreas Karatzas
a8eb1182f1 [CI][Models] Add VLM Support for Sequence Classification Conversion (#32885) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
 2026-01-23 16:22:51 +08:00
Wentao Ye
7ef5873752 [CI] Fix mypy for vllm/v1/structured_output (#32722) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-01-23 11:55:51 +08:00
Eldar Kurtić
44f08af3a7 Add llmcompressor fp8 kv-cache quant (per-tensor and per-attn_head) (#30141) 
Signed-off-by: Eldar Kurtic <8884008+eldarkurtic@users.noreply.github.com>
Signed-off-by: eldarkurtic <8884008+eldarkurtic@users.noreply.github.com>
 2026-01-22 13:29:57 -07:00
Matthew Bonanni
955b43a5a5 [Bugfix][Attention] Explicitly report support for kv_cache_dtype bfloat16 (#32795) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
 2026-01-22 19:05:18 +00:00
Lucas Wilkinson
889722f3bf [FlashMLA] Update FlashMLA to expose new arguments (#32810) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
 2026-01-21 22:02:39 -07:00
Nick Hill
24dc30f7ff [ModelRunner V2] Don't pin reused flashinfer tensors (#32799) 
Signed-off-by: Nick Hill <nickhill123@gmail.com>
 2026-01-21 13:17:43 -08:00
elvischenv
808d6fd7b9 Bump Flashinfer to v0.6.1 (#30993) 
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
 2026-01-21 08:49:50 -08:00
Pleaplusone
6c20e89c02 [ROCm][Deepseekv3.2] Refactor Sparse Indexer as CustomOp (#29287) 
Signed-off-by: ganyi <ygan@amd.com>
 2026-01-21 23:16:30 +08:00
Robert Shaw
42135d6898 [MoE Refactor] Oracle Select FP8+NVFP4 Kernels In Priority (#32414) 2026-01-21 08:22:33 -05:00
Lucas Wilkinson
b4f64e5b02 Update FlashMLA (#32491) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
 2026-01-21 13:03:37 +08:00
Tomas Ruiz
4a5299c93f feat: spec decode with draft models (#24322) 
Signed-off-by: Tomas Ruiz <tomas.ruiz.te@gmail.com>
 2026-01-19 16:05:46 -05:00
Vadim Gimpelson
6101a26dc9 [BUGFIX] Fix degenerate strides in TRTLLM query tensors for FlashInfer backend. Fixes issue #32353 (#32417) 
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
 2026-01-18 16:57:32 -08:00
Wentao Ye
16de822c71 [Refactor] Remove unused file pallas_kv_cache_update.py (#32433) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-01-18 12:46:39 -08:00
Li Xie
c826c72a96 [Model] Support Step1 Model (#32511) 
Signed-off-by: xieli <xieli@stepfun.com>
 2026-01-18 10:20:46 +00:00
Isotr0py
8cc26acd8b [Performance] Improve Triton prefill attention kernel's performance (#32403) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2026-01-17 20:19:59 -08:00
Guofang.Tang
2b99f210f5 [Misc] Fix typo: seperator -> separator in flashmla_sparse.py (#32411) 
Signed-off-by: Guofang Tang <tinggofun@gmail.com>
Co-authored-by: Guofang Tang <tinggofun@gmail.com>
 2026-01-17 12:18:30 +00:00
Matthias Gehre
047413375c [Attention][AMD] Make flash-attn optional (#30361) 
Signed-off-by: Matthias Gehre <matthias.gehre@amd.com>
 2026-01-15 17:18:24 +00:00
Pleaplusone
130d6c9514 [ROCm][Perf] Enable shuffle kv cache layout and assembly paged attention kernel for AiterFlashAttentionBackend (#29887) 
Signed-off-by: ganyi <ygan@amd.com>
 2026-01-15 15:29:53 +00:00
vllmellm
e27078ea80 [Bugfix][ROCm][performance] Resolve the performance regression issue of the Qwen3-Next-80B-A3B-Thinking under rocm_atten (#32336) 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2026-01-14 19:32:48 +00:00
Matthew Bonanni
2263d44b68 [4/N][Attention] Move MLA common to model_executor (#32060) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
 2026-01-13 09:08:45 -08:00
Matthew Bonanni
98f60e5acb [6/N][Attention] Move utils to more appropriate locations (#32215) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
 2026-01-13 05:38:52 -08:00
Mickaël Seznec
a5bbbd2f24 [Quantization] fix: overflow with static per-tensor scaling (#29867) 
Signed-off-by: Mickael Seznec <mickael@mistral.ai>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
 2026-01-13 12:56:01 +00:00
cjackal
15b33ff064 [Misc] improve warning/assert messages (#32226) 
Signed-off-by: cjackal <44624812+cjackal@users.noreply.github.com>
 2026-01-13 03:11:23 +00:00
Matthew Bonanni
20228cb851 [3/N][Attention] Move AttentionMetadata-related code from utils.py to backend.py (#32054) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
 2026-01-12 09:13:56 -08:00
Asaf Joseph Gardin
8fb2c135be [Bugfix] Fix stale SSM state for new Mamba requests scheduled as decode (#32118) 
Signed-off-by: Josephasafg <ajgard7@gmail.com>
 2026-01-12 17:02:38 +00:00
Isotr0py
9dbe1fe960 [Bugfix] Fix missing scale passing for encoder Triton Attention implementation (#32149) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2026-01-12 11:13:41 +00:00
Vadim Gimpelson
e15a5ff07b [MISC] Add strict contiguity check for FlashInfer attention tensors (#32008) 
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
Signed-off-by: Vadim Gimpelson <156319763+vadiklyutiy@users.noreply.github.com>
 2026-01-10 12:40:05 -08:00
jvlunteren
b8bf5c45bb [Kernel] Optimize Sliding Window Attention in 3D Triton Kernel (#31984) 
Signed-off-by: Jan van Lunteren <jvl@zurich.ibm.com>
 2026-01-10 18:13:44 +00:00
Lucas Wilkinson
da6709c9fe [Misc] Delay deprecation of CommonAttentionMetadata properties (#32074) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
 2026-01-09 21:06:44 -08:00
Lucas Kabela
ea6d067a2a [Misc][LLaMa4] Compile LLaMa Vision Encoder (#30709) 
Signed-off-by: Lucas Kabela <lucaskabela@meta.com>
 2026-01-09 22:01:38 -05:00
Matthew Bonanni
0308901975 [2/N][Attention] Fix pre-commit errors (#32052) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
 2026-01-10 00:27:15 +00:00
Matthew Bonanni
2612ba9285 [1/N][Attention] Restructure attention: move files (#31916) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
 2026-01-09 13:10:24 -08:00
R3hankhan
8e27663b6a [CPU] Add head sizes 80 and 112 with vec16 fallback (#31968) 
Signed-off-by: Rehan Khan <Rehan.Khan7@ibm.com>
 2026-01-09 22:14:46 +08:00
vllmellm
1a19e9cd87 [Bugfix][ROCm]Fix Qwen3-Next-80B-A3B-Thinking inference and optimize non-standard block size (544) support under rocm_atten (#31380) 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2026-01-09 19:28:02 +08:00
Rabi Mishra
107cf8e92f fix(rocm): Add get_supported_kernel_block_sizes() to ROCM_ATTN (#31712) 
Signed-off-by: rabi <ramishra@redhat.com>
 2026-01-08 15:46:07 +08:00
Cyrus Leung
b665bbc2d4 [Chore] Migrate V0 attention utils (#31891) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2026-01-07 13:44:36 +00:00
vllmellm
41cfa50632 [ROCm][AITER] fix wrong argument passed to AITER flash_attn_varlen_func (#31880) 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2026-01-07 11:25:03 +00:00
weiyu
e7596371a4 [Refactor][TPU] Remove torch_xla path and use tpu-inference (#30808) 
Signed-off-by: Wei-Yu Lin <weiyulin@google.com>
Signed-off-by: weiyu <62784299+weiyu0824@users.noreply.github.com>
 2026-01-07 16:07:16 +08:00
Lucas Wilkinson
c7a79d41a0 [Attention][3/n] Remove usage of deprecated seq_lens_cpu and num_computed_tokens_cpu CommonAttentionMetadata properties (#31850) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
 2026-01-07 13:31:34 +08:00
vllmellm
6409004b26 [ROCm][AITER] bugfix accuracy regression in ROCM_AITER_TRITON_MLA backend (#31816) 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2026-01-07 05:04:53 +00:00
Jack Yang
0a2c2dc3f1 fixed mypy warnings for files vllm/v1/attention with TEMPORARY workaround (#31465) 
Signed-off-by: Zhuohao Yang <zy242@cornell.edu>
Co-authored-by: Zhuohao Yang <zy242@cornell.edu>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
 2026-01-07 04:08:47 +00:00
Lucas Wilkinson
4c73be14e0 [Attention][2/n] Remove usage of deprecated seq_lens_cpu and num_computed_tokens_cpu CommonAttentionMetadata properties (#31774) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
 2026-01-06 17:32:14 +00:00
Lucas Wilkinson
e0327c9db2 [Attention][1/n] Remove usage of deprecated seq_lens_cpu and num_computed_tokens_cpu CommonAttentionMetadata properties (#31773) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
 2026-01-06 04:05:17 -08:00
Or Ozeri
d8e38d4939 Triton Attention: Support cross-layers blocks (#30687) 
Signed-off-by: Or Ozeri <oro@il.ibm.com>
 2026-01-05 19:29:16 +00:00
Isotr0py
6aa5b18e1d [v1] Add encoder-only/cross attention support to Triton Attention backend (#31406) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2026-01-06 00:00:23 +08:00
Kevin McKay
825c2dc133 [Bugfix][Hardware][AMD] Fix last_page_len calculation in AITER MLA decode (#31282) 
Signed-off-by: c0de128 <kevin.mckay@outlook.com>
 2026-01-01 21:14:00 -08:00
Wentao Ye
357d435c54 [Bug] Fix log issue with \n (#31390) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
 2025-12-30 21:16:55 -08:00
yt0428
3f52fa5aa2 [Model] Add support for openPangu moe model (#28775) 
Signed-off-by: yuantao <2422264527@qq.com>
Signed-off-by: yt0428 <51468697+yt0428@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
 2025-12-30 08:11:38 -08:00
Asaf Joseph Gardin
34916ae37f [Mamba] - Consolidate Mambas Attention Logic (#28133) 2025-12-23 21:57:00 +01:00
Patrick von Platen
3faa8bee57 adapt voxtral (#31095) 
Signed-off-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2025-12-23 05:31:55 -08:00