xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-04-29 08:47:09 +08:00
Code Issues Packages Projects Releases Wiki Activity
12,354 Commits 155 Branches 89 Tags
Commit Graph

560 Commits

Author SHA1 Message Date
Hank_
6482e3895b
chores: adjust the attn register param order (#30688) 
Signed-off-by: Hank <hcc.mayday@gmail.com>
 2025-12-17 19:58:16 +08:00
Nicolò Lucchesi
e087fbc393
[MM] Pass FA version in ViT Attn (#30756) 
Signed-off-by: NickLucche <nlucches@redhat.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
 2025-12-17 07:54:45 +08:00
TJian
2410132bb1
[ROCm] [Bugfix] Fix torch sdpa hallucination (#30789) 
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
 2025-12-16 15:32:43 -08:00
Lucas Wilkinson
9fec0e13d5
[Attention] Cache attention metadata builds across hybrid KV-cache groups (#29627) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Stanislaw Wozniak <stw@zurich.ibm.com>
 2025-12-16 17:10:16 -05:00
Matthew Bonanni
51e5b3e3c4
[Bugfix] Fix ViT with FlashAttention on ROCm (#30703) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
 2025-12-15 19:45:21 +00:00
Isotr0py
ec154c36ee
[Platform] Refactor Platform attention backend selection to avoid breakpoint for OOT platform (#30212) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-12-15 17:36:07 +00:00
Shanshan Shen
87b4d1557d
[CustomOp][MM] Extract MMEncoderAttention as CustomOp and replace the backend of QwenVisionAttention with it. (#30125) 
Signed-off-by: shen-shanshan <467638484@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
 2025-12-15 11:13:32 +08:00
Matthew Bonanni
86a3261525
[Bugfix] Pass FA version in MultiHeadAttention (#30575) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
 2025-12-13 00:02:11 +00:00
jvlunteren
9c0ee995a8
[Kernel] Support CUDA Graphs in 3D Triton Attention Kernel (#28306) 
Signed-off-by: Jan van Lunteren <jvl@zurich.ibm.com>
Signed-off-by: jvlunteren <161835099+jvlunteren@users.noreply.github.com>
Co-authored-by: Thomas Parnell <tom.parnell@gmail.com>
Co-authored-by: Thomas Parnell <tpa@zurich.ibm.com>
 2025-12-12 16:55:40 +01:00
Qiu
a11f4a81e0
[Misc][PCP&DCP] relocate PCP feature check (#30050) 
Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
 2025-12-11 03:36:18 -08:00
Cyrus Leung
5a87d8b9b1
[Deprecation] Remove deprecated plugin and compilation fields for v0.13 release (#30396) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-12-10 19:59:35 -08:00
Lucas Wilkinson
abe93bce59
[Attention] Make seq_lens_cpu optional in CommonAttentionMetadata to enable true async spec-decode (#29624) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com>
 2025-12-09 17:18:10 -08:00
rasmith
7618dc973d
[CI/Build] Make test_mha_attn.py run on correct platform only and check for flash_attn_varlen_func in layer.py (#29145) 2025-12-09 20:18:17 +00:00
Wentao Ye
d9417096d1
[Feature] Batch invariant: Enable TRITON_MLA without prefix-caching (#29125) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-12-08 19:31:57 -05:00
Dazhi Jiang
bcb6f5947f
[Perf] Remove sync point in vit torch sdpa attn backend (#30232) 
Signed-off-by: Dazhi Jiang <dazhi_jiang@163.com>
 2025-12-08 07:12:42 +00:00
Isotr0py
b952f4d3c3
[v1] Add PrefixLM support to FlexAttention backend (#27938) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2025-12-07 15:51:36 +00:00
Matthew Bonanni
66e674cdd5
[Attention][UX][1/N] Add AttentionConfig and change attention env vars to CLI arguments (#26315) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
 2025-12-05 09:48:43 -08:00
Augusto Yao
9726e64530
bugfix: correct attn output with base 2 or e (#28840) 
Signed-off-by: augusto.yjh <augusto.yjh@antgroup.com>
 2025-11-29 07:52:12 +08:00
Isotr0py
6f9d81d03b
[V0 deprecation] Clean up legacy paged attention helper functions (#28043) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2025-11-28 16:44:33 +00:00
Mingyuan Ma
460d8bbf2d
Remove upstream fa checks (#29471) 
Signed-off-by: mingyuanm <mingyuanm@nvidia.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
 2025-11-28 05:52:42 -08:00
Cyrus Leung
33b06a6f24
[Misc] Remove redundant attention var constants (#29650) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-11-28 04:35:19 -08:00
Matthew Bonanni
fc1d8be3dc
[Attention] Update attention imports (#29540) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
 2025-11-27 11:19:09 -05:00
Matthew Bonanni
430dd4d9eb
[Attention] Remove imports from vllm/attention/__init__.py (#29342) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
 2025-11-26 10:53:15 -07:00
Pleaplusone
d9d342d214
[Performance][MLA][ROCm] Remove redundant D2D copy in deepseek (#27457) 
Signed-off-by: ganyi <ygan@amd.com>
 2025-11-26 12:45:28 +08:00
Nicolò Lucchesi
798e87db5c
[Core] Generalize Encoder-Decoder seq_lens computation to avoid Whisper hardcoded logic (#29268) 
Signed-off-by: NickLucche <nlucches@redhat.com>
Co-authored-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com>
 2025-11-25 11:32:11 +00:00
Lucas Wilkinson
2d9ee28cab
[CI/Test Fix] Fix CP tests on Blackwell (#29338) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
 2025-11-24 20:55:57 -08:00
Roger Wang
0ff70821c9
[Core] Deprecate xformers (#29262) 
Signed-off-by: Roger Wang <hey@rogerw.io>
 2025-11-24 04:18:55 +00:00
Nicolò Lucchesi
066209a045
[Attention] Refactor FA block_size limitations to hybrid models only (#29084) 
Signed-off-by: NickLucche <nlucches@redhat.com>
 2025-11-22 06:38:44 -08:00
Matthew Bonanni
11857a00b0
[Attention] Add ROCM_AITER_MLA_SPARSE to attention backend registry (#29103) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
 2025-11-20 20:24:43 -08:00
Or Ozeri
647464719b
[KVConnector][Core] Support cross-layer KV blocks (#27743) 
Signed-off-by: Or Ozeri <oro@il.ibm.com>
 2025-11-20 19:09:59 +01:00
Pleaplusone
06c20c9904
[ROCm] Add AMD GPU support on Deepseek v3.2 and SparseMLA (#26670) 
Signed-off-by: ganyi <ygan@amd.com>
 2025-11-20 02:54:01 -08:00
Qiang Zhang
3fb0d90999
[AMD] Use Decoupled Kernel Block Size to Support AITER MLA block_size=1 (#27715) 
Signed-off-by: chiangzhang <chiangzhang@tencent.com>
 2025-11-20 02:11:52 +00:00
Qiu
2fd893b4ce
[Feature] Prefill Context Parallel (PCP) basic support (#28718) 
Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>
Signed-off-by: FENP <yuanyongjie.yyj@antgroup.com>
Signed-off-by: LookAround <lixushi@huawei.com>
Signed-off-by: Jingchun Gao <gaojingchun1@huawei.com>
Signed-off-by: zhenwenqi2024 <zhenwenqi_2022@qq.com>
Co-authored-by: FENP <yuanyongjie.yyj@antgroup.com>
Co-authored-by: LookAround <lixushi@huawei.com>
Co-authored-by: Jingchun Gao <gaojingchun1@huawei.com>
Co-authored-by: zhenwenqi2024 <zhenwenqi_2022@qq.com>
Co-authored-by: Jingchun Gao <63247409+gjc0824@users.noreply.github.com>
 2025-11-19 15:52:44 -05:00
Aleksandr Malyshev
ac10fd3c69
Upstreaming aiter triton attention backend as a new backend (#28701) 
Signed-off-by: Aleksandr Malyshev <maleksan@amd.com>
Co-authored-by: Aleksandr Malyshev <maleksan@amd.com>
 2025-11-19 19:59:30 +00:00
Shanshan Shen
d44e9df7d4
[Model][Mamba] Add selector for mamba attention backend and make it pluggable for other device (#26487) 
Signed-off-by: shen-shanshan <467638484@qq.com>
 2025-11-19 16:24:55 +00:00
Song Zhixin
285eaa4285
[Bugfix] Safeguard against missing backend in AttentionBackendEnum (#28846) 
Signed-off-by: jesse <szxfml@gmail.com>
Signed-off-by: Song Zhixin <szxfml@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-11-18 10:53:44 +00:00
Benjamin Chislett
bf3ffb61e6
[Bugfix] Fix ChunkedLocalAttention CUDA Graph setting (#28739) 
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
 2025-11-14 14:14:46 -08:00
rasmith
15ae8e0784
[Bugfix][CI/Test][Spec Decode] Fix illegal memory access in offline_inference/spec_decode.py (Issue 27619) (#28432) 
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
 2025-11-13 22:34:01 -08:00
Huamin Li
07a606aa7e
[CI Failure] Fix backend selection for encoder-only models (#28534) 
Signed-off-by: Huamin Li <3ericli@gmail.com>
 2025-11-13 10:11:27 -05:00
Benjamin Chislett
304419576a
[Perf] Refactor cudagraph_support to enable full CUDA graphs for spec decoding with FlashInfer (#28479) 
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
 2025-11-13 01:56:40 +09:00
Nicolò Lucchesi
728a9eb70e
[Misc] Refactor Attention kv transfer methods into decorator (#27816) 
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Co-authored-by: Mark McLoughlin <markmc@redhat.com>
 2025-11-12 16:05:44 +00:00
wangxiyuan
10138c92a5
[V0 deprecation] Deprecate use_v1 parameter (#28112) 
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
 2025-11-12 14:03:52 +00:00
Andreas Karatzas
9f0247cfa4
VLLM_USE_TRITON_FLASH_ATTN V0 variable deprecation (#27611) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
 2025-11-11 18:34:36 -08:00
Li, Jiang
7f829be7d3
[CPU] Refactor CPU attention backend (#27954) 
Signed-off-by: jiang1.li <jiang1.li@intel.com>
 2025-11-12 09:43:06 +08:00
Lukas Geiger
76e4dcf225
[Misc] Remove unused attention prefix prefill ops functions (#26971) 
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
 2025-11-11 18:26:04 +00:00
Matthew Bonanni
b30dfa03c5
[Attention] Refactor CUDA attention backend selection logic (#24794) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
 2025-11-11 07:40:44 -05:00
David Ben-David
cc079763c5
[BugFix] Avoid calling KV connector layer APIs when metadata is unset (#28253) 
Signed-off-by: David Ben-David <davidb@pliops.com>
Co-authored-by: David Ben-David <davidb@pliops.com>
Co-authored-by: Mark McLoughlin <markmc@redhat.com>
 2025-11-10 23:39:36 -08:00
Lucas Wilkinson
39029d5192
[CI/Test Fix] Fix CP tests on Blackwell (#28404) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-11-11 01:36:29 +00:00
Adrian Abeyta
a5a790eea6
[Bugfix] Ensure calculated KV scales are applied in attention. (#27232) 
Signed-off-by: adabeyta <aabeyta@redhat.com>
 2025-11-10 23:42:37 +00:00
vllmellm
f080a83511
[RFC][ROCm][AITER] Keep all AITER kernels in _aiter_ops class like _custom_ops and _ipex_ops (#24490) 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
 2025-11-10 08:20:53 -08:00