 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 |
|
|
Shanshan Shen
|
08d954f036
|
[Doc] Add developer guide for CustomOp (#30886)
Signed-off-by: shen-shanshan <467638484@qq.com>
|
2026-01-09 16:21:11 +00:00 |
|
|
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 |
|
|
Lucas WilkinsonandLuka Govedič
|
6cdf015c3c
|
[Misc] Fix Current vLLM config is not set. warnings, assert to avoid issues in the future (#31747)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
|
2026-01-08 15:20:49 -08:00 |
|
|
Isotr0py
|
2972a05473
|
[MM Encoder]: Make MMEncoderAttention's scale takes effect properly (#31950)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2026-01-08 02:33:48 -08:00 |
|
|
Rabi Mishra
|
39d82005f7
|
fix(rocm): add early return in get_flash_attn_version for ROCm (#31286)
Signed-off-by: rabi <ramishra@redhat.com>
|
2026-01-08 10:28:07 +08:00 |
|
|
Matthew Bonanni
|
0d7667419f
|
[0/N][Attention] Fix miscellaneous pre-commit issues (#31924)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
|
2026-01-08 01:15:17 +00:00 |
|
|
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 |
|
|
BlankRandWentao Ye
|
0790f07695
|
[Misc] Improve error messages for unsupported types and parameters (#30593)
Signed-off-by: BlankR <hjyblanche@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2026-01-07 09:00:16 +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 |
|
|
|
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 |
|
|
Isotr0py
|
02809af1e7
|
[Bugfix]: Fix cross attention backend selection for Turing GPU (#31806)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2026-01-06 23:15:56 +08:00 |
|
|
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 |
|
|
Andreas Karatzas
|
6ef770df7c
|
[MoE] Fix output_shape calculation in Attention layer to handle 3D query inputs (#31596)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2026-01-02 15:46:23 +00:00 |
|
|
|
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 |
|
|
Boyuan Feng
|
62def07d67
|
[BugFix] register quant scale tensors as buffer (#31395)
Signed-off-by: Boyuan Feng <boyuan@meta.com>
|
2025-12-28 11:20:02 +08:00 |
|
|
Andreas Karatzas
|
bfa2c0bbb9
|
[ROCm][Bugfix] Fix RuntimeError in MMEncoderAttention by replacing .view() with .reshape() (#31203)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2025-12-23 21:48:01 +00:00 |
|
|
Kevin McKay
|
42b42824ae
|
[Misc] Fix grammar errors in comments and messages (#31115)
Signed-off-by: c0de128 <kevin.mckay@outlook.com>
|
2025-12-21 21:14:02 -08:00 |
|
|
zejunchen-zejun
|
d52c5096d7
|
[Bugfix] fix the alias bug of AttentionBackendEnum when register CUSTOM attention backend to vllm (#30869)
Signed-off-by: zejunchen-zejun <zejun.chen@amd.com>
|
2025-12-20 09:03:35 +08:00 |
|
|
Thomas Parnell
|
b5545d9d5c
|
[Bugfix] [Kernel] Triton attention kernels: mask out V blocks that fall outside sliding window (#30887)
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
|
2025-12-19 21:39:54 +08:00 |
|
|
Isotr0py
|
ac1c934276
|
[Bugfix] Fix incorrect tiles creation for mm prefix triton attention (#30974)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2025-12-19 16:00:33 +08:00 |
|
|
Isotr0py
|
d2dc5dfc6e
|
[Bugfix] Remove tile_size=64 for mm_prefix triton attention (#30973)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2025-12-18 20:42:32 +01:00 |
|
|
Isotr0py
|
700a5ad6c6
|
[MM Encoder]: Migrate legacy ViT MultiHeadAttention to new MMEncoderAttention interface (#30684)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2025-12-19 02:04:19 +08:00 |
|
|
Andreas Karatzas
|
8da6ae49c3
|
[ROCm][Bugfix] Fix fa_version argument error in flash_attn_maxseqlen_wrapper for ROCm without aiter (#30909)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2025-12-18 16:45:51 +08:00 |
|
|
Isotr0py
|
74a1ac38b0
|
[v1] Add PrefixLM support to TritonAttention backend (#30386)
|
2025-12-17 16:05:24 -08:00 |
|
|
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 LucchesiandCyrus Leung
|
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 WilkinsonandStanislaw Wozniak
|
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 |
|
|
Isotr0pyandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
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 |
|
|
|
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 |
|
|
|
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 |
|
|
QiuandCyrus Leung
|
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 WilkinsonandBenjamin Chislett
|
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 |
|
|
|
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 MaandRoger Wang
|
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 LucchesiandEkagra Ranjan
|
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 |
|