Commits · 2ce3d0ce360bf1e31e7ea3b2b0971a37bf5707c6 · OpenDAS / vllm_cscc

02 Apr, 2026 1 commit

[Feature] KV cache per-token-head INT8/FP8 quantization (#38378) · 2ce3d0ce

JartX authored Apr 02, 2026


Signed-off-by: JartX <sagformas@epdcenter.es>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: yangyang4991 <yangyang4991@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Isotr0py <2037008807@qq.com>

2ce3d0ce

27 Mar, 2026 1 commit
- enable skipping of SW attention layers when using FP8 KV cache (#33695) · 98e7f223
  Jonas M. Kübler authored Mar 27, 2026
```
Signed-off-by: Jonas Kuebler <kuebj@amazon.com>
```
  98e7f223
24 Mar, 2026 1 commit
- [V0 Deprecation] Refactor kv cache from list to element (#37487) · c59a132f
  Wentao Ye authored Mar 23, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  c59a132f
23 Mar, 2026 1 commit

[Bugfix] Register VLLM_BATCH_INVARIANT in envs.py to fix spurious unknown env var warning (#35007) · dc6908ac

Ranran authored Mar 23, 2026


Signed-off-by: Ranran <1012869439@qq.com>
Signed-off-by: Ranran <hzz5361@psu.edu>
Signed-off-by: ran <hzz5361@psu.edu>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>

dc6908ac

18 Mar, 2026 1 commit
- [V0 Deprecation] Deprecate virtual engine (#37195) · 0d81a1fe
  Wentao Ye authored Mar 18, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  0d81a1fe
09 Mar, 2026 1 commit
- Reapply [Attention] Refactor `check_and_update_config` (#35122) · 77a73458
  Matthew Bonanni authored Mar 09, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  77a73458
24 Feb, 2026 2 commits

[Attn,KV-cache] Use per-head scales in the attention selector (#34281) · a87cc508

Eldar Kurtić authored Feb 24, 2026


Signed-off-by: Your Name <you@example.com>
Signed-off-by: Eldar Kurtic <research@neuralmagic.com>
Co-authored-by: Eldar Kurtic <research@neuralmagic.com>
Co-authored-by: Your Name <you@example.com>

a87cc508

[ROCm] AITER fused RoPE+KVCache (#33443) · 2ff4e511

Rohan Potdar authored Feb 23, 2026


Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
Signed-off-by: charlifu <charlifu@amd.com>
Signed-off-by: Rohan Potdar <66227218+Rohan138@users.noreply.github.com>
Co-authored-by: charlifu <charlifu@amd.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Douglas Lehr <91553416+dllehr-amd@users.noreply.github.com>

2ff4e511

07 Feb, 2026 1 commit
- move checks out of `unified_kv_cache_update` custom op (#33943) · de3869bb
  Rohan Potdar authored Feb 07, 2026
```
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
```
  de3869bb
31 Jan, 2026 1 commit
- [Attention] Move MLA `forward` from backend to layer (#33284) · aaa901ad
  Matthew Bonanni authored Jan 30, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  aaa901ad
27 Jan, 2026 1 commit
- [5/N][Attention] Finish eliminating `vllm/attention` folder (#32064) · a608b4c6
  Matthew Bonanni authored Jan 27, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  a608b4c6
24 Jan, 2026 1 commit

[Performance] Split FlashAttn attention and cache update (#25954) · a28b94e6

ElizaWszola authored Jan 24, 2026


Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Luka Govedič <luka.govedic@gmail.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Varun Sundar Rabindranath <varunsundar08@gmail.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <luka.govedic@gmail.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Luka Govedič <lgovedic@redhat.com>

a28b94e6

22 Jan, 2026 1 commit

Add llmcompressor fp8 kv-cache quant (per-tensor and per-attn_head) (#30141) · 44f08af3

Eldar Kurtić authored Jan 22, 2026


Signed-off-by: Eldar Kurtic <8884008+eldarkurtic@users.noreply.github.com>
Signed-off-by: eldarkurtic <8884008+eldarkurtic@users.noreply.github.com>

44f08af3

18 Jan, 2026 1 commit
- [Model] Support Step1 Model (#32511) · c826c72a
  Li Xie authored Jan 18, 2026
```
Signed-off-by: xieli <xieli@stepfun.com>
```
  c826c72a
15 Jan, 2026 1 commit
- [Misc] Remove redundant line (#32366) · d86fc23b
  Li Wang authored Jan 15, 2026
```
Signed-off-by: wangli <wangli858794774@gmail.com>
```
  d86fc23b
09 Jan, 2026 1 commit
- [1/N][Attention] Restructure attention: move files (#31916) · 2612ba92
  Matthew Bonanni authored Jan 09, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  2612ba92
02 Jan, 2026 1 commit
- [MoE] Fix output_shape calculation in Attention layer to handle 3D query inputs (#31596) · 6ef770df
  Andreas Karatzas authored Jan 02, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  6ef770df
30 Dec, 2025 1 commit

[Model] Add support for openPangu moe model (#28775) · 3f52fa5a

yt0428 authored Dec 31, 2025


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>

3f52fa5a

28 Dec, 2025 1 commit
- [BugFix] register quant scale tensors as buffer (#31395) · 62def07d
  Boyuan Feng authored Dec 27, 2025
```
Signed-off-by: Boyuan Feng <boyuan@meta.com>
```
  62def07d
18 Dec, 2025 1 commit

[MM Encoder]: Migrate legacy ViT `MultiHeadAttention` to new... · 700a5ad6

Isotr0py authored Dec 19, 2025


[MM Encoder]: Migrate legacy ViT `MultiHeadAttention` to new `MMEncoderAttention` interface (#30684)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>

700a5ad6

15 Dec, 2025 2 commits

[Bugfix] Fix ViT with FlashAttention on ROCm (#30703) · 51e5b3e3
Matthew Bonanni authored Dec 15, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
51e5b3e3

[CustomOp][MM] Extract MMEncoderAttention as CustomOp and replace the backend... · 87b4d155

Shanshan Shen authored Dec 15, 2025


[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>

87b4d155

13 Dec, 2025 1 commit
- [Bugfix] Pass FA version in `MultiHeadAttention` (#30575) · 86a32615
  Matthew Bonanni authored Dec 12, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  86a32615
09 Dec, 2025 2 commits
- [CI/Build] Make test_mha_attn.py run on correct platform only and check for... · 7618dc97
  rasmith authored Dec 09, 2025
```
[CI/Build] Make test_mha_attn.py run on correct platform only and check for flash_attn_varlen_func in layer.py (#29145)
```
  7618dc97
- [Feature] Batch invariant: Enable `TRITON_MLA` without prefix-caching (#29125) · d9417096
  Wentao Ye authored Dec 08, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  d9417096
07 Dec, 2025 1 commit
- [v1] Add PrefixLM support to FlexAttention backend (#27938) · b952f4d3
  Isotr0py authored Dec 07, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  b952f4d3
05 Dec, 2025 1 commit

[Attention][UX][1/N] Add AttentionConfig and change attention env vars to CLI arguments (#26315) · 66e674cd

Matthew Bonanni authored Dec 05, 2025

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>

66e674cd

28 Nov, 2025 1 commit

Remove upstream fa checks (#29471) · 460d8bbf

Mingyuan Ma authored Nov 28, 2025


Signed-off-by: mingyuanm <mingyuanm@nvidia.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>

460d8bbf

26 Nov, 2025 1 commit
- [Attention] Remove imports from `vllm/attention/__init__.py` (#29342) · 430dd4d9
  Matthew Bonanni authored Nov 26, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  430dd4d9
24 Nov, 2025 1 commit
- [Core] Deprecate `xformers` (#29262) · 0ff70821
  Roger Wang authored Nov 23, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.io>
```
  0ff70821
18 Nov, 2025 1 commit

[Bugfix] Safeguard against missing backend in AttentionBackendEnum (#28846) · 285eaa42

Song Zhixin authored Nov 18, 2025

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>

285eaa42

13 Nov, 2025 1 commit
- [CI Failure] Fix backend selection for encoder-only models (#28534) · 07a606aa
  Huamin Li authored Nov 13, 2025
```
Signed-off-by: Huamin Li <3ericli@gmail.com>
```
  07a606aa
12 Nov, 2025 1 commit

[Misc] Refactor Attention kv transfer methods into decorator (#27816) · 728a9eb7

Nicolò Lucchesi authored Nov 12, 2025


Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Co-authored-by: Mark McLoughlin <markmc@redhat.com>

728a9eb7

11 Nov, 2025 2 commits

[Attention] Refactor CUDA attention backend selection logic (#24794) · b30dfa03

Matthew Bonanni authored Nov 11, 2025


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>

b30dfa03

[BugFix] Avoid calling KV connector layer APIs when metadata is unset (#28253) · cc079763

David Ben-David authored Nov 11, 2025


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>

cc079763

10 Nov, 2025 1 commit
- [Bugfix] Ensure calculated KV scales are applied in attention. (#27232) · a5a790ee
  Adrian Abeyta authored Nov 10, 2025
```
Signed-off-by: adabeyta <aabeyta@redhat.com>
```
  a5a790ee
01 Nov, 2025 1 commit

[Multimodal][XPU]Enable vision attn backend for xpu platform (#27525) · 7e2729b5

Yan Ma authored Nov 01, 2025


Signed-off-by: Yan Ma <yan.ma@intel.com>
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Co-authored-by: Yejing Lai <yejing.lai@intel.com>
Co-authored-by: Guancheng Fu <110874468+gc-fu@users.noreply.github.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>

7e2729b5

26 Oct, 2025 1 commit

[BUGFIX][ROCM] ViT FlashAttention on ROCm (no GFX9) and contiguous on qwen3vl... · 65d2cf95

JartX authored Oct 26, 2025


[BUGFIX][ROCM] ViT FlashAttention on ROCm (no GFX9) and contiguous on qwen3vl ROCm TORCH_SDPA (#27190)
Signed-off-by: JartX <sagformas@epdcenter.es>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>

65d2cf95

25 Oct, 2025 1 commit
- [Attention] Add missing kv cache scale setup (#27490) · a99564ac
  Matthew Bonanni authored Oct 25, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  a99564ac
23 Oct, 2025 1 commit

[Bugfix] Honor --mm_encoder_attn_backend when used (#27124) · 570c3e1c

Bradley D authored Oct 23, 2025


Co-authored-by: Bradley D <4551889+bradleyhd@users.noreply.github.com>
Co-authored-by: Roger Wang <hey@rogerw.io>

570c3e1c