Commits · f2c47886fdbabfeae7ddad871ee7889ee472d026 · OpenDAS / vllm_cscc

12 Feb, 2026 1 commit

[Attention] Add FlashInfer Sparse MLA backend (#33451) · f2c47886

Matthew Bonanni authored Feb 12, 2026


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>

f2c47886

11 Feb, 2026 3 commits
- [ROCm] [aiter] Split KV cache update for AiterFlashAttention (#33681) · 64f570ab
  kliuae authored Feb 12, 2026
```
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
```
  64f570ab
- Reapply [Attention][FA3] Update FA3 to include new swizzle optimization (#34043) · c7914d30
  Lucas Wilkinson authored Feb 11, 2026
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  c7914d30
- [XPU][9/N] clean up existing ipex code/doc (#34111) · cb9574eb
  Kunshang Ji authored Feb 11, 2026
```
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
```
  cb9574eb
10 Feb, 2026 2 commits

[BUGFIX] Fix accuracy bugs in Qwen3-Next MTP (#34077) · 000214c4
Vadim Gimpelson authored Feb 10, 2026
```
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
```
000214c4

[Perf][Kernel] Add faster topKperRow decode kernel for DeepSeek-V3.2 sparse attention (#33680) · afdce12c

Roberto L. Castro authored Feb 10, 2026

Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
Signed-off-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>

afdce12c

08 Feb, 2026 1 commit
- [Revert] Fix performance regression for GLM-4.7-GPTQ decode and MTP acceptance rate (#33771) · 179ae7da
  aabbccddwasd authored Feb 09, 2026
```
Signed-off-by: aabbccddwasd <aabbccddwasd@qq.com>
```
  179ae7da
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
06 Feb, 2026 2 commits
- [ROCm][AITER] Fix AITER import regression for explicit backend selection (#33749) · 350ca72c
  Andreas Karatzas authored Feb 06, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  350ca72c
- [cpu][performance] CPU Paged Attention NEON BFMMLA BF16 Implementation (#32263) · 1363e3d6
  Gassan Salama authored Feb 06, 2026
```
Signed-off-by: Gassan <gassan.salama@arm.com>
```
  1363e3d6
05 Feb, 2026 3 commits
- [Spec Decode] Unified Parallel Drafting (#32887) · af3162d3
  Benjamin Chislett authored Feb 05, 2026
```
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
```
  af3162d3
- Revert "[Attention][FA3] Update FA3 to include new swizzle optimization" (#33841) · e3bf79ff
  Luka Govedič authored Feb 04, 2026
  
  e3bf79ff
- [Bugfix] Disable TRTLLM attention when KV transfer is enabled (#33192) · bbe0574d
  zhanqiuhu authored Feb 04, 2026
```
Signed-off-by: Zhanqiu Hu <zh338@cornell.edu>
```
  bbe0574d
04 Feb, 2026 1 commit
- Implement zero-copy GQA for multimodal and CPU (#33732) · 6e98f6d8
  Taeksang Kim authored Feb 05, 2026
```
Signed-off-by: Taeksang Kim <ts.kim@hyperaccel.ai>
```
  6e98f6d8
03 Feb, 2026 2 commits
- [Attention][FA3] Update FA3 to include new swizzle optimization (#23465) · 2267cb1c
  Lucas Wilkinson authored Feb 03, 2026
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  2267cb1c
- [XPU][1/N] Deprecate ipex and switch to vllm-xpu-kernels for xpu platform (#33379) · e1060448
  Kunshang Ji authored Feb 03, 2026
```
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
```
  e1060448
02 Feb, 2026 1 commit
- fix[ROCm]: Remove unconditional aiter import (#32902) · 9eb58f8c
  Rabi Mishra authored Feb 02, 2026
```
Signed-off-by: rabi <ramishra@redhat.com>
```
  9eb58f8c
31 Jan, 2026 5 commits
- [ROCM] Enable aiter attn backend for qwen3-next model (#32492) · 527bcd14
  jennyyyyzhen authored Jan 31, 2026
```
Signed-off-by: jennyyyyzhen <yzhen@hmc.edu>
```
  527bcd14
- [Attention] Clarify comment explaining attn_logits +1 dimension (#33427) · 5b55c0be
  Francesco Fusco authored Jan 31, 2026
```
Signed-off-by: Francesco Fusco <ffu@zurich.ibm.com>
```
  5b55c0be
- [Misc] offest -> offset in comments and variable names (#33444) · a2ef06e1
  Russell Bryant authored Jan 30, 2026
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  a2ef06e1
- [BugFix] Fix whisper FA2 + full cudagraphs (#33360) · 0a3c71e7
  Lucas Wilkinson authored Jan 30, 2026
```
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>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  0a3c71e7
- [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
30 Jan, 2026 1 commit

[Misc] Replace Optional[X] with X | None syntax (#33332) · 1a7894db

杨朱 · Kiki authored Jan 30, 2026


Signed-off-by: carlory <baofa.fan@daocloud.io>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>

1a7894db

28 Jan, 2026 3 commits
- [Bugfix] Add missing encoder only guard for do_kv_cache_update (#33269) · ab597c86
  Gregory Shtrasberg authored Jan 28, 2026
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
```
  ab597c86
- [ROCm] Enabling forward_includes_kv_cache on ROCm MHA backends (#33106) · 22ad6495
  Gregory Shtrasberg authored Jan 28, 2026
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
```
  22ad6495
- Add flake8-implicit-str-concat rules to Ruff (#33191) · 2eb673a0
  Harry Mellor authored Jan 28, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  2eb673a0
27 Jan, 2026 3 commits
- [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
- [Bugfix] Disable CG for Whisper+FA2 (#33164) · 1f3a2c29
  Nicolò Lucchesi authored Jan 27, 2026
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  1f3a2c29
- Fix IndexError with encoder-decoder models when using Custom Paged Attention (#33112) · c568581f
  Strahinja Stamenkovic authored Jan 27, 2026
```
Signed-off-by: sstamenk <strahinja.stamenkovic@amd.com>
```
  c568581f
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

23 Jan, 2026 6 commits
- fix: Add glm4_moe_lite to MLA detection (#32614) · 586a57ad
  Markus / Mark authored Jan 23, 2026
```
Signed-off-by: marksverdhei <marksverdhei@hotmail.com>
Signed-off-by: Markus / Mark <46672778+marksverdhei@users.noreply.github.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
```
  586a57ad
- [V1][Hybrid] Mamba Prefix Caching with align mode (#30877) · 5206e5e2
  Harry Huang authored Jan 24, 2026
```
Signed-off-by: huanghaoyan.hhy <huanghaoyan.hhy@alibaba-inc.com>
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
```
  5206e5e2
- [Feature]: Remove DtoH Copy for lfm2_vl On Default Stream (#32815) · 13d8746c
  tianshu-Michael-yu authored Jan 23, 2026
```
Signed-off-by: Tianshu Yu <tianshuyu.formal@gmail.com>
```
  13d8746c
- [Misc] Add `get_name` to missing AttentionBackends (#32698) · 160c6fa3
  Nicolò Lucchesi authored Jan 23, 2026
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  160c6fa3
- [CI][Models] Add VLM Support for Sequence Classification Conversion (#32885) · a8eb1182
  Andreas Karatzas authored Jan 23, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  a8eb1182
- [CI] Fix mypy for `vllm/v1/structured_output` (#32722) · 7ef58737
  Wentao Ye authored Jan 22, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  7ef58737
22 Jan, 2026 3 commits
- 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
- [Bugfix][Attention] Explicitly report support for kv_cache_dtype bfloat16 (#32795) · 955b43a5
  Matthew Bonanni authored Jan 22, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  955b43a5
- [FlashMLA] Update FlashMLA to expose new arguments (#32810) · 889722f3
  Lucas Wilkinson authored Jan 21, 2026
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  889722f3
21 Jan, 2026 1 commit
- [ModelRunner V2] Don't pin reused flashinfer tensors (#32799) · 24dc30f7
  Nick Hill authored Jan 21, 2026
```
Signed-off-by: Nick Hill <nickhill123@gmail.com>
```
  24dc30f7