Commits · 2f7dbc9b42c51ba192e3dded515e4e07cdfdabea · OpenDAS / vllm_cscc

04 Oct, 2025 1 commit

Add batch invariant kernel override for FlashInfer backend [2/n] (#25769) · 2f7dbc9b

Bram Wasti authored Oct 03, 2025


Signed-off-by: Bram Wasti <bwasti@meta.com>
Signed-off-by: Bram Wasti <bwasti@fb.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>

2f7dbc9b

03 Oct, 2025 2 commits
- [backends][short_conv] CUDA graph piecewise edits (#24215) · 5f42fc53
  Paul Pak authored Oct 03, 2025
```
Signed-off-by: Paul Pak <paulpak58@gmail.com>
```
  5f42fc53
- Quick fix for IMA with the Prefix Prefill kernel during graph capture (#25983) · 5f2cacdb
  Sage Moore authored Oct 03, 2025
```
Signed-off-by: Sage Moore <sage@neuralmagic.com>
```
  5f2cacdb
02 Oct, 2025 4 commits

[Bugfix] Disable cascade attention with FlashInfer (#26130) · f1fc2107

Michael Goin authored Oct 02, 2025

Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

f1fc2107

[Deepseek v3.2] Support indexer prefill chunking (#25999) · 1e50f1be
Chen Zhang authored Oct 02, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
1e50f1be

[BugFix] Fix FI accuracy issue when used for MLA prefill (#26063) · decf7f79

Lucas Wilkinson authored Oct 02, 2025

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: mgoin <mgoin64@gmail.com>

decf7f79

[ROCm][Bugfix] Add missing parameter to ROCm backend (#26029) · 0b018d8b
Gregory Shtrasberg authored Oct 01, 2025
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
```
0b018d8b

01 Oct, 2025 2 commits
- Fix test_mamba_ssm_ssd.py due to missing _query_start_loc_to_chunk_indices_offsets (#25995) · c36f0aa3
  Huamin Li authored Oct 01, 2025
```
Signed-off-by: Huamin Li <3ericli@gmail.com>
```
  c36f0aa3
- [Model] MTP fallback to eager for DeepSeek v32 (#25982) · 001e50c9
  Lucia Fang authored Sep 30, 2025
```
Signed-off-by: Lu Fang <fanglu@fb.com>
```
  001e50c9
30 Sep, 2025 1 commit

[New Model] DeepSeek-V3.2 (Rebased to Main) (#25896) · fa7e254a

Yongye Zhu authored Sep 30, 2025


Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Signed-off-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>
Signed-off-by: Lucia Fang <fanglu@meta.com>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Lucia Fang <116399278+luccafong@users.noreply.github.com>
Co-authored-by: Lucia Fang <fanglu@meta.com>
Co-authored-by: NickLucche <nlucches@redhat.com>
Co-authored-by: Siyuan Fu <siyuanf@nvidia.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Xiaozhu Meng <mxz297@gmail.com>
Co-authored-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>

fa7e254a

29 Sep, 2025 1 commit
- [Kernel] Chunk-aligned mamba2 (#24683) · fea3e476
  Thomas Parnell authored Sep 29, 2025
  
  fea3e476
26 Sep, 2025 4 commits
- Kernel-override Determinism [1/n] (#25603) · dc48ba0c
  Bram Wasti authored Sep 26, 2025
```
Signed-off-by: Bram Wasti <bwasti@meta.com>
```
  dc48ba0c
- [Model] Mamba2 varlen refactor (#21467) · 2b6b1d78
  Chih-Chieh Yang authored Sep 26, 2025
```
Signed-off-by: Chih-Chieh-Yang <7364402+cyang49@users.noreply.github.com>
Co-authored-by: RishiAstra <40644327+RishiAstra@users.noreply.github.com>
```
  2b6b1d78
- Remove cuda hard-code in compute_causal_conv1d_metadata (#25555) · dd70437a
  Icey authored Sep 26, 2025
```
Signed-off-by: Icey <1790571317@qq.com>
```
  dd70437a
- [Qwen3-Next][GDN] fixes cuda graph capturing bug in GDN metadata and a stride... · 99b3a504
  Tao He authored Sep 26, 2025
```
[Qwen3-Next][GDN] fixes cuda graph capturing bug in GDN metadata and a stride bug in causal_conv_1d. (#25743)
Signed-off-by: Tao He <linzhu.ht@alibaba-inc.com>
```
  99b3a504
25 Sep, 2025 4 commits
- [V0 deprecation] Remove _VLLM_V1 suffixes from attention backend names (#25489) · 3468f17e
  Matthew Bonanni authored Sep 25, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
```
  3468f17e
- [CPU] update torch 2.8 and fix missing fields in TorchSDPAMetadata (#25652) · eb32335e
  Li, Jiang authored Sep 25, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
  eb32335e
- [torch.compile] Make Query Quantization Fusable (#24914) · 69a8c8e9
  Jonas M. Kübler authored Sep 25, 2025
```
Signed-off-by: Jonas Kuebler <kuebj@amazon.com>
```
  69a8c8e9
- [Kernel] Support DCP for Triton backend (#25132) · 05c19485
  Wei Wei authored Sep 24, 2025
```
Signed-off-by: Wei Wei <wwei6@meta.com>
```
  05c19485
24 Sep, 2025 5 commits
- [V0 Deprecation] Remove unused classes in attention (#25541) · e6750d0b
  Woosuk Kwon authored Sep 24, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
```
  e6750d0b
- [BugFix] Potential Fix for FA3 full-cudagraph IMA (#25490) · 2338daff
  Lucas Wilkinson authored Sep 24, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  2338daff
- [Spec Decode] Enable FlashInfer Spec Decoding (#25196) · c30b405b
  Benjamin Chislett authored Sep 23, 2025
```
Signed-off-by: Benjamin Chislett <benjamin.chislett@centml.ai>
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Co-authored-by: lhsjohn <huashuoli@tencent.com>
```
  c30b405b
- [BugFix] Fix MLA assert with CUTLASS MLA (#25478) · 9df8da54
  Lucas Wilkinson authored Sep 23, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  9df8da54
- [Bugfix] Use a separate FlashInfer workspace buffer for trtllm-gen (#25520) · 19836092
  Benjamin Chislett authored Sep 23, 2025
  
  19836092
23 Sep, 2025 5 commits

[V1][Kernel] Add triton implementation for `reshape_and_cache_flash` (#24503) · 100b630a

Burkhard Ringlein authored Sep 23, 2025

Signed-off-by: Burkhard Ringlein <ngl@zurich.ibm.com>
Co-authored-by: Chih-Chieh Yang <chih.chieh.yang@ibm.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>

100b630a

[Core/DBO][2/N] Dual-Batch Overlap add DeepEP High Throughput support and Prefill support (#24845) · cc1dc7ed

Lucas Wilkinson authored Sep 23, 2025


Signed-off-by: Sage Moore <sage@neuralmagic.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Sage Moore <sage@neuralmagic.com>
Co-authored-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>

cc1dc7ed

[V1] Remove V0 code paths for Hybrid models (#25400) · a903669e
Thomas Parnell authored Sep 23, 2025
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
```
a903669e
[Bug] Fix Long Context OOM Issue (#25290) · 4741239d
Wentao Ye authored Sep 22, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
4741239d
[Performance] Remove input pads in cutlass_mla and optimize v_proj output handling (#25184) · 0b7bed9c
Alexander Matveev authored Sep 22, 2025
```
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
```
0b7bed9c

22 Sep, 2025 3 commits
- [CLI env var] Add VLLM_FLASH_ATTN_MAX_NUM_SPLITS_FOR_CUDA_GRAPH in env variables (#25274) · cfbee3d0
  Daisy-Ma-coder authored Sep 22, 2025
```
Signed-off-by: qqma <qqma@amazon.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: qqma <qqma@amazon.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  cfbee3d0
- [V1][Attention] Split triton_attn in triton-only and rocm specific backends (#24648) · 175811e3
  Burkhard Ringlein authored Sep 22, 2025
```
Signed-off-by: Burkhard Ringlein <ngl@zurich.ibm.com>
```
  175811e3
- [V0 Deprecation] Remove `MultiModalPlaceholderMap` (#25366) · f92d9526
  Cyrus Leung authored Sep 22, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  f92d9526
21 Sep, 2025 1 commit
- [V1] Add sliding window support to Flex Attention backend (#24089) · cf56cf78
  Isotr0py authored Sep 21, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  cf56cf78
19 Sep, 2025 2 commits
- allow disable flashinfer prefill (#25276) · ee7a66dd
  Lucia Fang authored Sep 19, 2025
```
Signed-off-by: Lu Fang <fanglu@fb.com>
```
  ee7a66dd
- [BugFix] Make FlashInferMetadataBuilder non-blocking (#25040) · b1a63d1b
  nvjullin authored Sep 20, 2025
```
Signed-off-by: Julien Lin <jullin@nvidia.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  b1a63d1b
18 Sep, 2025 4 commits
- [Bug] Fix `returned_lse` not Defined issue (#25106) · 75fb112d
  Wentao Ye authored Sep 18, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
```
  75fb112d
- [ROCm][AITER][Bugfix] Switch AITER to use PIECEWISE_AND_FULL compilation (#25104) · bbdc0f23
  Rohan Potdar authored Sep 18, 2025
```
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
```
  bbdc0f23
- [New Model] Support BertForTokenClassification / Named Entity Recognition (NER) task (#24872) · 5f696c33
  wang.yuqi authored Sep 18, 2025
```
Signed-off-by: wang.yuqi <noooop@126.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  5f696c33
- [PERF] Add `conv1d` metadata to GDN attn (#25105) · 072d7e53
  Vadim Gimpelson authored Sep 18, 2025
```
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
```
  072d7e53
17 Sep, 2025 1 commit

[Bugfix] Refactor Flashinfer TRTLLM attention kernel selection logic (#24600) · e67a79db

elvischenv authored Sep 18, 2025


Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

e67a79db