Commits · 379ea2823a751ef43de7b3e7bcb3262b1e14c510 · OpenDAS / vllm_cscc

29 Aug, 2025 1 commit

Update PyTorch to 2.8.0 (#20358) · 67c14906

Huy Do authored Aug 29, 2025


Signed-off-by: Huy Do <huydhn@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

67c14906

28 Aug, 2025 3 commits
- [V1] Enable prefill optimization for Gemma3n (#22628) · cb293f6a
  Yong Hoon Shin authored Aug 28, 2025
```
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
```
  cb293f6a
- [BugFix][FlashInfer] Fix potential race condition for paged_kv_indptr_cpu (#23737) · 7ffbf272
  Woosuk Kwon authored Aug 28, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  7ffbf272
- [ROCm][Aiter] Add triton fp8 bmm kernel for mla (#23264) · 04d1dd7f
  Divakar Verma authored Aug 28, 2025
```
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Co-authored-by: ShaoChunLee <Shao-Chun.Lee@amd.com>
```
  04d1dd7f
27 Aug, 2025 3 commits
- [Docs] Fix warnings in `mkdocs build` (continued) (#23743) · 4e4d017b
  Hyogeun Oh (오효근) authored Aug 28, 2025
```
Signed-off-by: Zerohertz <ohg3417@gmail.com>
Signed-off-by: Hyogeun Oh (오효근) <ohg3417@gmail.com>
```
  4e4d017b
- [FlashInfer] Cache hyper params in metadata builder (#23732) · 11eddf02
  Woosuk Kwon authored Aug 27, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  11eddf02
- Optimize input preparation for FlashInfer [2/N] (#23174) · 6578e873
  Woosuk Kwon authored Aug 27, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  6578e873
25 Aug, 2025 3 commits
- [Misc] Simplify FlashInfer attention metadata (#23585) · efc88cf6
  Woosuk Kwon authored Aug 25, 2025
```
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
```
  efc88cf6
- Updates to Flex + VLLm integration (#21416) · e0329ed4
  Driss Guessous authored Aug 25, 2025
```
Signed-off-by: drisspg <drisspguessous@gmail.com>
```
  e0329ed4
- [Attention] Unify mamba and attention backend selection (#23171) · 5c4b6e66
  Ayush Satyam authored Aug 25, 2025
```
Signed-off-by: Ayush Satyam <ayushsatyam146@gmail.com>
```
  5c4b6e66
22 Aug, 2025 4 commits
- [NVIDIA][torch.compile] Support Flashinfer TRTLLM FP8-q/kv NVFP4-out Attention Kernel (#22703) · 24d0c9e6
  elvischenv authored Aug 23, 2025
```
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  24d0c9e6
- [Attention] Allow V1 flash_attn to support cross-attention (#23297) · 281710ef
  Russell Bryant authored Aug 22, 2025
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  281710ef
- [Attention] Refactor AttentionMetadata Preparation for Encoder-only Models (#23154) · 17373dcd
  Chen Zhang authored Aug 21, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  17373dcd
- [Kernel] Add FP8 support with FlashMLA backend (#22668) · 19fe1a05
  Matthew Bonanni authored Aug 21, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
```
  19fe1a05
21 Aug, 2025 3 commits
- [Core] Always use tensor cores for Flashinfer Decode Wrapper (#23214) · 1d353b63
  Pavani Majety authored Aug 21, 2025
```
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
```
  1d353b63
- [Model] Add LFM2 architecture (#22845) · 2e2000f3
  Paul Pak authored Aug 21, 2025
```
Signed-off-by: Paul Pak <paulpak58@gmail.com>
```
  2e2000f3
- [V1][Mamba1] - Full CUDA and Piecewise CUDA Graphs Support (#23035) · 3663870c
  Asaf Joseph Gardin authored Aug 21, 2025
```
Signed-off-by: asafg <asafg@ai21.com>
Signed-off-by: asafg <39553475+Josephasafg@users.noreply.github.com>
Co-authored-by: asafg <asafg@ai21.com>
```
  3663870c
20 Aug, 2025 5 commits
- Feature/mla tests (#23195) · 10cc12ba
  Matthew Bonanni authored Aug 20, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  10cc12ba
- Remove chunked_prefill_enabled flag in V1 MLA (#23183) · a4fbb32f
  Matthew Bonanni authored Aug 20, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
```
  a4fbb32f
- [Misc] Add max_seq_len to CommonAttentionMetadata (#23216) · d6d13bd4
  Woosuk Kwon authored Aug 20, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  d6d13bd4
- fix cuda graph (#22721) · d983769c
  who who who authored Aug 20, 2025
```
Signed-off-by: fsx950223 <fsx950223@outlook.com>
```
  d983769c
- [Attention] Optimize make_local_attention_virtual_batches for Flash Attention (#23185) · a634733f
  Zebing Lin authored Aug 19, 2025
```
Signed-off-by: linzebing <linzebing1995@gmail.com>
```
  a634733f
19 Aug, 2025 6 commits
- [BugFix] fix CUTLASS MLA full cudagraph (#23200) · 14e2b073
  Lucas Wilkinson authored Aug 19, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  14e2b073
- [Misc] Minor refactoring for FlashInfer backend (#23147) · e61bac87
  Woosuk Kwon authored Aug 19, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  e61bac87
- [Misc] Enable yapf for FlashInfer backend (#23193) · 5b5f350d
  Woosuk Kwon authored Aug 19, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  5b5f350d
- [NVIDIA] Support Flashinfer TRTLLM FP8-q/kv/out Attention Kernel (#21716) · 03752dba
  elvischenv authored Aug 19, 2025
```
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  03752dba
- [Log] Warning Once for Cutlass MLA (#23137) · 90bbe0a5
  Wentao Ye authored Aug 19, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  90bbe0a5
- [TPU] make ptxla not imported when using tpu_commons (#23081) · e9d6a3db
  Chengji Yao authored Aug 18, 2025
```
Signed-off-by: Chengji Yao <chengjiyao@gmail.com>
Signed-off-by: Chengji Yao <chengjiyao@google.com>
Co-authored-by: Chengji Yao <chengjiyao@gmail.com>
```
  e9d6a3db
16 Aug, 2025 2 commits
- [Bugfix gpt-oss] Fix float32 convert for flashinfer sink support (#23016) · 000cceca
  Michael Goin authored Aug 16, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  000cceca
- [Kernel] Simplify `get_kv_cache_layout` and cache `use_trtllm_attention` env-dependent bit (#22735) · 070da660
  Nicolò Lucchesi authored Aug 16, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  070da660
15 Aug, 2025 5 commits

minor: zero workspace buffer init for flashinfer trtllm-gen attn (#22603) · 1723ef1a
eigen authored Aug 15, 2025

1723ef1a

[Core] Allow full cudagraph with separate attention routines and orthogonal to... · 74f441f4

fhl2000 authored Aug 15, 2025


[Core] Allow full cudagraph with separate attention routines and orthogonal to compilation, add support for FA2 and FlashInfer (#20059)
Signed-off-by: fhl <2410591650@qq.com>
Signed-off-by: fhl2000 <63384265+fhl2000@users.noreply.github.com>
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>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>

74f441f4

[V1] - Split Prefill and Decode for Mamba1 models (#22653) · fe91ce95

amirai21 authored Aug 15, 2025


Signed-off-by: amirk <amirk@ai21.com>
Signed-off-by: asafg <asafg@ai21.com>
Co-authored-by: asafg <asafg@ai21.com>
Co-authored-by: Asaf Joseph Gardin <39553475+Josephasafg@users.noreply.github.com>

fe91ce95

[Mamba] - refactor: Renamed mamba_attn to mamba2_attn (#22818) · 3d232dbd
Asaf Joseph Gardin authored Aug 15, 2025
```
Signed-off-by: asafg <asafg@ai21.com>
Co-authored-by: asafg <asafg@ai21.com>
```
3d232dbd
[Feature] Full Cuda Graph Support for Cutlass MLA and 6% E2E Throughput Improvement (#22763) · 5c3fbfe4
Wentao Ye authored Aug 15, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
5c3fbfe4

13 Aug, 2025 3 commits
- [Bugfix][mamba] Fix type annotation of Mamba2Metadata (#22787) · fceafaf5
  Chen Zhang authored Aug 13, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  fceafaf5
- [V1] Add tree drafting tests for eagle spec decoding (#22705) · d94e3026
  Giancarlo Delfin authored Aug 13, 2025
```
Signed-off-by: Giancarlo Delfin <gdelfin@meta.com>
```
  d94e3026
- Force TRTLLM attention for gpt-oss on SM100 (#22678) · c6b92879
  Michael Goin authored Aug 13, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  c6b92879
12 Aug, 2025 2 commits

[Kernel][AMD] Avoid D2H copy and cumsum kernel (#22683) · 6bd8ebf0

Xiaozhu Meng authored Aug 12, 2025


Signed-off-by: Xiaozhu <mxz297@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

6bd8ebf0

[Bugfix] Fix ModernBert load & Enable sliding window attention for... · 6d729c43

wang.yuqi authored Aug 12, 2025


[Bugfix] Fix ModernBert load & Enable sliding window attention for bidirectional attention. (#22637)
Signed-off-by: wang.yuqi <noooop@126.com>
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Max de Bayser <mbayser@br.ibm.com>

6d729c43