Commits · a6bed85bf1fbaa1735ab2100a86c2641b15eec57 · OpenDAS / vllm_cscc

27 Nov, 2025 3 commits
- fix: 修改attetion这里的import bug · 8cfbe041
  wujl5 authored Nov 27, 2025
  
  8cfbe041
- update reshape_and_cache_cuda import · b550cf96
  zhuwenwen authored Nov 27, 2025
  
  b550cf96
- 增加VLLM_USE_OPT_RESHAPE_AND_CACHE 环境变量用来控制优化reshape and cache kernel · fe054987
  laibao authored Nov 27, 2025
  
  fe054987
10 Sep, 2025 1 commit
- support cascade_attention · ead74dfa
  zhuwenwen authored Sep 10, 2025
  
  ead74dfa
20 Aug, 2025 2 commits
- set v1 attention use fa · f7beb354
  zhuwenwen authored Aug 20, 2025
  
  f7beb354
- update value_stride_order · 716852ab
  zhuwenwen authored Aug 20, 2025
  
  716852ab
19 Aug, 2025 1 commit
- update v1 fa layout · 864c718a
  zhuwenwen authored Aug 19, 2025
  
  864c718a
14 Aug, 2025 1 commit
- remove seq_lens_tensor of v1 fa · 693d5ed4
  zhuwenwen authored Aug 14, 2025
  
  693d5ed4
13 Aug, 2025 1 commit
- add VLLM_USE_PA_PRINT_PARAM to print v1 fa size · 8a1e7a3d
  zhuwenwen authored Aug 13, 2025
  
  8a1e7a3d
08 Aug, 2025 1 commit
- update fa full_cuda_graph support · 513f17a4
  zhuwenwen authored Aug 08, 2025
  
  513f17a4
24 Jul, 2025 2 commits
- support full_cuda_graph · 8da1c576
  zhuwenwen authored Jul 24, 2025
  
  8da1c576
- update fa v1 interface · f9408aff
  zhuwenwen authored Jul 24, 2025
  
  f9408aff
07 Jul, 2025 1 commit
- update vllm_flash_attn_varlen_func · ef6c0877
  zhuwenwen authored Jul 07, 2025
  
  ef6c0877
06 Jul, 2025 1 commit
- [V1] Support any head size for FlexAttention backend (#20467) · 9fb52e52
  Cyrus Leung authored Jul 07, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  9fb52e52
04 Jul, 2025 1 commit
- update flash_attn.py · 4080ac85
  zhuwenwen authored Jul 04, 2025
  
  4080ac85
01 Jul, 2025 1 commit
- [CUDA graphs] Enable full cuda graphs with FA3 AoT scheduling (#20301) · 8acb4bad
  Woosuk Kwon authored Jul 01, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  8acb4bad
27 Jun, 2025 1 commit
- Quick Fix by adding conditional import for flash_attn_varlen_func in flash_attn (#20143) · dec197e3
  Chendi.Xue authored Jun 27, 2025
```
Signed-off-by: Chendi.Xue <chendi.xue@intel.com>
```
  dec197e3
26 Jun, 2025 1 commit
- [Hardware][Intel GPU] Add v1 Intel GPU support with Flash attention backend. (#19560) · b69781f1
  Kunshang Ji authored Jun 27, 2025
```
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
```
  b69781f1
25 Jun, 2025 1 commit
- [BugFix] Fix full-cuda-graph illegal memory access in FA3 (#20057) · 0f9e7354
  Lucas Wilkinson authored Jun 25, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  0f9e7354
17 Jun, 2025 2 commits
- [Feature][ROCm] Add full graph capture support for TritonAttentionBackend (#19158) · a44b1c95
  Charlie Fu authored Jun 17, 2025
```
Signed-off-by: charlifu <charlifu@amd.com>
```
  a44b1c95
- [V1][Kernel] Flashinfer HND KV cache layout (#19280) · 4c8f64fa
  Nicolò Lucchesi authored Jun 17, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  4c8f64fa
15 Jun, 2025 1 commit
- [Kernel] Raise verbose error and consolidate `num_heads/num_kv_heads` divisibility check (#19339) · 0b73736a
  22quinn authored Jun 14, 2025
```
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
```
  0b73736a
13 Jun, 2025 1 commit
- [CUDA] Enable full cudagraph for FlashMLA (#18581) · 3597b06a
  Luka Govedič authored Jun 13, 2025
```
Signed-off-by: luka <luka@neuralmagic.com>
```
  3597b06a
12 Jun, 2025 1 commit
- [torch.compile][ROCm] Fuse quantization onto attention using a torch.compile pass (#16756) · f98548b9
  Luka Govedič authored Jun 12, 2025
```
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: Sage Moore <sage@neuralmagic.com>
```
  f98548b9
04 Jun, 2025 2 commits
- [P/D] Heterogeneous TP (#18833) · b2fac671
  Nicolò Lucchesi authored Jun 05, 2025
```
Signed-off-by: nicklucche <nlucches@redhat.com>
```
  b2fac671
- [Bugfix] Fix FA3 full cuda graph correctness (#19106) · b124e108
  Woosuk Kwon authored Jun 03, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  b124e108
03 Jun, 2025 2 commits
- [V1] Support cross-layer KV sharing (#18212) · bdf13965
  Yong Hoon Shin authored Jun 03, 2025
```
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
```
  bdf13965
- [Misc] Add SPDX-FileCopyrightText (#19100) · 02f0c7b2
  Simon Mo authored Jun 03, 2025
```
Signed-off-by: simon-mo <simon.mo@hey.com>
```
  02f0c7b2
28 May, 2025 1 commit
- set VLLM_FLASH_ATTN_BACKEND to use FlashAttention Backend for attention computation on rocm · 82f60bef
  zhuwenwen authored May 28, 2025
  
  82f60bef
26 May, 2025 1 commit
- fix kernels tests of attention and core · f1467ce5
  zhuwenwen authored May 26, 2025
  
  f1467ce5
10 May, 2025 1 commit
- [v1] Pass BlockTable and KVCacheSpec to AttentionMetadataBuilders (#17483) · 950751a9
  Chen Zhang authored May 11, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  950751a9
08 May, 2025 1 commit

[Core] Support full cuda graph in v1 (#16072) · 7ea2adb8

Chanh Nguyen authored May 07, 2025


Signed-off-by: Chanh Nguyen <cnguyen@linkedin.com>
Co-authored-by: Chanh Nguyen <cnguyen@linkedin.com>

7ea2adb8

06 May, 2025 1 commit
- [v1] AttentionMetadata for each layer (#17394) · cba31c47
  Chen Zhang authored May 06, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  cba31c47
02 May, 2025 2 commits
- [BugFix][Attention] Fix sliding window attention in V1 giving incorrect results (#17574) · 3015d563
  Lucas Wilkinson authored May 02, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
```
  3015d563
- [BugFix][Attention] Fix sliding window attention in V1 giving incorrect results (#17574) · 0f87d8f7
  Lucas Wilkinson authored May 02, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
```
  0f87d8f7
29 Apr, 2025 1 commit
- [V1] Remove num_input_tokens from attn_metadata (#17193) · 24e6ad3f
  Chen Zhang authored Apr 30, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  24e6ad3f
28 Apr, 2025 2 commits

[BugFix] Fix cascade attention - RuntimeError: scheduler_metadata must have... · cc5befbc

Lucas Wilkinson authored Apr 28, 2025


[BugFix] Fix cascade attention - RuntimeError: scheduler_metadata must have shape (metadata_size) (#17283)
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>

cc5befbc

[BugFix] Fix vllm_flash_attn install issues (#17267) · d8bccde6

Lucas Wilkinson authored Apr 27, 2025


Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Aaron Pham <contact@aarnphm.xyz>

d8bccde6

23 Apr, 2025 1 commit
- [BugFix] llama4 fa3 fix - RuntimeError: scheduler_metadata must have shape (metadata_size) (#16998) · d0da99fb
  Lucas Wilkinson authored Apr 23, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
```
  d0da99fb
22 Apr, 2025 1 commit

[V1] V1 FlashInfer Attention (#16684) · 986537f1

Michael Goin authored Apr 21, 2025


Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Aurick Qiao <qiao@aurick.net>

986537f1