Commits · 6f1db287efaf173acceca7e7d6eef75ba0121fc3 · OpenDAS / vllm_cscc · GitLab

23 Oct, 2025 1 commit

support prefix cache on kme · 6f1db287

zhuwenwen authored Oct 23, 2025

fix the error in test_moe caused by moe align not supporting 511
multi-modal switching to torch implementation on z100l&k100

6f1db287

30 Sep, 2025 1 commit
- fix Z100L&K100 precision error · 9e5ec696
  zhuwenwen authored Sep 30, 2025
  
  9e5ec696
29 Sep, 2025 1 commit
- when v1 is set to block_size 16, switch to triton implementation · e470f6a1
  zhuwenwen authored Sep 29, 2025
  
  e470f6a1
01 Sep, 2025 1 commit
- add dca and sparse attention support on rocm · 12112a4d
  zhuwenwen authored Sep 01, 2025
  
  12112a4d
27 Aug, 2025 1 commit
- feat: w4a8 marlin合入主分支, 通过-q slimquant_w4a8_marlin 可以启用 · 533d4c72
  jujl1 authored Aug 27, 2025
  
  533d4c72
20 Aug, 2025 1 commit
- set v1 attention use fa · f7beb354
  zhuwenwen authored Aug 20, 2025
  
  f7beb354
07 Aug, 2025 1 commit
- 修改增加lmslimquant_w4a8量化支持 · 8b1e4ef0
  gaoqiong authored Aug 07, 2025
  
  8b1e4ef0
06 Aug, 2025 1 commit
- update VLLM_FLASH_ATTN_V1 to VLLM_USE_FLASH_ATTN_PA · 88dbf92c
  zhuwenwen authored Aug 06, 2025
  
  88dbf92c
01 Aug, 2025 2 commits
- update rocm.py · 0480314d
  zhuwenwen authored Aug 01, 2025
  
  0480314d
- update HIP_VISIBLE_DEVICES of rocm · d0cc5577
  zhuwenwen authored Aug 01, 2025
  
  d0cc5577
26 Jul, 2025 1 commit
- 增加moe awq-marlin的支持 · c2bcb0ab
  yangql authored Jul 26, 2025
  
  c2bcb0ab
03 Jul, 2025 1 commit
- update VLLM_FLASH_ATTN_BACKEND to VLLM_FLASH_ATTN_V1 · 64fc5a29
  zhuwenwen authored Jul 03, 2025
  
  64fc5a29
02 Jul, 2025 1 commit
- [UT][intel GPU] use current_platform instead of device hardcode in v1 tests (#20169) · a0389e05
  Liangliang Ma authored Jul 02, 2025
```
Signed-off-by: Ma, Liangliang <liangliang.ma@intel.com>
```
  a0389e05
01 Jul, 2025 1 commit
- [BugFix][V1][ROCm] Triton MLA uses V0 backend on V1 engine (#19067) · 96453cfa
  TY-AMD authored Jul 01, 2025
```
Signed-off-by: Tianyuan Wu <Tianyuan.Wu@amd.com>
```
  96453cfa
27 Jun, 2025 1 commit
- 1.临时解决gemm调用到blaslt问题 · 6d172ab4
  王敏 authored Jun 27, 2025
```
2.支持设置v1的chunked_prefill开关
```
  6d172ab4
18 Jun, 2025 1 commit

[Hardware][AMD] integrate aiter chunked prefill into vllm (#18596) · 8b6e1d63

Zzz9990 authored Jun 18, 2025


Signed-off-by: fsx950223 <fsx950223@outlook.com>
Signed-off-by: charlifu <charlifu@amd.com>
Co-authored-by: fsx950223 <fsx950223@outlook.com>
Co-authored-by: charlifu <charlifu@amd.com>

8b6e1d63

17 Jun, 2025 1 commit
- [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
03 Jun, 2025 1 commit
- [Misc] Add SPDX-FileCopyrightText (#19100) · 02f0c7b2
  Simon Mo authored Jun 03, 2025
```
Signed-off-by: simon-mo <simon.mo@hey.com>
```
  02f0c7b2
31 May, 2025 1 commit
- [ROCm][Kernel] Add gfx950 support for skinny gemms (#18010) · 306d6040
  Charlie Fu authored May 31, 2025
```
Signed-off-by: charlifu <charlifu@amd.com>
```
  306d6040
29 May, 2025 2 commits
- [ROCm][V0][Attention] Revert to the previous FA triton kernel (#18226) · 1b7cfd5a
  Gregory Shtrasberg authored May 29, 2025
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
```
  1b7cfd5a
- [tests]fix start with test and async_engine · 2664c459
  zhuwenwen authored May 29, 2025
  
  2664c459
28 May, 2025 4 commits
- [Platform][Dist] Make torch distributed process group extendable (#18763) · d781930f
  Mengqing Cao authored May 28, 2025
```
Signed-off-by: Mengqing Cao <cmq0113@163.com>
```
  d781930f
- update use_rocm_custom_paged_attention · df877aad
  zhuwenwen authored May 28, 2025
  
  df877aad
- [rocm] Fix wrong attention log (#18764) · 794ae1f5
  fxmarty-amd authored May 28, 2025
```
Signed-off-by: Felix Marty <felmarty@amd.com>
```
  794ae1f5
- set VLLM_FLASH_ATTN_BACKEND to use FlashAttention Backend for attention computation on rocm · 82f60bef
  zhuwenwen authored May 28, 2025
  
  82f60bef
23 May, 2025 1 commit
- [Hardware] correct method signatures for HPU,ROCm,XPU (#18551) · 60cad94b
  Ning Xie authored May 23, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  60cad94b
22 May, 2025 1 commit
- [Compile][Platform] Make PiecewiseBackend pluggable and extendable (#18076) · f8d2cc5f
  Mengqing Cao authored May 23, 2025
```
Signed-off-by: Mengqing Cao <cmq0113@163.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
```
  f8d2cc5f
21 May, 2025 1 commit
- [ROCm][Kernel][V1] Enable AMD Radeon GPU Custom Paged Attention on v1 (#17004) · dd5fa7e0
  Hosang authored May 21, 2025
```
Signed-off-by: Hosang Yoon <hosang.yoon@amd.com>
```
  dd5fa7e0
14 May, 2025 1 commit
- Update deprecated type hinting in `platform`, `plugins`, `triton_utils`, `vllm_flash_attn` (#18129) · c8ea982d
  Harry Mellor authored May 14, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  c8ea982d
12 May, 2025 1 commit
- [Core] Use platform-agnostic device control for DP engine core (#17245) · 289199fe
  Jade Zheng authored May 13, 2025
```
Signed-off-by: Jade Zheng <zheng.shoujian@outlook.com>
```
  289199fe
09 May, 2025 1 commit

[FEAT][ROCm]: Support AITER MLA on V1 Engine (#17523) · 3c9396a6

vllmellm authored May 09, 2025


Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: qli88 <qiang.li2@amd.com>
Co-authored-by: Hongxia Yang <62075498+hongxiayang@users.noreply.github.com>

3c9396a6

08 May, 2025 1 commit

[Kernel][Hardware][AMD] Bf16 mfma opt for ROCm skinny GEMMs (#17071) · 5a499e70

Hashem Hashemi authored May 07, 2025


Signed-off-by: Hashem Hashemi <hashem.hashemi@amd.com>
Signed-off-by: charlifu <charlifu@amd.com>
Co-authored-by: charlifu <charlifu@amd.com>

5a499e70

07 May, 2025 2 commits
- [Quantization] Quark MXFP4 format loading (#16943) · db593aa6
  Bowen Bao authored May 07, 2025
  
  db593aa6
- update rocm.py · 660af62e
  zhuwenwen authored May 07, 2025
  
  660af62e
02 May, 2025 1 commit
- [Hardware][AMD] Improve OAM device ID + llama4 Maverick MOE tuning (#16263) · 9352cdb5
  Xiaodong Wang authored May 02, 2025
```
Signed-off-by: Lu Fang <lufang@fb.com>
Co-authored-by: Lu Fang <lufang@fb.com>
```
  9352cdb5
01 May, 2025 1 commit

[ROCM] Add gfx950 to the custom attention archs (#16034) · 811a6c09

Juan Villamizar authored May 01, 2025


Signed-off-by: jpvillam <Juan.Villamizar@amd.com>
Signed-off-by: seungrokjung <seungrok.jung@amd.com>
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Co-authored-by: seungrokjung <seungrok.jung@amd.com>
Co-authored-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>

811a6c09

29 Apr, 2025 1 commit
- update rocm.py · 43a52016
  zhuwenwen authored Apr 29, 2025
  
  43a52016
28 Apr, 2025 1 commit
- Make name of `compressed-tensors` quant method consistent across vLLM (#17255) · b6dd32aa
  Harry Mellor authored Apr 28, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  b6dd32aa
27 Apr, 2025 1 commit
- [MISC] Use string annotation types for class definitions (#17244) · 30215ca6
  Jade Zheng authored Apr 27, 2025
```
Signed-off-by: Jade Zheng <zheng.shoujian@outlook.com>
```
  30215ca6
26 Apr, 2025 1 commit
- [ROCm][Misc] Follow-ups for Skinny Gemms on ROCm. (#17011) · 54271bb7
  Charlie Fu authored Apr 26, 2025
```
Signed-off-by: charlifu <charlifu@amd.com>
```
  54271bb7