Commits · e30c273bc9bbb2ea31268b22b67ba8221e058e2c · change / sglang

"examples/community/stable_diffusion_xl_reference.py" did not exist on "ecded50ad58b6c297da261397b9fc3930690812f"

09 May, 2025 3 commits
- opt flashinfer mla cat (#5822) · e30c273b
  xu-yfei authored May 09, 2025
```
Co-authored-by: xuyongfei.xyf <xuyongfei.xyf@antgroup.com>
```
  e30c273b
- Cutlass MLA: Disable split kv due to https://github.com/NVIDIA/cutlass/issues/2274 (#6101) · 0ab3f437
  Trevor Morris authored May 08, 2025
  
  0ab3f437
- [Fix] Incorrect Memory Allocation on CUDA:0 by Non-Zero CUDA Processes in TP/DP (#5745) · cec98f10
  yhyang201 authored May 09, 2025
  
  cec98f10
08 May, 2025 23 commits
- docs: update README (#6132) · 8dc4efd0
  Yineng Zhang authored May 08, 2025
  
  8dc4efd0
- chore: bump sgl-kernel 0.1.2 (#6131) · 6578cf27
  Yineng Zhang authored May 08, 2025
  
  6578cf27
- Remove unecessary is_fa3_supported check (#6112) · 087751a8
  Stefan He authored May 08, 2025
  
  087751a8
- upgrade xgrammar to 0.1.19 (#6129) · 911f3ba6
  Yixin Dong authored May 08, 2025
  
  911f3ba6
- [sgl-kernel] fix: fix cu118 compile error (#6123) · f6f96b05
  PGFLMG authored May 09, 2025
```
Co-authored-by: zhyncs <me@zhyncs.com>
```
  f6f96b05
- [AMD] switch to custom allreduce regardless of MSCCL setting on ROCm (#6097) · 2a936a84
  Hubert Lu authored May 08, 2025
  
  2a936a84
- [perf] dsv3 bmm fallback to bf16 (#5662) · 5e023301
  JieXin Liang authored May 09, 2025
  
  5e023301
- [Feature] Add FlashAttention3 as a backend for VisionAttention (#5764) · fa7d7fd9
  Zhu Chen authored May 09, 2025
```
Co-authored-by: othame <chenzhu_912@zju.edu.cn>
Co-authored-by: Mick <mickjagger19@icloud.com>
Co-authored-by: Yi Zhang <1109276519@qq.com>
```
  fa7d7fd9
- [fix] fix pyproject.toml dependencies (#6119) · f1ff736d
  JieXin Liang authored May 08, 2025
  
  f1ff736d
- DeepEP normal support deepgemm-contiguous (#5626) · acc816d8
  lukec authored May 08, 2025
```
Co-authored-by: Yingyi Huang <yingyihuang2000@outlook.com>
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
Co-authored-by: Xuting Zhou <xutingz@nvidia.com>
Co-authored-by: ZhengHSI <zhenghsi@qq.com>
```
  acc816d8
- Change AMD test threshold (#6091) · a05bd83a
  fzyzcjy authored May 08, 2025
  
  a05bd83a
- [PD] Add control to slow down a server (#5572) · cef91b1e
  fzyzcjy authored May 08, 2025
  
  cef91b1e
- Tiny refactor weight loading logic (#5232) · 6450c122
  fzyzcjy authored May 08, 2025
  
  6450c122
- Tiny refactor ModelConfig.from_server_args (#5219) · b6cf3532
  fzyzcjy authored May 08, 2025
  
  b6cf3532
- Overlap shared expert and routed expert computations (#5121) · 3b2680a4
  fzyzcjy authored May 08, 2025
  
  3b2680a4
- optimize pad operations in fa3 to accelarate 100+us (#6077) · 79961afa
  Minglei Zhu authored May 07, 2025
  
  79961afa
- adding Triton configs for DeepSeekV3 FusedMoE kernel on Blackwell (#6111) · cfca4e0e
  Baizhou Zhang authored May 07, 2025
  
  cfca4e0e
- [CI]Add performance CI for VLM (#6038) · e88dd482
  XinyuanTong authored May 07, 2025
```
Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
```
  e88dd482
- Clean logs for DeepSeek-V3 launching (#6079) · 73600673
  Baizhou Zhang authored May 07, 2025
  
  73600673
- Update doc for MLA attention backends (#6034) · 8f508cc7
  Baizhou Zhang authored May 07, 2025
  
  8f508cc7
- Deferring 8 GPU test (#6102) · 9bddf1c8
  Cheng Wan authored May 07, 2025
  
  9bddf1c8
- Clean up fa3 test from 8 gpus (#6105) · 24c13ca9
  Stefan He authored May 07, 2025
  
  24c13ca9
- [refactor] slightly tidy fp8 module (#5993) · b70957fc
  JieXin Liang authored May 08, 2025
  
  b70957fc
07 May, 2025 9 commits
- feat(engine): add bootstrap parameters to generate methods (dynamo) (#6075) · e444c13f
  ishandhanani authored May 07, 2025
  
  e444c13f
- [Doc]Fix description for dp_size argument (#6063) · fee37d9e
  Baizhou Zhang authored May 07, 2025
  
  fee37d9e
- Super tiny fix doc (#5233) · c68de479
  fzyzcjy authored May 07, 2025
  
  c68de479
- Hint users DeepEP normal mode is incompatible with CUDA Graph (#5014) · 4c7b4242
  fzyzcjy authored May 07, 2025
  
  4c7b4242
- Fix the timeout for 8 gpu tests (#6084) · 38053c33
  Lianmin Zheng authored May 07, 2025
  
  38053c33
- [Feature] Support for Ascend NPU backend (#3853) · 00c2c1f0
  Song Zhang authored May 07, 2025
```
Signed-off-by: Song Zhang <gepin.zs@antgroup.com>
Co-authored-by: 22dimensions <waitingwind@foxmail.com>
```
  00c2c1f0
- feat: add release workflow for SGLang kernels on aarch64 (#6010) · cb691945
  Johnny authored May 07, 2025
```
Co-authored-by: Qiaolin-Yu <liin1211@outlook.com>
Co-authored-by: Yineng Zhang <me@zhyncs.com>
```
  cb691945
- fix custom_allreduce namespace (#6039) · d25398cb
  Xiaoyu Zhang authored May 07, 2025
  
  d25398cb
- Add DeepEP to CI PR Test (#5655) · 8a828666
  Jinyan Chen authored May 07, 2025
```
Co-authored-by: Jinyan Chen <jinyanc@nvidia.com>
```
  8a828666
06 May, 2025 5 commits
- Fix sgl-kernel build on aarch64 platforms (#6062) · aff584fa
  Qiaolin Yu authored May 06, 2025
  
  aff584fa
- chore: upgrade cutlass 3.9.2 (#6004) · 6f566147
  Yineng Zhang authored May 06, 2025
```
Co-authored-by: yizhang2077 <1109276519@qq.com>
```
  6f566147
- [Fix] Fix and rename flashmla CI test (#6045) · bdd17998
  Baizhou Zhang authored May 06, 2025
  
  bdd17998
- fix: deepep dockerfile, use pip install deepep. (#5885) · c9abd7be
  Hank Han authored May 07, 2025
  
  c9abd7be
- Better PD initialization (#5751) · a3e4e9bf
  Liangsheng Yin authored May 07, 2025
  
  a3e4e9bf