Commits · 2f20f43026ef85ccc81035731d64c201274a43be · change / sglang · GitLab

13 Aug, 2025 16 commits
- Swap xeon ci to gnr server (#9042) · 2f20f430
  DiweiSun authored Aug 14, 2025
  
  2f20f430
- [Model] Support Qwen3ForSequenceClassification for Qwen3-Embed Model (#7957) · 65736dc5
  Zhihao Liu authored Aug 14, 2025
  
  65736dc5
- chore: bump v0.5.0rc1 (#9069) · 7b56e494
  Yineng Zhang authored Aug 13, 2025
  
  7b56e494
- Support FA3 backend for gpt-oss (#9028) · 0ff6d1fc
  Ke Bao authored Aug 14, 2025
  
  0ff6d1fc
- [PD] feat: mooncake use batch reg/dereg (#8910) · 4a16a71c
  Teng Ma authored Aug 14, 2025
```
Co-authored-by: Shangming Cai <csmthu@gmail.com>
```
  4a16a71c
- [PD] optimize kv cache transfer directly using batch transfer (#9149) · a16923ef
  Francis authored Aug 14, 2025
```
Co-authored-by: Shangming Cai <csmthu@gmail.com>
```
  a16923ef
- [router] optimize Rust compilation and development workflow (#9133) · 6337d905
  Simo Lin authored Aug 13, 2025
  
  6337d905
- feat: update fa3 (#9126) · 71fb8c95
  Yineng Zhang authored Aug 13, 2025
  
  71fb8c95
- Update fa3 interface and add unit test (#9150) · 94f44b88
  Ke Bao authored Aug 13, 2025
  
  94f44b88
- Double vision prefill throughput by defaulting to optimal vision attention backend (#8484) · 3b3b3baf
  Kevin Xiang Li authored Aug 13, 2025
```
Co-authored-by: Xiang (Kevin) Li <lik@nvidia.com>
```
  3b3b3baf
- Update docker file for MI35x base image update to support gpt-oss mxfp4 model (#9111) · 35e6bc92
  kk authored Aug 13, 2025
```
Co-authored-by: wunhuang <wunhuang@amd.com>
```
  35e6bc92
- Fix gpt-oss ~2x memory consumption issue (#9146) · 9394ed63
  fzyzcjy authored Aug 13, 2025
  
  9394ed63
- Support Triton FP8 Gemm can handle hidden_dim not divisible by 16 (#9093) · 930fe467
  Stefan He authored Aug 12, 2025
```
Co-authored-by: Xiaoyu Zhang <35585791+BBuf@users.noreply.github.com>
```
  930fe467
- [1/2][resubmit again] sgl-kernel: Fuse routed scaling factor into moe_fused_gate (#9088) · 13c48dcf
  Trevor Morris authored Aug 12, 2025
  
  13c48dcf
- Use FlashInfer's TRTLLM FP8 Blockscale GEMM (#8588) · 8723b4f1
  Elfie Guo authored Aug 12, 2025
  
  8723b4f1
- fix: wrong docker hub org name (#9137) · 62f99e08
  li chaoran authored Aug 13, 2025
```
Signed-off-by: mywaaagh_admin <pkwarcraft@gmail.com>
```
  62f99e08
12 Aug, 2025 24 commits
- [Feature] Support custom set kv buffer kernel (#8884) · 86a0be65
  DarkSharpness authored Aug 12, 2025
  
  86a0be65
- Support page first layout zero copy for mooncake store (#8651) · 0edda320
  huangtingwei authored Aug 13, 2025
```
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
```
  0edda320
- chore: use cp310 (#9130) · 924827c3
  Yineng Zhang authored Aug 12, 2025
  
  924827c3
- fix: update Dockerfile (#9129) · c81daf83
  Yineng Zhang authored Aug 12, 2025
  
  c81daf83
- [AMD] Support Wave attention backend with AMD GPU optimizations (#8660) · 25caa7a8
  jacky.cheng authored Aug 13, 2025
```
Signed-off-by: Stanley Winata <stanley.winata@amd.com>
Signed-off-by: Harsh Menon <harsh@nod-labs.com>
Signed-off-by: nithinsubbiah <nithinsubbiah@gmail.com>
Signed-off-by: Ivan Butygin <ivan.butygin@gmail.com>
Signed-off-by: xintin <gaurav.verma@amd.com>
Co-authored-by: Harsh Menon <harsh@nod-labs.com>
Co-authored-by: Stanley Winata <stanley.winata@amd.com>
Co-authored-by: Stanley Winata <68087699+raikonenfnu@users.noreply.github.com>
Co-authored-by: Stanley Winata <stanley@nod-labs.com>
Co-authored-by: Ivan Butygin <ivan.butygin@gmail.com>
Co-authored-by: nithinsubbiah <nithinsubbiah@gmail.com>
Co-authored-by: Nithin Meganathan <18070964+nithinsubbiah@users.noreply.github.com>
Co-authored-by: Ivan Butygin <ibutygin@amd.com>
```
  25caa7a8
- Fix typos in supported models documentation (#9119) · 03d11449
  Hangzhi authored Aug 12, 2025
  
  03d11449
- [Quantization] Supported w8a8 int8 quantized Gemma3 and Qwen-VL models (#8619) · 83123f48
  ichernob authored Aug 12, 2025
```
Co-authored-by: ronnie_zheng <zl19940307@163.com>
```
  83123f48
- [feat] Enable Ascend profiling on SGLang (#8610) · 48afa8f1
  ronnie_zheng authored Aug 13, 2025
```
Co-authored-by: liyou_b <2953090824@qq.com>
```
  48afa8f1
- [feat] add ascend readme and docker release (#8700) · 2ecbd8b8
  li chaoran authored Aug 13, 2025
```
Signed-off-by: mywaaagh_admin <pkwarcraft@gmail.com>
Signed-off-by: lichaoran <pkwarcraft@gmail.com>
Co-authored-by: Even Zhou <even.y.zhou@outlook.com>
Co-authored-by: ronnie_zheng <zl19940307@163.com>
```
  2ecbd8b8
- fix: update Dockerfile (#9125) · 305b27c1
  Yineng Zhang authored Aug 12, 2025
  
  305b27c1
- [router] update router documentation (#9121) · 1ce30dd1
  Simo Lin authored Aug 12, 2025
  
  1ce30dd1
- Fuse writing KV buffer into rope kernel (part 2: srt) (#9014) · c9ee7385
  Jiaqi Gu authored Aug 12, 2025
```
Co-authored-by: fzyzcjy <5236035+fzyzcjy@users.noreply.github.com>
```
  c9ee7385
- fix(docker): update sgl_kernel version to 0.3.4 in Dockerfile.gb200 (#9118) · 1f9ec653
  ishandhanani authored Aug 12, 2025
  
  1f9ec653
- router: Fix user guide link README.md (#9122) · ad359d1c
  Chang Su authored Aug 12, 2025
  
  ad359d1c
- [5/n] DP Enhancement: Correct `num_token_non_padded` (#9107) · 5f5b3b24
  Cheng Wan authored Aug 12, 2025
  
  5f5b3b24
- Fix typo in REVIEWERS (#9113) · 4caca4f6
  Shangming Cai authored Aug 13, 2025
```
Signed-off-by: Shangming Cai <csmthu@gmail.com>
```
  4caca4f6
- [Bugfix] Fix accuracy-test-1-gpu failure caused by `builtin_tools` (#9114) · f2a5de28
  Chang Su authored Aug 12, 2025
  
  f2a5de28
- Runtime check CUDA driver version to avoid unresolved green context symbols (#9021) · 445f9dca
  Liangsheng Yin authored Aug 12, 2025
  
  445f9dca
- chore: bump sgl-kernel v0.3.4 (#9103) · 3a9afe2a
  Yineng Zhang authored Aug 12, 2025
  
  3a9afe2a
- Fuse writing KV buffer into rope kernel (part 1: sgl-kernel) (#9077) · 9aea2555
  fzyzcjy authored Aug 12, 2025
  
  9aea2555
- update support new models doc (#9096) · fcc11e5e
  Yichao Cheng authored Aug 12, 2025
```
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
```
  fcc11e5e
- Fuse two kernels of hidden states padding into quantization kernel (#9005) · 5190ba7f
  fzyzcjy authored Aug 12, 2025
```
Co-authored-by: Qiaolin-Yu <liin1211@outlook.com>
```
  5190ba7f
- docs: fix broken links in README.md (#9075) · 5438886c
  Hsiang-Yu Tsou authored Aug 12, 2025
  
  5438886c
- bugfix: Fix the commentary msg extraction in GptOssDetector (#9097) · 9c83d74d
  Chang Su authored Aug 11, 2025
  
  9c83d74d