Commits · 708f4ff490d3e80d75299cfc3aa4719dd7efaec8 · change / sglang

"vscode:/vscode.git/clone" did not exist on "8bdbff8d3fea4314691035ac624d0573f1bfd9ef"

06 Oct, 2025 29 commits
- Rename max_micro_batch_size -> pp_max_micro_batch_size (#11279) · 708f4ff4
  Lianmin Zheng authored Oct 06, 2025
  
  708f4ff4
- [Auto Sync] Update test_utils.py (20251006) (#11280) · e2daeb35
  Lianmin Zheng authored Oct 06, 2025
```
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Sehoon Kim <sehoon@x.ai>
```
  e2daeb35
- Fix code sync scripts (#11276) · 0e7b3530
  Lianmin Zheng authored Oct 06, 2025
  
  0e7b3530
- [router][grpc] Refine streaming processes (#11277) · b07c9c76
  Chang Su authored Oct 06, 2025
  
  b07c9c76
- [Bug] Fix incorrect assertion in FA4 and add UT. (#11182) · 748f86f3
  Lifu Huang authored Oct 06, 2025
  
  748f86f3
- docker: add manifest to versioned docker releases (#11268) · 73ea484a
  ishandhanani authored Oct 06, 2025
  
  73ea484a
- disable sm100 for FlashMLA and fast-hadamard-transform in cuda12.6.1 (#11274) · 4aeb193f
  gongwei-130 authored Oct 06, 2025
  
  4aeb193f
- [router][tool call] Clean up redundant `detect_format` and `has_tool_markers` (#11270) · 466992b2
  Chang Su authored Oct 06, 2025
  
  466992b2
- Enable native ModelOpt quantization support (1/3) (#7149) · 155cbb51
  Zhiyu authored Oct 06, 2025
```
Signed-off-by: Zhiyu Cheng <zhiyuc@nvidia.com>
```
  155cbb51
- Remove env var warnings for release (#11262) · eb30b888
  Lianmin Zheng authored Oct 06, 2025
  
  eb30b888
- [router] add ipv6 support across all components (#11219) · 5ee777c9
  Simo Lin authored Oct 06, 2025
  
  5ee777c9
- chore: bump SGLang version to 0.5.3 (#11263) · a4a3d823
  sglang-bot authored Oct 06, 2025
  
  a4a3d823
- chore: bump SGLang version to 0.5.3rc2 (#11259) · 0b13cbb7
  sglang-bot authored Oct 06, 2025
```
Co-authored-by: sglang-bot <sglang-bot@users.noreply.github.com>
```
  0b13cbb7
- Support DeepSeek V3.2 Exp (#11061) · efbc687c
  fzyzcjy authored Oct 06, 2025
```
Co-authored-by: Stefan He <11166516+hebiao064@users.noreply.github.com>
Co-authored-by: Liangsheng Yin <95566987+hnyls2002@users.noreply.github.com>
Co-authored-by: Baizhou Zhang <56809903+fridge003@users.noreply.github.com>
Co-authored-by: DarkSharpness <76582120+darksharpness@users.noreply.github.com>
Co-authored-by: ZhengdQin <46387172+zhengdqin@users.noreply.github.com>
Co-authored-by: DarkSharpness <2040703891@qq.com>
Co-authored-by: hnyls2002 <lsyincs@gmail.com>
Co-authored-by: Zhengda Qin <zhengdqin@gmail.com>
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
Co-authored-by: HAI <hixiao@gmail.com>
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
```
  efbc687c
- Add flashmla and fast hadamard transform to Dockerfile (#11235) · 292a867a
  Baizhou Zhang authored Oct 05, 2025
  
  292a867a
- Improve bot release workflow (#11240) · 8fd41eae
  Kangyan-Zhou authored Oct 05, 2025
  
  8fd41eae
- feat: add shortcut detection for multimodal templates in Jinja format (#11209) · 0cd1996e
  Xinyuan Tong authored Oct 05, 2025
  
  0cd1996e
- Update condition for sgl-kernel-benchmark-test (#11254) · b6b4b563
  Lianmin Zheng authored Oct 05, 2025
  
  b6b4b563
- update sgl kernel version to 0.3.14.post1 (#11242) · f8924ad7
  Lianmin Zheng authored Oct 05, 2025
  
  f8924ad7
- Bump torch_memory_saver 0.0.9rc2 (#11252) · 2f80bd9f
  fzyzcjy authored Oct 06, 2025
  
  2f80bd9f
- Use cu128 for torch audio to fix some CI tests (#11251) · 366a603e
  Lianmin Zheng authored Oct 05, 2025
  
  366a603e
- [quantization] Enable aiter mxfp4 fused_moe for Quark (#10048) · baee0860
  Bowen Bao authored Oct 05, 2025
```
Co-authored-by: HaiShaw <hixiao@gmail.com>
```
  baee0860
- [quantization] Fix scale remapping for mllama4 (#10042) · c7a104c1
  Bowen Bao authored Oct 05, 2025
```
Co-authored-by: HAI <hixiao@gmail.com>
```
  c7a104c1
- ci: make find_local_hf_snapshot_dir more robust (#11248) · 97d966a7
  Mick authored Oct 06, 2025
  
  97d966a7
- Fix spec_utils.py (#11247) · 8e66d87f
  sglang-bot authored Oct 05, 2025
  
  8e66d87f
- Create two new GH workflows to automatically bump SGLang and Kernel version (#10996) · a20fc7b7
  Kangyan-Zhou authored Oct 05, 2025
  
  a20fc7b7
- [Auto Sync] Update io_struct.py (20251004) (#11206) · 6b30e097
  Lianmin Zheng authored Oct 05, 2025
```
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: jzhou-xai <jzhou@x.ai>
```
  6b30e097
- Rename runner labels (#11228) · d645ae90
  Lianmin Zheng authored Oct 05, 2025
  
  d645ae90
- Remove gdrcopy check in ci_install_deepep.sh (#11237) · 41763ba0
  Cheng Wan authored Oct 05, 2025
  
  41763ba0
05 Oct, 2025 11 commits
- Update transformers package version to 4.57.0 (#11222) · 652c24a6
  Xinyuan Tong authored Oct 05, 2025
```
Co-authored-by: yhyang201 <yhyang201@gmail.com>
```
  652c24a6
- [Fix AMD CI] VRAM cleanup (#11174) · 5e142484
  sunxxuns authored Oct 05, 2025
```
Co-authored-by: root <root@smci350-zts-gtu-e17-15.zts-gtu.dcgpu>
```
  5e142484
- Refactor and optimize mooncake CI (#11162) · c560410d
  Shangming Cai authored Oct 06, 2025
```
Signed-off-by: Shangming Cai <csmthu@gmail.com>
```
  c560410d
- [Feat] Support Torch Symm Mem AllReduce (#10571) · 590f2da0
  Yuan Luo authored Oct 06, 2025
```
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
```
  590f2da0
- Update DeepGEMM repository tag to specific commit (#11229) · 148d8d48
  Lianmin Zheng authored Oct 05, 2025
  
  148d8d48
- chore: bump sgl-kernel v0.3.14.post1 (#11137) · 1a599509
  PGFLMG authored Oct 06, 2025
  
  1a599509
- Update `v1/responses` to be more OpenAI-compatible. (#9624) · 36a6b8db
  Vincent Zhong authored Oct 05, 2025
  
  36a6b8db
- [Feature] Add a fast-topk to sgl-kernel for DeepSeek v3.2 (#11194) · e0b2d3ee
  DarkSharpness authored Oct 06, 2025
```
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
```
  e0b2d3ee
- Tiny `skip_sample` adjust (#11225) · 4cb5a523
  Liangsheng Yin authored Oct 05, 2025
  
  4cb5a523
- Add DeepSeek-V3.2 Tool Call Template (#11063) · 85c1f793
  Xu Wenqing authored Oct 05, 2025
```
Signed-off-by: 许文卿 <xwq391974@alibaba-inc.com>
```
  85c1f793
- Add --max-new-tokens CLI flag for MMMU evaluation (#11217) · 48e9e719
  yhyang201 authored Oct 05, 2025
  
  48e9e719