Commits · 959d1ab84b9a4ee4c38409e005bc6557640569c8 · change / sglang · GitLab

27 Oct, 2025 13 commits
- fix(metrics): double times add_latency for DECODE_BOOTSTRAP (#12209) · 959d1ab8
  Jimmy authored Oct 27, 2025
  
  959d1ab8
- [Detokenizer Manager] Cleanup state when reqs are finished (#12205) · 6c1c1933
  Muqi Li authored Oct 27, 2025
  
  6c1c1933
- Fix crash after flush cache (#12107) · 3029d301
  cctry authored Oct 27, 2025
```
Co-authored-by: fzyzcjy <5236035+fzyzcjy@users.noreply.github.com>
```
  3029d301
- Optimize triton_mrope with torch compile (#12112) · f389f017
  Yuan Luo authored Oct 27, 2025
```
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
```
  f389f017
- Add support for AutoRound quantized models (#10153) · caa4819b
  Weiwei authored Oct 27, 2025
  
  caa4819b
- GLM-4-0414 and GLM-4.1V Code Refactor (#12117) · a88b006e
  Yuxuan Zhang authored Oct 27, 2025
  
  a88b006e
- [sgl-kernel][4/N]Support Expert Specialization Grouped GEMM (#12080) · ce112c07
  Qi Yuhang authored Oct 27, 2025
  
  ce112c07
- [sgl-kernel] feat: Support sm120 cutlass fp8 gemm kernel (#9403) · f7dc2f33
  Joonchen Liau authored Oct 27, 2025
  
  f7dc2f33
- docs: update contact (#12192) · cd784faf
  Yineng Zhang authored Oct 26, 2025
  
  cd784faf
- [Fix] Fix cu130 sgl-kernel wheel renaming (#12173) · 75c09e1f
  Baizhou Zhang authored Oct 26, 2025
  
  75c09e1f
- [sgl-route] Optimize the use of constant slices and retain to simplif… (#12159) · 09af0a7b
  rongfu.leng authored Oct 27, 2025
```
Signed-off-by: rongfu.leng <lenronfu@gmail.com>
```
  09af0a7b
- [doc] add example of using w4fp8 for Deepseek (#12057) · c8d385ce
  Kevin_Xiong authored Oct 27, 2025
```
Co-authored-by: Chao Xiong <chaoxiong@Chaos-MacBook-Air.local>
```
  c8d385ce
- chore: bump SGLang version to 0.5.4.post1 (#12169) · 55d75e11
  sglang-bot authored Oct 27, 2025
  
  55d75e11
26 Oct, 2025 27 commits
- Remove description for `--enable-beta-spec` argument (#12177) · 3f4cc0af
  Xinyuan Tong authored Oct 26, 2025
  
  3f4cc0af
- fix broken deepep/flashmla install in container by adding `--no-build-isolation` (#12170) · cadfae66
  ishandhanani authored Oct 26, 2025
  
  cadfae66
- Remove deprecated --enable-beta-spec argument and fix b200 test (#12167) · da1766e4
  Kangyan-Zhou authored Oct 26, 2025
```
Co-authored-by: Claude <noreply@anthropic.com>
```
  da1766e4
- [router] Remove SharedXxxStorage type aliases to make Arc explicit (#12171) · a124b517
  Chang Su authored Oct 26, 2025
  
  a124b517
- [router][grpc] Add `ResponsesContext` and fix error propagation in responses api (#12164) · d05a968b
  Chang Su authored Oct 26, 2025
  
  d05a968b
- [misc][grpc] Remove duplicate log (#12168) · 94aad0de
  Chang Su authored Oct 26, 2025
  
  94aad0de
- [WIP] support MiniMax M2 model (#12129) · 7ebc28f5
  赵晨阳 authored Oct 26, 2025
```
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Signed-off-by: xuebi <xuebi@minimaxi.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
Co-authored-by: Roger Young <42564206+rogeryoungh@users.noreply.github.com>
Co-authored-by: xuebi <xuebi@minimaxi.com>
```
  7ebc28f5
- add gitignore for claude code and serena mcp (#12166) · b89111d6
  Simo Lin authored Oct 26, 2025
  
  b89111d6
- transfer mrope_position_delta to device when first running (#11047) · 0b3b3e9a
  ash-sigh authored Oct 27, 2025
  
  0b3b3e9a
- Avoid using flashinfer_allreduce_fusion when dp attention is enabled. (#11632) · a1d5bc4c
  Elfie Guo authored Oct 26, 2025
  
  a1d5bc4c
- model: support NVILA and NVILA Lite (#10399) · a8023891
  Zijian Zhang authored Oct 27, 2025
  
  a8023891
- Support DeepGEMM for deterministic inference (#12142) · 0103f374
  fzyzcjy authored Oct 26, 2025
  
  0103f374
- [Fix] fix allreduce bug in Piecewise Graph (#12106) · 96a5a949
  zyksir authored Oct 26, 2025
  
  96a5a949
- Fix ITL metrics when using openai endpoint with spec (#12156) · ea385ae8
  Liangsheng Yin authored Oct 26, 2025
  
  ea385ae8
- [router] centralize mcp tool args handling (#12155) · 9e949e58
  Simo Lin authored Oct 26, 2025
  
  9e949e58
- [router][grpc] Fix tool call id in `parse_json_schema_response` (#12152) · 6dbb569b
  Chang Su authored Oct 26, 2025
  
  6dbb569b
- Do not use `MagicMock` to mock `server_args` in tests (#12154) · 5994e6c3
  Liangsheng Yin authored Oct 26, 2025
  
  5994e6c3
- [HiCache]Page head layout IO kernel (#11615) · 3e6281d0
  huangtingwei authored Oct 26, 2025
  
  3e6281d0
- [quantization] AWQ Marlin doesn't work when dtype is bfloat16 (#11494) · 6371f7af
  Kai-Hsun Chen authored Oct 26, 2025
```
Signed-off-by: Kai-Hsun Chen <khchen@x.ai>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
```
  6371f7af
- [misc] depdencies & enviroment flag (#12113) · 8491c794
  Liangsheng Yin authored Oct 26, 2025
  
  8491c794
- [log] Make forward iter count optional (#12116) · bda3758f
  Liangsheng Yin authored Oct 26, 2025
  
  bda3758f
- Clean up attention backend selection code & Other minor rename (#12136) · 7b36c47b
  Lianmin Zheng authored Oct 25, 2025
  
  7b36c47b
- [router] cleaned up all the redundant comments in the config module (#12147) · 773d89da
  Chang Su authored Oct 25, 2025
  
  773d89da
- [router] update smg code owners for each component (#12141) · 03e7d949
  Simo Lin authored Oct 25, 2025
  
  03e7d949
- [NVIDIA] Change default quant method for model_opt (#11991) · ff604064
  Kaixi Hou authored Oct 25, 2025
  
  ff604064
- [router] MCP Manager Refactoring - Flat Architecture with Connection Pooling (#12097) · 212f5e48
  Simo Lin authored Oct 25, 2025
  
  212f5e48
- docs: update README (#12139) · fe527812
  Yineng Zhang authored Oct 25, 2025
  
  fe527812