Commits · 91e2f902db0e4c2d855e6c252de2ff38b92a1cc5 · change / sglang · GitLab

08 Aug, 2025 24 commits
- Fix kimi k2 function call format (#8968) · 91e2f902
  Lianmin Zheng authored Aug 08, 2025
  
  91e2f902
- [router] harden retries + metrics; fix streaming load; header filtering (#8972) · a59cbea9
  Simo Lin authored Aug 08, 2025
  
  a59cbea9
- refine aiter_backend for mtp (#7279) · 53f7874a
  valarLip authored Aug 09, 2025
```
Co-authored-by: HAI <hixiao@gmail.com>
```
  53f7874a
- [router] router circuit breaker core (#8941) · 61a46804
  Simo Lin authored Aug 08, 2025
  
  61a46804
- chore: bump v0.5.0rc0 (#8959) · 9020f7fc
  Yineng Zhang authored Aug 08, 2025
  
  9020f7fc
- [RL] fix skip_server_warmup and rl health_generate logic (#8757) · dd650e0e
  Zilin Zhu authored Aug 08, 2025
  
  dd650e0e
- Revert "Support Multi Process Tokenizer Manager" (#8960) · a9471542
  Lianmin Zheng authored Aug 08, 2025
  
  a9471542
- chore: update flashinfer (#8958) · 41357e51
  Yineng Zhang authored Aug 08, 2025
  
  41357e51
- Simple prefetch policy (#8692) · e2fd2b9c
  pansicheng authored Aug 08, 2025
  
  e2fd2b9c
- Support Multi Process Tokenizer Manager (#6555) · 7490e3f6
  ybyang authored Aug 08, 2025
```
Signed-off-by: ybyang <ybyang7@iflytek.com>
Signed-off-by: huanglong <huanglong@linux.alibaba.com>
Co-authored-by: lw9527 <952799980@qq.com>
Co-authored-by: huanglong <huanglong@linux.alibaba.com>
Co-authored-by: Huang Long <121648372+LLLL114@users.noreply.github.com>
```
  7490e3f6
- add zai-org/GLM-4.5-Air-FP8 model into nightly CI (#8894) · 6ee6619b
  Minglei Zhu authored Aug 08, 2025
  
  6ee6619b
- chore: bump sgl-kernel v0.3.3 (#8957) · 54ea57f2
  Yineng Zhang authored Aug 08, 2025
  
  54ea57f2
- [NVIDIA] Fix missing `get_col_major_tma_aligned_tensor` for Blackwell deepgemm in EpMoE (#8955) · b4c9f38a
  Kaixi Hou authored Aug 08, 2025
  
  b4c9f38a
- Add ernie4.py for ERNIE-4.5 (#7657) · 11325474
  Wenbo Yang authored Aug 08, 2025
  
  11325474
- Expert Parallelism for GPT-OSS (#8944) · 1d24db83
  Cheng Wan authored Aug 08, 2025
  
  1d24db83
- Fix typos and unify size(s)/stride(s) API calls (#8799) · 44401358
  triple-mu authored Aug 08, 2025
  
  44401358
- bench: add attention sink op benchmark, triton and trtllm-gen [B200] (#8932) · 9c7e3924
  eigen authored Aug 08, 2025
```
Co-authored-by: averyhuang <averyh@nvidia.com>
```
  9c7e3924
- minor: global workspace buffer for trtllm-gen mha from flashinfer (#8952) · 08fab2b0
  eigen authored Aug 08, 2025
  
  08fab2b0
- Better optimization log for gpt-oss model (#8953) · 0d1e27a0
  Xiaoyu Zhang authored Aug 08, 2025
  
  0d1e27a0
- Reduce scheduler recv requests overhead (#8947) · 774b47f3
  fzyzcjy authored Aug 08, 2025
  
  774b47f3
- Fix enable flashinfer mxfp4 moe bf16 check (#8950) · 76915d68
  Xiaoyu Zhang authored Aug 08, 2025
  
  76915d68
- refactor: Move scalar_types.py to sgl-kernel to avoid circular import (#8720) · 39fd1788
  Hongbo Xu authored Aug 08, 2025
  
  39fd1788
- Enhancements for bench_one_batch (#8703) · ed0a3dd5
  Zaili Wang authored Aug 08, 2025
```
Co-authored-by: root <root@gnr630186.jf.intel.com>
```
  ed0a3dd5
- [router] dedicated prefill HTTP client and request-path optimizations (#8923) · 2e901e89
  Simo Lin authored Aug 07, 2025
  
  2e901e89
07 Aug, 2025 16 commits
- correct the tp_plan logic (#8850) · d3be9710
  Stefan He authored Aug 07, 2025
  
  d3be9710
- fix: reasoning parser when request have enable_thinking flag (#8933) · 3e7ff1ab
  Xinyuan Tong authored Aug 07, 2025
```
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
```
  3e7ff1ab
- remove vllm fp8quant from fp8.py (#8937) · aaf0ad8c
  Stefan He authored Aug 07, 2025
  
  aaf0ad8c
- docs: update README (#8929) · 361379b5
  Yineng Zhang authored Aug 07, 2025
  
  361379b5
- chore: support blackwell cu129 image (#8928) · 1ac16add
  Yineng Zhang authored Aug 07, 2025
  
  1ac16add
- codeowner updates for modelopt related files (#8925) · c3a5fb3b
  Zhiyu authored Aug 07, 2025
  
  c3a5fb3b
- fix: use openai 1.99.1 (#8927) · 4bf6e5a6
  Yineng Zhang authored Aug 07, 2025
  
  4bf6e5a6
- Fix hopper launch gpt-oss model illegal memory (#8908) · 3ae33fcd
  Xiaoyu Zhang authored Aug 08, 2025
  
  3ae33fcd
- [router] upgrade router version to 0.1.9 (#8844) · 500b15c9
  Simo Lin authored Aug 07, 2025
  
  500b15c9
- [router] update pd router ci summary step with new threshold (#8916) · 16a4c66d
  Simo Lin authored Aug 07, 2025
  
  16a4c66d
- [router] re-enable pd router benchmark CI (#8912) · 89e6521c
  Simo Lin authored Aug 07, 2025
  
  89e6521c
- refactor(sgl-router): Replace `once_cell` with `LazyLock` in worker.rs and... · fd05b567
  Tien Nguyen authored Aug 07, 2025
```
refactor(sgl-router): Replace `once_cell` with `LazyLock` in worker.rs and remove once_cell dependency from Cargo.toml (#8698)
```
  fd05b567
- Fix sgl-kernel arch and missing package in CI (#8869) · 482c3db2
  fzyzcjy authored Aug 07, 2025
  
  482c3db2
- [Perf] Auto enable best flashinfer mxfp4 kernel in b200 (#8898) · 47824c14
  Xiaoyu Zhang authored Aug 07, 2025
  
  47824c14
- Disable gemma3 for SWA due to CUDA illegal memory access error (#8895) · c36a6693
  Xinyuan Tong authored Aug 07, 2025
```
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
```
  c36a6693
- [CPU] Fix fallback allgather issue (#8041) · 62f8eb48
  blzheng authored Aug 07, 2025
  
  62f8eb48