Commits · 9eefe2c0b71c995383cd94ddc81f2016a4e93ace · change / sglang · GitLab

18 Oct, 2025 3 commits
- Set CUDA_VISIBLE_DEVICES to achieve one GPU per process (#9170) · 9eefe2c0
  Lianmin Zheng authored Oct 17, 2025
```
Co-authored-by: SangBin Cho <rkooo567@gmail.com>
Co-authored-by: Cheng Wan <cwan@x.ai>
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
```
  9eefe2c0
- Manually flip deepep_mode for cuda_graph (#11666) · 69fe3c97
  Zilin Zhu authored Oct 18, 2025
  
  69fe3c97
- Support casting bf16 NextN moe to fp8 (#11613) · 8af84912
  fzyzcjy authored Oct 18, 2025
  
  8af84912
17 Oct, 2025 23 commits
- Support shared experts overlap in cutlass moe (#11611) · 505329ca
  fzyzcjy authored Oct 18, 2025
  
  505329ca
- Super tiny fix missing input throughput (#11607) · 8a382fd3
  fzyzcjy authored Oct 18, 2025
  
  8a382fd3
- [Lint] Add `python/sglang` to ruff F401 checks and remove unused imports in files (#11685) · 62797440
  Chang Su authored Oct 17, 2025
  
  62797440
- [Fix] Skip visual layers when applying LoRA to Qwen2VL modules (#11519) · 2614adf9
  Antonin Vidon authored Oct 17, 2025
  
  2614adf9
- [Auto Sync] Update common.py (20251017) (#11782) · fdd7c69d
  Lianmin Zheng authored Oct 17, 2025
```
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
```
  fdd7c69d
- [minor] sync code on python/sglang/test/test_deterministic.py and improve ci tests (#11777) · b9a54e09
  Lianmin Zheng authored Oct 17, 2025
```
Co-authored-by: Stefan He <hebiaobuaa@gmail.com>
Co-authored-by: Byron Hsu <byronhsu1230@gmail.com>
```
  b9a54e09
- Cleaning indexer for DeepSeek V3.2 (#11682) · 20b8d230
  Baizhou Zhang authored Oct 17, 2025
  
  20b8d230
- [router][grpc] Remove timeout for connections and remove `max_tokens`... · d1984e21
  Chang Su authored Oct 17, 2025
```
[router][grpc] Remove timeout for connections and remove `max_tokens` deprecation warning log (#11775)
```
  d1984e21
- [Auto Sync] Update scheduler.py (20251017) (#11738) · b79f75fd
  Yineng Zhang authored Oct 17, 2025
  
  b79f75fd
- Turn on shm_allreduce and shm_allgather for fp16 (#10725) · 8fcc69e7
  Chunyuan WU authored Oct 18, 2025
  
  8fcc69e7
- [Feature] Reuse flashinfer workspace for PD-Multiplexing. (#11540) · f440baa1
  ykcombat authored Oct 18, 2025
  
  f440baa1
- [doc] update router document (#11767) · 2bc3fcd4
  Keyang Ru authored Oct 17, 2025
  
  2bc3fcd4
- [router] fix grpc client time out to 1h (#11768) · a5978a20
  Simo Lin authored Oct 17, 2025
  
  a5978a20
- [router] Fix UTF-8 Boundary Panic in Stop Sequence Decoder (#11766) · e483c1ea
  Simo Lin authored Oct 17, 2025
  
  e483c1ea
- Revert "Set csgmv as default lora backend. (#11488)" (#11735) · da681f35
  Yineng Zhang authored Oct 17, 2025
  
  da681f35
- add tuned fuse moe kernel for qwen3 235b fp8 on h200 (#11730) · 9b0f725b
  pdasgup authored Oct 17, 2025
```
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
```
  9b0f725b
- Abstraction for spec worker and code cleanup (#11643) · cde5a6e3
  Liangsheng Yin authored Oct 17, 2025
  
  cde5a6e3
- ci: reduce and refactor vlm ut and combine test files (#11062) · 3e4c7da2
  Mick authored Oct 17, 2025
  
  3e4c7da2
- [overlap-spec] Make plan stream an option (#11724) · d88ac9bc
  Liangsheng Yin authored Oct 17, 2025
  
  d88ac9bc
- [CI] Try fix broken event loop init (#11746) · ce11dd82
  Liangsheng Yin authored Oct 17, 2025
  
  ce11dd82
- [router][CI] Clean up deprecated fields in `pr-test-pd-router.yml` (#11739) · 9e87b60f
  Chang Su authored Oct 16, 2025
  
  9e87b60f
- Revert "[router] fix get_models endpoint for openai router (#11687)" (#11740) · 7780230a
  Keyang Ru authored Oct 16, 2025
  
  7780230a
- [router] Add rustfmt and set group imports by default (#11732) · dc01313d
  Chang Su authored Oct 16, 2025
  
  dc01313d
16 Oct, 2025 14 commits
- [router] add spec.rs to enables tests under spec folder (#11734) · 7a7f99be
  Keyang Ru authored Oct 16, 2025
  
  7a7f99be
- Reduce the image processing latency in VLM (#11541) · fd389df9
  StonyPort authored Oct 17, 2025
```
Co-authored-by: qiuxuan.lzw <qiuxuan.lzw@alibaba-inc.com>
```
  fd389df9
- Revert "make radix cache deterministic" (#11728) · b0d1d717
  Baizhou Zhang authored Oct 16, 2025
  
  b0d1d717
- [router] Fix tool_choice normalization in ChatCompletionRequest and fix ut (#11731) · c7962868
  Chang Su authored Oct 16, 2025
  
  c7962868
- [router][grpc] add dissag info to warm up in grpc server (#11727) · 4f24ab17
  Simo Lin authored Oct 16, 2025
  
  4f24ab17
- [router] fix p and d worker filtering and bootstrap port handling (#11729) · 64affab4
  Simo Lin authored Oct 16, 2025
  
  64affab4
- [Router] Refactor protocol definitions: split spec.rs into modular files (#11677) · 4c9bcb9d
  Keyang Ru authored Oct 16, 2025
```
Co-authored-by: Chang Su <chang.s.su@oracle.com>
```
  4c9bcb9d
- model: qwen3-omni (thinker-only) (#10911) · 86b04d25
  Mick authored Oct 17, 2025
```
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
```
  86b04d25
- chore: bump SGLang version to 0.5.3.post3 (#11693) · 85ebeecf
  sglang-bot authored Oct 16, 2025
```
Co-authored-by: sglang-bot <sglang-bot@users.noreply.github.com>
```
  85ebeecf
- [ci]use H20 to run disaggregation test (#11543) · 0dd6cf16
  Hank Han authored Oct 17, 2025
  
  0dd6cf16
- [router] fix get_models endpoint for openai router (#11687) · 0975ba99
  Keyang Ru authored Oct 16, 2025
  
  0975ba99
- [CI] Add GLM4MoE model test (#11706) · 1de3924b
  Shangming Cai authored Oct 16, 2025
```
Signed-off-by: Shangming Cai <csmthu@gmail.com>
```
  1de3924b
- [Bugfix] Fix Qwen3/DSV3/DSV3.2 model support (#11510) · 3cceaa38
  Even Zhou authored Oct 16, 2025
  
  3cceaa38
- Set csgmv as default lora backend. (#11488) · b0d20cde
  Lifu Huang authored Oct 15, 2025
  
  b0d20cde