Commits · ebda73dc723ce822ede7b3e04dcb2f9f84216cc3 · change / sglang

"vscode:/vscode.git/clone" did not exist on "1f0cb544cab8eeeef9eaa2d53300c18c03f3a3ed"

18 Oct, 2025 19 commits
- Use cutlass fp4 gemm by default (#11813) · ebda73dc
  Qiaolin Yu authored Oct 18, 2025
  
  ebda73dc
- support server arg override KV cache to bf16 to avoid slow cases (#11749) · f9a7d9b3
  b8zhong authored Oct 18, 2025
  
  f9a7d9b3
- [overlap-spec] support page size > 1 (#11772) · a93f10a7
  Liangsheng Yin authored Oct 19, 2025
  
  a93f10a7
- [HiCache] feat: add more eviction policy (#11506) · 585e1223
  Teng Ma authored Oct 18, 2025
  
  585e1223
- Bump torch_memory_saver to avoid installing pre-release versions (#11797) · a7043c6f
  fzyzcjy authored Oct 18, 2025
  
  a7043c6f
- Fix install instructions and pyproject.tomls (#11781) · 67e34c56
  Lianmin Zheng authored Oct 18, 2025
  
  67e34c56
- Eager Compiler for Torch Compile (#11803) · 1d726528
  Yuwei An authored Oct 18, 2025
```
Signed-off-by: Oasis-Git <ayw.sirius19@gmail.com>
```
  1d726528
- set default attention backend for deterministic inference (#11801) · f4488e9d
  Minglei Zhu authored Oct 18, 2025
  
  f4488e9d
- [RL] use cpu group to prepare_mlp_sync_batch_raw when the server is offloaded (#10152) · e68a2b5b
  Zilin Zhu authored Oct 18, 2025
  
  e68a2b5b
- [RL] support weight update with DP attention (#11669) · 31b9f19e
  Zilin Zhu authored Oct 18, 2025
  
  31b9f19e
- fix(glm45): disable reduce scatter (#11665) · f7ab9554
  Jimmy authored Oct 18, 2025
```
Co-authored-by: Shangming Cai <csmthu@gmail.com>
```
  f7ab9554
- [router][grpc] Support parallel queue puts in grpc_request_manager and remove... · ca240eef
  Chang Su authored Oct 17, 2025
```
[router][grpc] Support parallel queue puts in grpc_request_manager and remove mutex for grpc_client (#11798)
```
  ca240eef
- [Refactor] move `deep_gemm_wrapper` out of `quantization` (#11784) · 5b214b50
  Cheng Wan authored Oct 17, 2025
  
  5b214b50
- completely remove mixed mode deterministic test as prefix mode could cover it (#11783) · 13219e1e
  Minglei Zhu authored Oct 17, 2025
```
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
```
  13219e1e
- Make single-batch overlap compatible with offloading (#11614) · 33e9bbec
  fzyzcjy authored Oct 18, 2025
  
  33e9bbec
- Super tiny fix CI (#11788) · dcb8f090
  fzyzcjy authored Oct 18, 2025
  
  dcb8f090
- 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 16 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
- [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
- 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
16 Oct, 2025 5 commits
- 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][grpc] add dissag info to warm up in grpc server (#11727) · 4f24ab17
  Simo Lin authored Oct 16, 2025
  
  4f24ab17
- 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