Commits · 9dcdf5da0333b3592cccf0285ad092f9eaf5abfe · change / sglang

"vscode:/vscode.git/clone" did not exist on "83f2d9d4ed9d5a4e966a73225375ac0063a46acf"

25 Aug, 2025 12 commits
- Tiny fix wrong comments (#9589) · 9dcdf5da
  fzyzcjy authored Aug 25, 2025
  
  9dcdf5da
- fix: resolve tuning fused moe issue (#9587) · f8b757bc
  Yineng Zhang authored Aug 25, 2025
  
  f8b757bc
- fix: revert #8593 (#9581) · ebd9dbe7
  Yineng Zhang authored Aug 25, 2025
  
  ebd9dbe7
- chore: upgrade flashinfer 0.2.14.post1 (#9578) · 938e986e
  Yineng Zhang authored Aug 25, 2025
  
  938e986e
- bugfix for undefined logging functions in HarmonyBrowserTool & HarmonyPythonTool (#9229) · 17d5eda8
  Yuhao Zhou authored Aug 25, 2025
  
  17d5eda8
- Offload tensors by sharding on GPU (#9536) · 71a7f1d8
  fzyzcjy authored Aug 25, 2025
  
  71a7f1d8
- Reintroduce memory usage fix (#9535) · 433266c1
  fzyzcjy authored Aug 25, 2025
  
  433266c1
- Update CUTLASS 4.2 & Enable K-Major Scale Factor for SM90 FP8 Blockwise Group GEMM (#9559) · fda47926
  Qi Yuhang authored Aug 25, 2025
  
  fda47926
- remove redundant rank0_log function. (#9560) · a0b22f2f
  miter authored Aug 25, 2025
```
Co-authored-by: linhuang <linhuang@ruijie.com.cn>
```
  a0b22f2f
- [PD] Improve disaggregation metrics output: update the metrics to keep... · b5c6529e
  SCDESPERTATE authored Aug 25, 2025
```
[PD] Improve disaggregation metrics output: update the metrics to keep reflecting real stats (#7317)
```
  b5c6529e
- fix: Update OpenAI client base URL in documentation (#9576) · ca4b86c5
  Xinyuan Tong authored Aug 25, 2025
  
  ca4b86c5
- Add target module validation for init adapters (#9429) · dd6ec029
  Beichen Ma authored Aug 24, 2025
  
  dd6ec029
24 Aug, 2025 5 commits
- fix: use sgl-kernel 0.3.5 (#9565) · bf863e3b
  Yineng Zhang authored Aug 24, 2025
  
  bf863e3b
- [router] add right rustls dependency in sgl-router cargo.toml (#9498) · 9e169ea8
  Bruce-x-1997 authored Aug 25, 2025
```
Co-authored-by: bruce.xu <bruce.xu@gmicloud.ai>
```
  9e169ea8
- chore: bump v0.5.1.post1 (#9558) · e0ab167d
  Yineng Zhang authored Aug 24, 2025
  
  e0ab167d
- chore: update configurer (#9557) · c807cd7c
  Yineng Zhang authored Aug 24, 2025
  
  c807cd7c
- fix(grok): remove duplicate replicate_lm_head configuration (#9549) · 327f7b7c
  Vincent Zhong authored Aug 23, 2025
  
  327f7b7c
23 Aug, 2025 16 commits
- [doc] deepseekv31 support (#9544) · 80425e59
  Xiaotong Jiang authored Aug 23, 2025
  
  80425e59
- [readme] Include additional resources for the SGLang x AMD SF Meetup event (#9547) · af9d4eb0
  Mingyi authored Aug 23, 2025
  
  af9d4eb0
- feat: allow use local branch to build image (#9546) · fb107cfd
  gongwei-130 authored Aug 23, 2025
  
  fb107cfd
- Release 0.5.1 (#9533) · 97a38ee8
  Lianmin Zheng authored Aug 23, 2025
  
  97a38ee8
- Update grok.py and tiktoken tokenizer (#9532) · 86d10d22
  Lianmin Zheng authored Aug 23, 2025
  
  86d10d22
- feat(hicache): Supports 3fs-hicache compatibility with dp-attention (#9372) · 83871aa1
  hzh0425 authored Aug 23, 2025
  
  83871aa1
- Partially unify triton per token group quant kernels (#9485) · b1b3f0b3
  fzyzcjy authored Aug 23, 2025
  
  b1b3f0b3
- Tiny make device_loading_context more static (#9478) · 34e5e11f
  fzyzcjy authored Aug 23, 2025
  
  34e5e11f
- Overlapped weight offload (#8034) · 2600fc0d
  fzyzcjy authored Aug 23, 2025
  
  2600fc0d
- [fix] Fix mxfp4 triton MoE tp bug (#9473) · ccd3fb94
  hlu1 authored Aug 23, 2025
```
Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com>
```
  ccd3fb94
- tool-call(dsv3): Improve deepseek-v3 chat template and tool_choice = `required` (#9525) · c9dd70fb
  Chang Su authored Aug 23, 2025
  
  c9dd70fb
- fix: blackwell dsv3 fp8 issue temporary solution (#9530) · 6b2b8bf0
  Yineng Zhang authored Aug 23, 2025
  
  6b2b8bf0
- [benchmark] Add benchmark scripts for ceval and boolq (#8946) · 4edbe0d5
  yuxingcyx authored Aug 23, 2025
```
Co-authored-by: chenyuxing <2818499974@qq.com>
Co-authored-by: hanqing <huang010706@126.com>
Co-authored-by: Muggle <62579327+trawolf@users.noreply.github.com>
Co-authored-by: ronnie_zheng <zl19940307@163.com>
```
  4edbe0d5
- Add enable_flashinfer_mxfp4_bf16_moe for higher precision and slower moe backend (#9004) · 0374304a
  fzyzcjy authored Aug 23, 2025
  
  0374304a
- Support GC Freezing to improve latency & throughput (#9241) · 127d4b0d
  Chanh Nguyen authored Aug 22, 2025
```
Co-authored-by: Chanh Nguyen <cnguyen@linkedin.com>
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
```
  127d4b0d
- Add support for extensions of interface and pre-registrations to NIXL HiCache (#9211) · 7e880286
  Moein Khazraee authored Aug 22, 2025
```
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
```
  7e880286
22 Aug, 2025 7 commits
- [router] ignore client error when record failure in pd_router (#9503) · 446c8e4c
  Bruce-x-1997 authored Aug 23, 2025
```
Co-authored-by: bruce.xu <bruce.xu@gmicloud.ai>
```
  446c8e4c
- [router] Move all protocols to spec.rs file (#9519) · 5ef545e6
  Keyang Ru authored Aug 22, 2025
  
  5ef545e6
- Add Qwen3-30B-A3B-Thinking-2507 support on AMD GPUs. (#9456) · c4500233
  sogalin authored Aug 22, 2025
  
  c4500233
- [AMD] Fix Llama 4 FP8 accuracy issues on MI300X (#7699) · f445a1d9
  Hubert Lu authored Aug 22, 2025
  
  f445a1d9
- [NVIDA] [1/N] Nvfp4 Masked Gemm: Add quant op for the flashinfer grouped gemm (#9200) · e5638573
  Kaixi Hou authored Aug 22, 2025
  
  e5638573
- [router] add json tool parser (#9516) · f556ac8b
  Simo Lin authored Aug 22, 2025
  
  f556ac8b
- [MTP] Force greedy sampling on AMD (#9127) · 110a6598
  datdo-msft authored Aug 22, 2025
  
  110a6598