Commits · 5fd311d33e625edf2c9b53b1681cf27c55a84013 · change / sglang

"vscode:/vscode.git/clone" did not exist on "62789aa45b2a98db9c93ef072763d470910668b1"

22 Aug, 2025 9 commits
- [code clean] add H20 cutlass groupGemm default config (#9333) · 5fd311d3
  kousakawang authored Aug 22, 2025
```
Co-authored-by: wanghanpei <wanghanpei@bytedance.com>
```
  5fd311d3
- [router] remove all tokenizer metrics for performance (#9474) · 53e2cd46
  Chang Su authored Aug 21, 2025
  
  53e2cd46
- Support MHA with chunked prefix cache for flashinfer/flashmla backend, support... · 9708d353
  Yongfei Xu authored Aug 22, 2025
```
Support MHA with chunked prefix cache for flashinfer/flashmla backend, support page size > 1 for MHA chunked prefix (#8616)
Co-authored-by: xuyongfei.xyf <xuyongfei.xyf@antgroup.com>
```
  9708d353
- [AMD] Remove the deprecated C10_WARP_SIZE (#9356) · 704ced1b
  Hubert Lu authored Aug 21, 2025
  
  704ced1b
- Add Support for Page Size greater than 1 for Flashinfer MLA Backend (#8593) · 3cc3d9b9
  Pavani Majety authored Aug 21, 2025
```
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
```
  3cc3d9b9
- Update reasoning parser doc (#9468) · 0b3a5b11
  Xinyuan Tong authored Aug 22, 2025
```
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
```
  0b3a5b11
- Revert "bugfix: Fix output_ids extraction in detokenizer_manager" (#9467) · 6c855db8
  Xinyuan Tong authored Aug 22, 2025
  
  6c855db8
- feat: update auto_choose_speculative_params (#9470) · 0f9318f7
  Yineng Zhang authored Aug 21, 2025
  
  0f9318f7
- fix: tmp revert gpt oss tp sharding on hopper (#9469) · 849957bc
  Yineng Zhang authored Aug 21, 2025
  
  849957bc
21 Aug, 2025 26 commits
- [FA3] Init Spec Page Table only when Spec is enabled to save ~40MB (#9455) · cded039b
  Stefan He authored Aug 21, 2025
  
  cded039b
- feat: add fused moe config for GLM-4.5-Air-FP8 on B200 (#9463) · 275f9df3
  zixuanzhang226 authored Aug 21, 2025
  
  275f9df3
- Add deepseek v3.1 thinking parser support and update docs (#9464) · e8449ab5
  Xinyuan Tong authored Aug 22, 2025
```
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
```
  e8449ab5
- fix: support fb fp8 (#9462) · 4746aaea
  Yineng Zhang authored Aug 21, 2025
  
  4746aaea
- fix: should return a invalid request response when schema missing (#9461) · 10d34f74
  gongwei-130 authored Aug 21, 2025
  
  10d34f74
- accomendate reasoning_effort set in chat_template_kwargs (#9458) · 9ba72530
  gongwei-130 authored Aug 21, 2025
  
  9ba72530
- [5/n]decouple quantization implementation from vLLM dependency (#9454) · 9c8e4f69
  Hongbo Xu authored Aug 22, 2025
  
  9c8e4f69
- [router] add tokenizer benchmark (#9427) · 78ae1758
  Simo Lin authored Aug 21, 2025
  
  78ae1758
- [fix] Fix mxfp4 weight loading bug with TP sharding in GPT-OSS (#9433) · dae9a80f
  hlu1 authored Aug 21, 2025
```
Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com>
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
```
  dae9a80f
- Fix quant kernel test errors and benchmark wrong output speeds (#7604) · e85cb1ce
  fzyzcjy authored Aug 21, 2025
  
  e85cb1ce
- Refactor weight offloading logic (#8521) · 55d336cb
  fzyzcjy authored Aug 21, 2025
  
  55d336cb
- [Bug] Fix w4afp8 moe kernel (#9392) · de4990a5
  Yuhao Yao authored Aug 21, 2025
  
  de4990a5
- ci: enhance xeon ci (#9395) · 029e0af3
  DiweiSun authored Aug 21, 2025
  
  029e0af3
- Enables speculative decoding for the trtllm_mla attention backend (#9238) · 64574ef8
  pranavm-nvidia authored Aug 21, 2025
  
  64574ef8
- [NVIDIA] Fix trtllm fp4 moe backend when used in MTP (#9384) · 18da2c96
  Kaixi Hou authored Aug 21, 2025
  
  18da2c96
- Fix tiny misalign with previous truncation setting in tokenizer_manager (#9430) · 9b5f0f64
  Liangsheng Yin authored Aug 21, 2025
  
  9b5f0f64
- Fix FP4 inference corruption issue in glm4.5-air model (#9346) · 70bb066e
  Azure authored Aug 21, 2025
  
  70bb066e
- [feature] Ascend NPU graph support (#9399) · 2c4b4b78
  VDV1985 authored Aug 21, 2025
```
Co-authored-by: ronnie_zheng <zl19940307@163.com>
Co-authored-by: yezhifeng (D) <y00897525@china.huawei.com>
Co-authored-by: anon189Ty <Stari_Falcon@outlook.com>
Co-authored-by: Maksim <makcum888e@mail.ru>
Co-authored-by: ssshinigami <44640852+ssshinigami@users.noreply.github.com>
```
  2c4b4b78
- feat: Add Triton fallback option and SM120 MoE configs for FP8 models (#9251) · 7cd2ee06
  Martin Vit authored Aug 21, 2025
  
  7cd2ee06
- [bug] fix errors related to context length in SD (#9388) · eb19ccad
  Liangsheng Yin authored Aug 21, 2025
  
  eb19ccad
- [PD] Fix nvlink transport accuracy through transferring metadata with tcp (#9261) · 25ef53f0
  Shangming Cai authored Aug 21, 2025
```
Signed-off-by: Shangming Cai <csmthu@gmail.com>
```
  25ef53f0
- Fix biased_grouped_topk_cpu (#9420) · c674bf9c
  Cao E authored Aug 21, 2025
  
  c674bf9c
- Fix max_seq_len_k in trtllm_mha attention backend (#9416) · af1973b8
  Qiaolin Yu authored Aug 20, 2025
  
  af1973b8
- [router] add glm and step3 reasoning parser (#9415) · 5cfbb4c1
  Chang Su authored Aug 20, 2025
  
  5cfbb4c1
- [router] add tokenizer integration test with real mini tokenizer (#9413) · e6523102
  Chang Su authored Aug 20, 2025
  
  e6523102
- [router] Add IGW (Inference Gateway) Feature Flag (#9371) · 3828db43
  Keyang Ru authored Aug 20, 2025
```
Co-authored-by: Yineng Zhang <me@zhyncs.com>
```
  3828db43
20 Aug, 2025 5 commits
- Support trtllm_allreduce_fusion in flashinfer for cuda<12.8 (#9339) · 88fbc31b
  strgrb authored Aug 21, 2025
```
Co-authored-by: Zhang Kaihong <zhangkaihong.zkh@alibaba-inc.com>
```
  88fbc31b
- Add support for Qwen3-seq-cls (#9357) · 8f5b9910
  nathan authored Aug 21, 2025
  
  8f5b9910
- misc: parse bench_serving result as markdown table (#9377) · ef3004d9
  Mick authored Aug 21, 2025
  
  ef3004d9
- fix: InternS1 don't recognize image, updates image token for InternVL processor (#9381) · 84719b52
  Xinyuan Tong authored Aug 21, 2025
```
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
```
  84719b52
- Fixed the issue where eagle3 TPOT was not as good as without eagle3. (#9404) · e99729c9
  jiapingW authored Aug 21, 2025
  
  e99729c9