Commits · 7e28c67d19ddea8c74fca7b7e6dd2e3e3bec3c37 · change / sglang

"vscode:/vscode.git/clone" did not exist on "93000580261971971ebb12aff03f6bc3ce30a9f2"

30 Oct, 2025 2 commits
- Fix DeepSeek chat templates to handle tool call arguments type checking (#11700) (#12123) · 7e28c67d
  Kangyan-Zhou authored Oct 30, 2025
  
  7e28c67d
- Import flash_mla from sgl-kernel (#12135) · 621dfb88
  Baizhou Zhang authored Oct 29, 2025
  
  621dfb88
29 Oct, 2025 6 commits
- [CI] Add Llama 3.1 8B FP4 to B200 CI (#12182) · 7ed8ba05
  b8zhong authored Oct 29, 2025
  
  7ed8ba05
- [2/2] Deepseek deterministic: support deepseek v3 deterministic inference on 8 x H200 (#12095) · e39628fd
  Minglei Zhu authored Oct 29, 2025
  
  e39628fd
- feat: return partial generation results when aborting requests in waiting queue (#11673) · caa5d296
  Yuhong Guo authored Oct 29, 2025
  
  caa5d296
- Eagle3 DP attention for Qwen3 MoE (#12002) · 750940ae
  Rain H authored Oct 29, 2025
  
  750940ae
- [ci] Try fixing broken CIs (#12317) · 685c0645
  Baizhou Zhang authored Oct 29, 2025
  
  685c0645
- Add continuous_usage_stats support for streaming responses (#12241) · 334543ff
  Xiaoyu Zhang authored Oct 29, 2025
  
  334543ff
28 Oct, 2025 5 commits
- [Feature] Sglang Tracing: Fine-Grained Tracking for Request Latency - Part 2 (#10804) · ea961060
  Feng Su authored Oct 28, 2025
```
Signed-off-by: Feng Su <sufeng@linux.alibaba.com>
```
  ea961060
- Feature/Add GET endpoint to query loaded LoRA adapters (#12229) · cc7b04a2
  Chenxi Li authored Oct 28, 2025
  
  cc7b04a2
- Support releasing CUDA graph memory when paused (#7873) · 691c8534
  fzyzcjy authored Oct 28, 2025
```
Co-authored-by: ryang-max <y1cunhui.yang@gmail.com>
Co-authored-by: ryang <38470282+ryang-max@users.noreply.github.com>
```
  691c8534
- Add env var to control custom Triton kernel cache and set CSGMV as default backend. (#12176) · ce832d70
  Lifu Huang authored Oct 27, 2025
  
  ce832d70
- [Auto Sync] Update scheduler.py, spec_info.py, run_suite.py... (20251027) (#12235) · a6ea3add
  Yineng Zhang authored Oct 27, 2025
```
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: gongwei-130 <56567052+gongwei-130@users.noreply.github.com>
```
  a6ea3add
27 Oct, 2025 2 commits
- Add support for Matryoshka embeddings (#126) (#11142) · 9fc3e8aa
  satyamk7054 authored Oct 27, 2025
```
Co-authored-by: Satyam Kumar <satyamk@linkedin.com>
```
  9fc3e8aa
- Add support for AutoRound quantized models (#10153) · caa4819b
  Weiwei authored Oct 27, 2025
  
  caa4819b
26 Oct, 2025 7 commits
- Remove deprecated --enable-beta-spec argument and fix b200 test (#12167) · da1766e4
  Kangyan-Zhou authored Oct 26, 2025
```
Co-authored-by: Claude <noreply@anthropic.com>
```
  da1766e4
- model: support NVILA and NVILA Lite (#10399) · a8023891
  Zijian Zhang authored Oct 27, 2025
  
  a8023891
- Support DeepGEMM for deterministic inference (#12142) · 0103f374
  fzyzcjy authored Oct 26, 2025
  
  0103f374
- Do not use `MagicMock` to mock `server_args` in tests (#12154) · 5994e6c3
  Liangsheng Yin authored Oct 26, 2025
  
  5994e6c3
- [quantization] AWQ Marlin doesn't work when dtype is bfloat16 (#11494) · 6371f7af
  Kai-Hsun Chen authored Oct 26, 2025
```
Signed-off-by: Kai-Hsun Chen <khchen@x.ai>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
```
  6371f7af
- [misc] depdencies & enviroment flag (#12113) · 8491c794
  Liangsheng Yin authored Oct 26, 2025
  
  8491c794
- [Test] Add dsv3.2 nsa backend testing (#11936) · b72f9f08
  Johnsonms authored Oct 25, 2025
  
  b72f9f08
25 Oct, 2025 6 commits
- Accelerate deepseek fp4 b200 ci (#11993) · d98b81e2
  Qiaolin Yu authored Oct 25, 2025
  
  d98b81e2
- Reenable b200 tests (#11814) · 9e656dd3
  Kangyan-Zhou authored Oct 25, 2025
  
  9e656dd3
- Skip TestLlama4LoRA in CI (#12098) · d9b31011
  Lifu Huang authored Oct 25, 2025
  
  d9b31011
- [Fix] Set global args in cpu test (#12105) · ce869793
  Baizhou Zhang authored Oct 24, 2025
  
  ce869793
- Support true on-policy (#12058) · 20bd2271
  fzyzcjy authored Oct 25, 2025
  
  20bd2271
- [2/N]Support DeepSeek-R1 w4a8 low latency deepep (#8464) · 13bf565d
  Jinwu authored Oct 25, 2025
```
Co-authored-by: Hank Han <hanhan7630@outlook.com>
Co-authored-by: Shangchuan Huang <2510421000@qq.com>
```
  13bf565d
24 Oct, 2025 4 commits
- adjust dynamic vs static outputs comparison in test_lora_update.py (#11884) · fc86b18b
  Glen Liu authored Oct 24, 2025
  
  fc86b18b
- support more model in piecewise cuda graph (#11745) · 1801cd19
  narutolhy authored Oct 23, 2025
  
  1801cd19
- Refactor Triton-kernel MoE runner integration (#11795) · 62eff37b
  Jonah Bernard authored Oct 23, 2025
  
  62eff37b
- [8/n] decouple quantization impl from vllm dependency - gguf srt (#11964) · 14a4d80e
  Fan Yin authored Oct 24, 2025
```
Co-authored-by: Peng Zhang <zhuangsen.zp@antgroup.com>
```
  14a4d80e
23 Oct, 2025 8 commits
- Revert "[ROCm] Remove vLLM rope dependency & use AITER impl" (#12028) · 8ae9d4bb
  b8zhong authored Oct 23, 2025
  
  8ae9d4bb
- model: support deepseek-ocr (#11891) · 770529a7
  Mick authored Oct 24, 2025
```
Co-authored-by: yhyang201 <47235274+yhyang201@users.noreply.github.com>
Co-authored-by: yhyang201 <yhyang201@gmail.com>
Co-authored-by: Shi Shuai <126407087+shuaills@users.noreply.github.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
```
  770529a7
- ci: fix night-ci with push retry mechanism (#11765) · 8bd26dd4
  Mick authored Oct 24, 2025
  
  8bd26dd4
- Feature/nano v2 offline modelopt fp8 and nvfp4 (#12018) · a9849683
  Netanel Haber authored Oct 23, 2025
```
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
```
  a9849683
- [Fix] memory leak by overlap + retract (#11981) · b0b4f716
  cctry authored Oct 23, 2025
```
Co-authored-by: Liangsheng Yin <lsyincs@gmail.com>
```
  b0b4f716
- Revert "Support nvidia/NVIDIA-Nemotron-Nano-9B-v2-FP8/NVFP4" (#12015) · 6c18addb
  Liangsheng Yin authored Oct 23, 2025
  
  6c18addb
- Support nvidia/NVIDIA-Nemotron-Nano-9B-v2-FP8/NVFP4 (#11866) · d6fee73d
  Netanel Haber authored Oct 23, 2025
  
  d6fee73d
- [CPU] Optimize FP16 decode_attention_cpu (#10652) · 13fb8b54
  blzheng authored Oct 23, 2025
  
  13fb8b54