Commits · 0eec4cb6cccaefeb002ae4a8a4d982b5d2c8fb2e · change / sglang

11 Aug, 2025 9 commits
- HiCache, add bench long context plus minor fixs (#9086) · 0eec4cb6
  Zhiqiang Xie authored Aug 11, 2025
```
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  0eec4cb6
- TRTLLM-MLA FP8 path (#8638) · f508cd3c
  Faraz authored Aug 11, 2025
```
Signed-off-by: Faraz Khoubsirat <58580514+farazkh80@users.noreply.github.com>
```
  f508cd3c
- Update hyperparameter_tuning.md (#9083) · 8c07fabd
  Lianmin Zheng authored Aug 11, 2025
  
  8c07fabd
- Fix docs for clip max new tokens (#9082) · f9afa7dc
  Liangsheng Yin authored Aug 11, 2025
  
  f9afa7dc
- [PD]decode: add CLIP_MAX_NEW_TOKEN for pop_preallocated (#8866) · 0d9e89ec
  Jimmy authored Aug 12, 2025
  
  0d9e89ec
- Fix broken Kimi models HuggingFace link (#9080) · 3d64fda3
  Hangzhi authored Aug 11, 2025
  
  3d64fda3
- Support radix cache for Lora feature (#7216) · 75e6a7cd
  Baizhou Zhang authored Aug 11, 2025
  
  75e6a7cd
- Improve docs and developer guide (#9044) · 2e8e7e35
  Lianmin Zheng authored Aug 10, 2025
  
  2e8e7e35
- Refactor the docs (#9031) · 2449a0af
  Lianmin Zheng authored Aug 10, 2025
  
  2449a0af
10 Aug, 2025 1 commit
- Improve LoRA Perf by Deprecating FlashInfer and Eliminating Redundant Tensor Ops (#8940) · f8a173bb
  Lifu Huang authored Aug 10, 2025
  
  f8a173bb
09 Aug, 2025 2 commits

Support glm4.1v and glm4.5v (#8798) · f29aba8c

Binyao Jiang authored Aug 09, 2025


Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xinyuan Tong <justinning0323@outlook.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: zRzRzRzRzRzRzR <2448370773@qq.com>
Co-authored-by: Minglei Zhu <mingleizhu1122@gmail.com>
Co-authored-by: Chang Su <csu272@usc.edu>

f29aba8c

Clean up server_args.py to have a dedicated function for model specific adjustments (#8983) · 706bd69c
Lianmin Zheng authored Aug 08, 2025

706bd69c

08 Aug, 2025 2 commits
- chore: bump v0.5.0rc0 (#8959) · 9020f7fc
  Yineng Zhang authored Aug 08, 2025
  
  9020f7fc
- Add ernie4.py for ERNIE-4.5 (#7657) · 11325474
  Wenbo Yang authored Aug 08, 2025
  
  11325474
07 Aug, 2025 2 commits
- Enables force reasoning based on chat template for Qwen3-Thinking (#8369) · 3fa3c6cd
  Xinyuan Tong authored Aug 06, 2025
```
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
Co-authored-by: Chang Su <csu272@usc.edu>
```
  3fa3c6cd
- Support GPU pinning for LoRA (#8697) · 6210e2c4
  Lifu Huang authored Aug 06, 2025
  
  6210e2c4
06 Aug, 2025 2 commits
- [Feature] improve TBO: two chunk overlap (#8144) · ca47e24f
  HouseWest authored Aug 06, 2025
  
  ca47e24f
- Support bailing moe (#8680) · d26ca84f
  Praneth Paruchuri authored Aug 06, 2025
  
  d26ca84f
03 Aug, 2025 3 commits
- chore: bump v0.4.10.post2 (#8727) · 8cd34458
  Yineng Zhang authored Aug 03, 2025
  
  8cd34458
- [feat] support minimum token load balance in dp attention (#7379) · f7b2853f
  Guanhua Wang authored Aug 03, 2025
  
  f7b2853f
- Support limiting max loaded loras in CPU. (#8650) · 8675bdf2
  Lifu Huang authored Aug 03, 2025
  
  8675bdf2
01 Aug, 2025 4 commits
- Add support for NCCL symmetric memory for TP allreduces (#8238) · 82e6c3a6
  Nicolas Castet authored Aug 01, 2025
  
  82e6c3a6
- fix arg typo for --disaggregation-transfer-backend (#8664) · b17c5b01
  Zac authored Aug 02, 2025
  
  b17c5b01
- [5/N] MoE Refactor: Update MoE parallelism arguments (#8658) · 6c88f6c8
  Cheng Wan authored Aug 01, 2025
  
  6c88f6c8
- chore: bump v0.4.10.post1 (#8652) · 33f0de33
  Ke Bao authored Aug 01, 2025
  
  33f0de33
31 Jul, 2025 3 commits

TRTLLM Gen MLA Decode Kernel Integration (same as #7938) (#8632) · 4b04998d
Faraz authored Jul 31, 2025
```
Signed-off-by: Faraz Khoubsirat <58580514+farazkh80@users.noreply.github.com>
```
4b04998d
chore: bump v0.4.10 (#8608) · 02328864
Yineng Zhang authored Jul 31, 2025

02328864

model: support Step3V (#8583) · 51c38163

Chang Su authored Jul 31, 2025


Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
Co-authored-by: nnnobody-code <nnnobody@foxmail.com>
Co-authored-by: ispobock <ispobaoke@gmail.com>
Co-authored-by: Qiaolin-Yu <qy254@cornell.edu>
Co-authored-by: Qiaolin-Yu <liin1211@outlook.com>
Co-authored-by: Xinyuan Tong <justinning0323@outlook.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>

51c38163

30 Jul, 2025 2 commits
- [Model] Add support for Arcee Foundational Model (#8154) · ec5f9442
  Adarsh Shirawalmath authored Jul 30, 2025
  
  ec5f9442
- [feature] [sgl-router] Add a dp-aware routing strategy (#6869) · a730ce81
  Rui Chen authored Jul 30, 2025
  
  a730ce81
29 Jul, 2025 1 commit
- chore: bump v0.4.9.post6 (#8517) · 6478831b
  Yineng Zhang authored Jul 29, 2025
  
  6478831b
28 Jul, 2025 4 commits
- [NVIDIA] Change to use `num_local_experts` (#8453) · 134fa43e
  Kaixi Hou authored Jul 28, 2025
  
  134fa43e
- chore: bump v0.4.9.post5 (#8458) · 45bc170b
  Yineng Zhang authored Jul 28, 2025
  
  45bc170b
- doc: add bench_one_batch_server in the benchmark doc (#8441) · 484d0e02
  Qiaolin Yu authored Jul 27, 2025
  
  484d0e02
- [feat] Support different attention backends for prefill and decode (#6338) · 28103384
  Qiaolin Yu authored Jul 27, 2025
```
Co-authored-by: tianqilin.99 <tianqilin.99@bytedance.com>
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
```
  28103384
27 Jul, 2025 1 commit

Support precomputed_embeddings for Llama 4 (#8156) · 44d600cd

Kevin Xiang Li authored Jul 27, 2025


Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xiang (Kevin) Li <lik@nvidia.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>

44d600cd

26 Jul, 2025 1 commit
- chore: bump v0.4.9.post4 (#8305) · 2272c2a5
  Yineng Zhang authored Jul 25, 2025
  
  2272c2a5
25 Jul, 2025 3 commits
- [Feat] Add reasoning parser for Qwen/Qwen3-235B-A22B-Thinking-2507 (#8363) · d8ee1564
  Chang Su authored Jul 25, 2025
  
  d8ee1564
- [torch.compile bug] avoid biased_grouped_topk_impl func repeatedly triggering... · 9045cc1e
  Xiaoyu Zhang authored Jul 25, 2025
```
[torch.compile bug] avoid biased_grouped_topk_impl func repeatedly triggering `torch.compile` in forward pass (#8353)
```
  9045cc1e
- [CPU] Add tutorial docs for SGL on CPU (#8000) · 15d27591
  Zaili Wang authored Jul 25, 2025
  
  15d27591