Commits · 51c38163c19cb64aee7727a60363d4f44108809b · change / sglang

"llm/llama.cpp/ggml/src/vulkan-shaders/sum_rows.comp" did not exist on "b0135f4b9b176eab9155b660d04c9ca2a1ec2341"

31 Jul, 2025 3 commits

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

Bug: Fix google gemma3n-mm audio input not working bug (#8365) · 59aab76f
Binyao Jiang authored Jul 30, 2025

59aab76f
Bump transfomers to 4.54.1 to fix Gemma cache issue. (#8541) · 67e53b16
Lifu Huang authored Jul 30, 2025

67e53b16

29 Jul, 2025 1 commit
- bring back kimi vl ci (#8537) · c0fd77e8
  Stefan He authored Jul 29, 2025
  
  c0fd77e8
28 Jul, 2025 5 commits
- feat: throttle requests at scheduler based on --max_queued_requests (#7565) · 747dd450
  harrisonlimh authored Jul 28, 2025
  
  747dd450
- GLM-4.5 Model Support Follow-up (#8445) · 581e7dcb
  Binyao Jiang authored Jul 27, 2025
  
  581e7dcb
- GLM-4.5 Model Support (#8224) · 6d6a8bc2
  Yuxuan Zhang authored Jul 28, 2025
```
Co-authored-by: Lifu Huang <lifu.hlf@gmail.com>
Co-authored-by: Binyao Jiang <byjiang1996@gmail.com>
Co-authored-by: Stefan He <hebiaobuaa@gmail.com>
```
  6d6a8bc2
- chore: bump transformer to 4.54.0 (#8416) · 4ad97370
  Stefan He authored Jul 27, 2025
```
Co-authored-by: Binyao Jiang <byjiang1996@gmail.com>
Co-authored-by: Lifu Huang <lifu.hlf@gmail.com>
```
  4ad97370
- [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 5 commits
- Fix test_openai_server (#8419) · 58dd95fb
  Chang Su authored Jul 27, 2025
  
  58dd95fb
- bugfix: Fix multiple finish_reason chunks and tool_calls finish reason check (#8417) · b47eda33
  Chang Su authored Jul 27, 2025
  
  b47eda33
- Fix: Improve test_openai_function_calling unit test and fix... · e983d666
  Binyao Jiang authored Jul 27, 2025
```
Fix: Improve test_openai_function_calling unit test and fix reasoning_parser.py think_start_token logic (#8316)
Co-authored-by: Chang Su <chang.s.su@oracle.com>
```
  e983d666
- Support overlapped lora updates (#8213) · df906455
  Lifu Huang authored Jul 27, 2025
  
  df906455
- 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 3 commits
- Add perf tests for LoRA (#8314) · 5c705b1d
  Lifu Huang authored Jul 26, 2025
  
  5c705b1d
- vlm: optimize tensor transport (#6003) · 3212c2ad
  Mick authored Jul 26, 2025
```
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
```
  3212c2ad
- Extract update_weights from RL Engine to SGLang to keep simplicity and fix torch reduce (#8267) · ce32bc2b
  Stefan He authored Jul 26, 2025
```
Co-authored-by: CuiBo 82354186+SuperCB@users.noreply.github.com
Co-authored-by: GeLee 865038696@qq.com
Co-authored-by: 杨睿 yangruipis@163.com
```
  ce32bc2b
25 Jul, 2025 6 commits
- [CI] Fix flaky threshold (#8370) · 3ec0b212
  Lianmin Zheng authored Jul 25, 2025
  
  3ec0b212
- [Feat] Add reasoning parser for Qwen/Qwen3-235B-A22B-Thinking-2507 (#8363) · d8ee1564
  Chang Su authored Jul 25, 2025
  
  d8ee1564
- Clean up server_args, triton cache manager (#8332) · ed2e313e
  Lianmin Zheng authored Jul 25, 2025
  
  ed2e313e
- [Bugfix][Feat] Add XML-ish grammar in EBNFComposer and fix misc bugs in Qwen3 detector (#8357) · f8260f25
  Chang Su authored Jul 25, 2025
  
  f8260f25
- DP Enhancement (#8280) · c0fb25e9
  Cheng Wan authored Jul 24, 2025
  
  c0fb25e9
- [Feature] Integrate quick allreduce and select the best allreduce implementation (#6619) · 28d4d472
  li haoyang authored Jul 25, 2025
```
Signed-off-by: Haoyang Li <Haoyang.Li@amd.com>
Co-authored-by: ilmarkov <imarkov@redhat.com>
```
  28d4d472
24 Jul, 2025 2 commits
- Fix incomplete tool call capture issue in streaming response of DeepSeek-V3... · 624a3b8d
  xianzhiT authored Jul 24, 2025
```
Fix incomplete tool call capture issue in streaming response of DeepSeek-V3 when enable MTP  (#7562)
```
  624a3b8d
- feat(function call): complete utility method for KimiK2Detector and enhance documentation (#8043) · 01079e17
  Chang Su authored Jul 23, 2025
  
  01079e17
23 Jul, 2025 3 commits
- Fix gemma3n with hybrid swa (#8240) · 38000a5f
  Xinyuan Tong authored Jul 23, 2025
```
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
```
  38000a5f
- Fix the issue of incorrect finish reason in final stream response chunk... · c87d4fec
  xianzhiT authored Jul 24, 2025
```
Fix the issue of incorrect finish reason in final stream response chunk returned during tool call (#7708)
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
```
  c87d4fec
- Introduce Stable LoRA ID System for Overlapped Updates and Prefix Caching (#8261) · 8abd3e77
  Lifu Huang authored Jul 23, 2025
  
  8abd3e77
21 Jul, 2025 2 commits
- [Feature] Add a test for Layer-wise Prefill (#8231) · 7b68d271
  Xiaoze Fan authored Jul 21, 2025
```
Signed-off-by: jason-fxz <jason341132@qq.com>
```
  7b68d271
- [Refactor] simplify multimodal data processing (#8107) · 8430bfe3
  Xinyuan Tong authored Jul 20, 2025
```
Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
```
  8430bfe3
20 Jul, 2025 4 commits
- [feature] enable NPU CI (#7935) · 93d124ef
  ronnie_zheng authored Jul 20, 2025
```
Co-authored-by: Even Zhou <14368888+iforgetmyname@users.noreply.github.com>
```
  93d124ef
- Feat: Support for Persimmon Model (#7983) · 83c104b1
  Praneth Paruchuri authored Jul 20, 2025
  
  83c104b1
- Add get_hidden_dim to qwen3.py for correct lora (#7312) · 877e35d7
  Pavel Logachev authored Jul 20, 2025
  
  877e35d7
- Enable FlashInfer support encoder models and add head_dim padding workaround (#6230) · cbdfb771
  Clay authored Jul 20, 2025
  
  cbdfb771
19 Jul, 2025 6 commits
- Support start up LoRA server without initial adapters (#8019) · 4e3defe5
  Lifu Huang authored Jul 19, 2025
  
  4e3defe5
- Fix LoRA buffer contamination during adapter eviction (#8103) · 3de617a7
  Lifu Huang authored Jul 19, 2025
  
  3de617a7
- Clean up server args (#8161) · bb0e8a32
  Lianmin Zheng authored Jul 19, 2025
  
  bb0e8a32
- [1/N] MoE Refactor: refactor `select_experts` (#7966) · 15ad6c90
  Cheng Wan authored Jul 19, 2025
  
  15ad6c90
- Feat: Support audio in Phi4-mm model (#8048) · b7e951a6
  Binyao Jiang authored Jul 18, 2025
  
  b7e951a6
- chore: tune mem fraction static for vlm (#6881) · 3964b352
  Mick authored Jul 19, 2025
  
  3964b352