Commits · c8295d235386db8b5c4c3571b6d963716d0bdce1 · change / sglang

"configs/vscode:/vscode.git/clone" did not exist on "476c51a73c1fda0ae562addecb7c9ad366c0cb04"

08 Sep, 2025 6 commits
- enable auto-round quantization model (#6226) · c8295d23
  Weiwei authored Sep 08, 2025
```
Signed-off-by: Zhang, Weiwei1 <weiwei1.zhang@intel.com>
```
  c8295d23
- [Bugfix] Qwen3MoE aclrtMemcpy failed with NPUGraph (#10013) · b67c277f
  Even Zhou authored Sep 08, 2025
  
  b67c277f
- Add speculator attention backend switch (#9981) · 8c5930f0
  cicirori authored Sep 08, 2025
  
  8c5930f0
- Add graph runner support with torch compile on CPU (#7843) · 7577f0e4
  Cao E authored Sep 08, 2025
  
  7577f0e4
- Standalone speculative decoding (#10090) · 8cda5a62
  Qiaolin Yu authored Sep 07, 2025
  
  8cda5a62
- vlm: enable GLM4.1V server testing & fix video processing (#10095) · f3440adc
  Xinyuan Tong authored Sep 08, 2025
```
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Binyao Jiang <byjiang1996@gmail.com>
```
  f3440adc
06 Sep, 2025 5 commits
- [CI] Refactor disaggregation tests (#10068) · 00974e4f
  Shangming Cai authored Sep 06, 2025
```
Signed-off-by: Shangming Cai <csmthu@gmail.com>
```
  00974e4f
- [Fix] Compatibility between DP attention and pipeline parallelism (#10100) · 21af5c04
  Cheng Wan authored Sep 06, 2025
```
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  21af5c04
- [7/N] MoE Refactor: the implementation of new framework (#9269) · 3fa62da7
  Cheng Wan authored Sep 05, 2025
  
  3fa62da7
- support Llama4 with non uniformed intermediate size across layers for… (#10047) · ab62b135
  gongwei-130 authored Sep 05, 2025
  
  ab62b135
- [Minor] Refactors KV memory pool (#9842) · 273b2834
  Xinyuan Tong authored Sep 06, 2025
  
  273b2834
05 Sep, 2025 2 commits
- [Fix] Add speculative_draft_model_revision to server_args (#5255) · 13705dae
  DevashishLal-CB authored Sep 05, 2025
```
Signed-off-by: Devashish Lal <devashish@rivosinc.com>
```
  13705dae
- Simplify `Router` arguments passing and build it in docker image (#9964) · 6e95f5e5
  Liangsheng Yin authored Sep 05, 2025
  
  6e95f5e5
04 Sep, 2025 3 commits
- metrics: support customer buckets for prompt/generation_tokens_histogram (#9634) · b32ab070
  Yingchun Lai authored Sep 04, 2025
  
  b32ab070
- feat(hicache): Add generic hicache ci e2e test and benchmark test (#9846) · 106c2b31
  hzh0425 authored Sep 04, 2025
```
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
```
  106c2b31
- feat: add gpt oss b200 ci (#9988) · de921733
  Yineng Zhang authored Sep 03, 2025
  
  de921733
03 Sep, 2025 1 commit
- Move parsers under a single folder (#9912) · 60e37f80
  Lianmin Zheng authored Sep 02, 2025
  
  60e37f80
02 Sep, 2025 1 commit

[model] support MiniCPM-V 4.0 (#8747) · 03dbf1aa

tc-mb authored Sep 03, 2025


Signed-off-by: tc-mb <caitianchi@modelbest.cn>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>

03dbf1aa

01 Sep, 2025 2 commits

Support Multi Process Tokenizer Manager(#6555) (#8964) · 5f77e129

ybyang authored Sep 01, 2025


Signed-off-by: ybyang <ybyang7@iflytek.com>
Signed-off-by: huanglong <huanglong@linux.alibaba.com>
Co-authored-by: Huang Long <121648372+LLLL114@users.noreply.github.com>
Co-authored-by: huanglong <huanglong@linux.alibaba.com>
Co-authored-by: Shangming Cai <csmthu@gmail.com>

5f77e129

Disable radix cache in test_lora_update.py for better stability (#9852) · 7de2ce45
Baizhou Zhang authored Aug 31, 2025

7de2ce45

29 Aug, 2025 3 commits
- feat: add original logprobs to response (#8375) · 839c93bd
  narutolhy authored Aug 29, 2025
```
Co-authored-by: Chayenne <zhaochen20@outlook.com>
Co-authored-by: luhongyu.4869 <luhongyu.4869@bytedance.com>
```
  839c93bd
- support enable in the reasoning field to enable thingking for thinkin… (#9715) · 3fd1431d
  gongwei-130 authored Aug 29, 2025
  
  3fd1431d
- accomendate json schema in the "schema" field, not in "json_schema" field of... · 9a7c8842
  gongwei-130 authored Aug 28, 2025
```
accomendate json schema in the "schema" field, not in "json_schema" field of response_format (#9786)
```
  9a7c8842
28 Aug, 2025 2 commits
- [AMD] Support Hierarchical Caching on AMD GPUs (#8236) · 711390a9
  Hubert Lu authored Aug 28, 2025
  
  711390a9
- Support speculative decoding in hybrid attention backend (#9573) · 4a4772ae
  Qiaolin Yu authored Aug 28, 2025
  
  4a4772ae
26 Aug, 2025 4 commits
- add `response_format` support for `completion` API (#9665) · b6c14ec0
  cicirori authored Aug 27, 2025
  
  b6c14ec0
- Fix kimi k2 function calling format (#9606) · 0936c766
  Xiaotong Jiang authored Aug 26, 2025
  
  0936c766
- model: Support nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 (#9301) · 4cd08dc5
  Netanel Haber authored Aug 26, 2025
  
  4cd08dc5
- [new feat] ascend backend support fia fusion kernel (#8328) · f92b729d
  ZhengdQin authored Aug 26, 2025
```
Co-authored-by: Even Zhou <even.y.zhou@outlook.com>
```
  f92b729d
25 Aug, 2025 2 commits

Fix Harmony reasoning parser for and auto-separation for gpt-oss models (#9190) · a0a77d93

Jonas authored Aug 26, 2025


Co-authored-by: Chang Su <chang.s.su@oracle.com>
Co-authored-by: Chayenne <zhaochen20@outlook.com>
Co-authored-by: zhaochenyang20 <zhaochenyang20@gmail.com>
Co-authored-by: minleminzui <2969413251@qq.com>
Co-authored-by: maocheng23 <maocheng@berkeley.edu>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>

a0a77d93

fix: revert #8593 (#9581) · ebd9dbe7
Yineng Zhang authored Aug 25, 2025

ebd9dbe7

22 Aug, 2025 1 commit
- 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
21 Aug, 2025 2 commits

ci: enhance xeon ci (#9395) · 029e0af3
DiweiSun authored Aug 21, 2025

029e0af3

[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

20 Aug, 2025 5 commits
- misc: parse bench_serving result as markdown table (#9377) · ef3004d9
  Mick authored Aug 21, 2025
  
  ef3004d9
- Support pinning adapter via server args. (#9249) · b0980af8
  Lifu Huang authored Aug 20, 2025
  
  b0980af8
- Revert "[feature] Rework Ascend NPU graph support" (#9385) · de2dd738
  Even Zhou authored Aug 20, 2025
  
  de2dd738
- [CI] Fix disaggregation failure tolerance CI (#9378) · d8ed60f2
  Shangming Cai authored Aug 20, 2025
```
Signed-off-by: Shangming Cai <csmthu@gmail.com>
```
  d8ed60f2
- [feature] Rework Ascend NPU graph support (#9350) · 3680d6f8
  Even Zhou authored Aug 20, 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>
```
  3680d6f8
19 Aug, 2025 1 commit
- Revert "[feature] Ascend NPU graph support (#8027)" (#9348) · f4fafacc
  Even Zhou authored Aug 20, 2025
  
  f4fafacc