Commits · a20e7df8d0bcccb37b02ce83919f73108bb407a2 · change / sglang · GitLab

13 Oct, 2025 2 commits
- Improve dp attention port assignment scheme (#5889) · a20e7df8
  Yongtong Wu authored Oct 13, 2025
```
Co-authored-by: Cheng Wan <cwan@x.ai>
```
  a20e7df8
- Revert "Deprecate `global_server_args_dict`" (#11520) · 1bdd0102
  Cheng Wan authored Oct 12, 2025
  
  1bdd0102
12 Oct, 2025 29 commits
- [lint] Fix the lint issue (#11516) · 6cd29694
  Cheng Wan authored Oct 12, 2025
  
  6cd29694
- Sync changes on io_struct.py and deterministic ops (#11498) · 2ac46e94
  Lianmin Zheng authored Oct 12, 2025
  
  2ac46e94
- [Fix] Improve longbench prompt and other logics (#11474) · 0aa65f94
  Binyao Jiang authored Oct 12, 2025
  
  0aa65f94
- fix: revert temporarily remove b200 tests (#11515) · 0ecb4261
  Yineng Zhang authored Oct 12, 2025
  
  0ecb4261
- chore: remove flashinfer cleanup cache (#11514) · 05f015f6
  Yineng Zhang authored Oct 12, 2025
  
  05f015f6
- Deprecate `global_server_args_dict` (#11331) · 1083e7e3
  Liangsheng Yin authored Oct 13, 2025
  
  1083e7e3
- [CI] fix lint (#11509) · 2157d12a
  Liangsheng Yin authored Oct 13, 2025
  
  2157d12a
- doc: add doc for adding new models into nightly-ci (#11443) · 9f2b457c
  Mick authored Oct 12, 2025
```
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
```
  9f2b457c
- Bugfix: Fix Type consistency for KV indices in SWARadixCache (#11452) · f5b34a51
  hzh0425 authored Oct 12, 2025
```
Co-authored-by: yizhang2077 <1109276519@qq.com>
```
  f5b34a51
- Fix unit tests (#11503) · 5a6ec8f9
  Lianmin Zheng authored Oct 12, 2025
  
  5a6ec8f9
- temporarily remove b200 tests (#11502) · 6a653bb1
  Lianmin Zheng authored Oct 12, 2025
  
  6a653bb1
- Fix port conflicts in CI (#11497) · 548a57b1
  Lianmin Zheng authored Oct 12, 2025
  
  548a57b1
- Temporarily remove b200 tests (#11501) · 88e73ed0
  Lianmin Zheng authored Oct 12, 2025
  
  88e73ed0
- move fla env check position (#11500) · 4b15fa00
  Yi Zhang authored Oct 12, 2025
  
  4b15fa00
- Move args from `global_config` to `environ` (#11332) · f4941906
  Liangsheng Yin authored Oct 12, 2025
  
  f4941906
- Fix CI break by express-laned PRs. (#11499) · 01e59e82
  Liangsheng Yin authored Oct 12, 2025
  
  01e59e82
- bailingMoE: Fix Key error of deepep_mode (#11465) · 99a0704a
  Mike Qiu authored Oct 12, 2025
```
Signed-off-by: Michael Qiu <qiudayu.qdy@antgroup.com>
Co-authored-by: Mike_Qiu <qiudayu.qdy@antgroup.com>
```
  99a0704a
- Fix the GPT function calling regex to allow dash in the name (#10577) · ec1cd90a
  Antoine Roux authored Oct 12, 2025
  
  ec1cd90a
- [chore][2/N] Avoid using default mutable parameters (#11479) · 1103dc62
  Kai-Hsun Chen authored Oct 12, 2025
```
Signed-off-by: Kai-Hsun Chen <khchen@x.ai>
```
  1103dc62
- [ perf ] Replace json-> orjson in hot path (#11221) · a220536f
  Vincent Zhong authored Oct 12, 2025
```
Signed-off-by: vincentzed <207368749+vincentzed@users.noreply.github.com>
```
  a220536f
- [bugfix]: use correct causality condition for flashattention, flashinfer, and... · 7b064f04
  Mahmoud Ashraf authored Oct 12, 2025
```
[bugfix]: use correct causality condition for flashattention, flashinfer, and triton backends (#10172)
```
  7b064f04
- [chore][1/N] Avoid using default mutable parameters (#11478) · 43190bec
  Kai-Hsun Chen authored Oct 12, 2025
```
Signed-off-by: Kai-Hsun Chen <khchen@x.ai>
```
  43190bec
- [smol] [perf] Qwen3-VL in place op. (#11481) · be740acd
  Vincent Zhong authored Oct 12, 2025
```
Signed-off-by: vincentzed <207368749+vincentzed@users.noreply.github.com>
```
  be740acd
- chore: bump sgl-kernel version to 0.3.16 (#11476) · 2db2cddd
  sglang-bot authored Oct 11, 2025
  
  2db2cddd
- [Router]: Small Typo in a comment within tree.rs (#11489) · 9b5efe34
  Wenyi Xu authored Oct 12, 2025
  
  9b5efe34
- Piecewise CUDA Graph Support & Torch Compile Backend (#10062) · 4ac8e09d
  Yuwei An authored Oct 11, 2025
```
Signed-off-by: Oasis-Git <ayw.sirius19@gmail.com>
```
  4ac8e09d
- Beta spec-overlap for EAGLE (#11398) · 20a6c0a6
  Liangsheng Yin authored Oct 12, 2025
```
Co-authored-by: Lianmin Zheng <15100009+merrymercy@users.noreply.github.com>
Co-authored-by: Hanming Lu <69857889+hanming-lu@users.noreply.github.com>
```
  20a6c0a6
- [Feature] support regex strings as a stopping condition (#10635) · 47c606d3
  Glen Liu authored Oct 11, 2025
  
  47c606d3
- [CI] Add nightly builds to dockerhub (#9804) · 9fcf7306
  Sahithi Chigurupati authored Oct 11, 2025
```
Signed-off-by: Sahithi Chigurupati <chigurupati.sahithi@gmail.com>
```
  9fcf7306
11 Oct, 2025 9 commits
- fix Xeon CI (#11454) · 0a304870
  Zaili Wang authored Oct 12, 2025
  
  0a304870
- [7/n] decouple quantization impl from vllm dependency - gguf kernel (#11019) · 8fdcd98e
  PGFLMG authored Oct 12, 2025
  
  8fdcd98e
- Add option to disable `any_whitespace` for `xgrammar` and `llguidance` backends. (#8919) · b5dcfd41
  Lorenzo Lu authored Oct 11, 2025
```
Co-authored-by: Chang Su <chang.s.su@oracle.com>
```
  b5dcfd41
- fix stop when stream (#11462) · 5061b8fd
  ybyang authored Oct 11, 2025
```
Signed-off-by: ybyang <ybyang7@iflytek.com>
Co-authored-by: Liangsheng Yin <lsyincs@gmail.com>
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
```
  5061b8fd
- [Fix] Fix split prefill with fa3. (#11428) · c8452551
  ykcombat authored Oct 11, 2025
  
  c8452551
- Fix enable_v2 in int8 quant (#11470) · bf3e7149
  fzyzcjy authored Oct 11, 2025
  
  bf3e7149
- [Documentation][Configuration] Server args and documentation of PD-Multiplexing. (#11427) · f5754d12
  ykcombat authored Oct 11, 2025
  
  f5754d12
- Adjust logits metada init for target verify (#11467) · 739daa63
  Liangsheng Yin authored Oct 11, 2025
  
  739daa63
- Super tiny delete unused openai router in sgl-router (#11448) · d957177a
  fzyzcjy authored Oct 11, 2025
  
  d957177a