Commits · 8601300bebf1be2f702732bea1a704adb802b084 · zhaoyu6 / sglang

"include/ck/config.hpp" did not exist on "81c942cd7e198b46f55be31451d51f27459d34ab"

28 Apr, 2025 11 commits
- fix: fix the error where the content is None when reasoning and tool … (#5838) · 8601300b
  mlmz authored Apr 28, 2025
  
  8601300b
- Feat: add support for thinking mode via chat_template_kwargs.enable_t… (#5551) · 6fa6f38e
  mlmz authored Apr 28, 2025
```
Co-authored-by: shuaills <shishuaiuoe@gmail.com>
Co-authored-by: Chayenne <zhaochen20@outlook.com>
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
Co-authored-by: Yineng Zhang <me@zhyncs.com>
```
  6fa6f38e
- Revert "Tiny refactor DefaultModelLoader.Source" (#5825) · 693723d1
  Lianmin Zheng authored Apr 28, 2025
  
  693723d1
- [Docs] Replace lists with tables for cleanup and readability in server_arguments (#5276) · 966eb908
  Michael Yao authored Apr 28, 2025
  
  966eb908
- Tiny refactor DefaultModelLoader.Source (#5482) · 644ed409
  fzyzcjy authored Apr 28, 2025
  
  644ed409
- Turn on overlap scheduler for multimodal models (#5771) · 3029889c
  Lianmin Zheng authored Apr 27, 2025
  
  3029889c
- Add a doc to fix sgl-kernel build link error in py39 with ccache (#5809) · ef15dcda
  Xiaoyu Zhang authored Apr 28, 2025
  
  ef15dcda
- Dockerfile.dev pip scikit_build_core (#5807) · ad4df307
  Xiaoyu Zhang authored Apr 28, 2025
  
  ad4df307
- chore: upgrade sgl-kernel 0.1.0 (#5690) · 41ac0c6d
  Yineng Zhang authored Apr 27, 2025
  
  41ac0c6d
- Add Cutlass MLA attention backend (#5390) · 84810da4
  Trevor Morris authored Apr 27, 2025
  
  84810da4
- Improve overlap scheduling (#5788) · 40d9b8ac
  Liangsheng Yin authored Apr 28, 2025
  
  40d9b8ac
27 Apr, 2025 29 commits
- [Misc] add structure logging, write to file and log tracing for SGL Router · f0365820
  Simo Lin authored Apr 27, 2025
  
  f0365820
- [Docs] update grafana setup guide in production metrics (#5643) · 86317c09
  Huapeng Zhou authored Apr 28, 2025
```
Co-authored-by: NoahM <88418672+zhudianGG@users.noreply.github.com>
```
  86317c09
- [CI] Improve github summary & enable fa3 for more models (#5796) · daed453e
  Lianmin Zheng authored Apr 27, 2025
  
  daed453e
- Update nightly-test.yml (#5797) · ded04b2e
  Lianmin Zheng authored Apr 27, 2025
  
  ded04b2e
- Release v0.4.6 (#5795) · 84022c0e
  Baizhou Zhang authored Apr 27, 2025
  
  84022c0e
- Add 8-GPU Test for Deepseek-V3 (#5691) · f9fb33ef
  Baizhou Zhang authored Apr 27, 2025
```
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
```
  f9fb33ef
- [CI] Fix test case (#5790) · a38f6932
  Lianmin Zheng authored Apr 27, 2025
  
  a38f6932
- [PD]Reduce kv transfer threads (#5791) · beb65c74
  Liangsheng Yin authored Apr 27, 2025
  
  beb65c74
- [CI] Fix ci tests (#5769) · 621e96bf
  Lianmin Zheng authored Apr 27, 2025
  
  621e96bf
- [CI] fix port conflicts (#5789) · 35ca04d2
  Lianmin Zheng authored Apr 27, 2025
  
  35ca04d2
- [CI] Tune threshold (#5787) · 3c4e0ee6
  Lianmin Zheng authored Apr 27, 2025
  
  3c4e0ee6
- Revert "Use device_id in dist init to reduce NCCL communicator warmup & creation overhead" (#5786) · 9c088829
  Lianmin Zheng authored Apr 27, 2025
  
  9c088829
- Revert "[fix] fix bench_one_batch_server" (#5785) · 005aad32
  Lianmin Zheng authored Apr 27, 2025
  
  005aad32
- Simplify FA3 tests (#5779) · 4d23ba08
  Lianmin Zheng authored Apr 27, 2025
  
  4d23ba08
- Revert "Revert "fix: import vllm_rotary_embedding error when head_size not in... · 6e313c1b
  Lianmin Zheng authored Apr 27, 2025
```
Revert "Revert "fix: import vllm_rotary_embedding error when head_size not in 64, 128, 256, 512"" (#5777)
```
  6e313c1b
- Split local attention test from fa3 test (#5774) · a45a4b23
  Baizhou Zhang authored Apr 27, 2025
  
  a45a4b23
- Fix eagle test case (#5776) · 981a2619
  Lianmin Zheng authored Apr 27, 2025
  
  981a2619
- Revert "fix: import vllm_rotary_embedding error when head_size not in 64, 128, 256, 512" (#5772) · 8ba31330
  Lianmin Zheng authored Apr 26, 2025
  
  8ba31330
- add switch to disable open api doc (#3744) · 02102063
  zhanweidu authored Apr 27, 2025
```
Signed-off-by: congcongke <zhanweidu@163.com>
```
  02102063
- Add memory_saver check (#4986) · 7e944246
  Kebe authored Apr 27, 2025
```
Signed-off-by: Kebe <mail@kebe7jun.com>
```
  7e944246
- Use sgl-kernel sgl_per_token_group_quant_int8 (#4971) · a086a113
  lambert0312 authored Apr 27, 2025
  
  a086a113
- update llguidance to 0.7.11; adds StructTag (#4870) · bdbe5f81
  Michał Moskal authored Apr 26, 2025
  
  bdbe5f81
- fix(srt): check if sample_indices is not None before usage. (#5633) · 9ad28f63
  aoshen524 authored Apr 26, 2025
  
  9ad28f63
- Handle JSONDecodeError while processing request data (#5599) · d7b1ce65
  yan97ao authored Apr 27, 2025
  
  d7b1ce65
- [misc] more decode step log for batch_one_batch (#5565) · f55933e1
  JieXin Liang authored Apr 27, 2025
  
  f55933e1
- Add Llama 4 to FA3 test (#5509) · 408ba022
  Stefan He authored Apr 26, 2025
  
  408ba022
- fix: Use `is not None` instead of `!= None` for None checks. (#5687) · 094891c0
  vzed authored Apr 26, 2025
  
  094891c0
- support for the DeepSeek model by enabling streaming response parsing (#5592) · a21ef363
  Frankey_8080 authored Apr 27, 2025
  
  a21ef363
- [fix] fix bench_one_batch_server (#5607) · 3c4dc38a
  JieXin Liang authored Apr 27, 2025
  
  3c4dc38a