Commits · e5b29bf14e4008f6a9bb08dc6e7fcac1a22351fe · change / sglang

29 Aug, 2025 1 commit

[PD] Support get_model_info interface for mini_lb (#9792) · e5b29bf1

Xuchun Shang authored Aug 29, 2025


Signed-off-by: Xuchun Shang <xuchun.shang@linux.alibaba.com>
Co-authored-by: Teng Ma <sima.mt@alibaba-inc.com>

e5b29bf1

28 Aug, 2025 1 commit
- [Feature] Support NPUGraph for DeepSeek on Ascend NPU (#9355) · 74dd4249
  chenxu140 authored Aug 29, 2025
```
Co-authored-by: Even Zhou <even.y.zhou@outlook.com>
```
  74dd4249
25 Aug, 2025 1 commit
- [PD] Improve disaggregation metrics output: update the metrics to keep... · b5c6529e
  SCDESPERTATE authored Aug 25, 2025
```
[PD] Improve disaggregation metrics output: update the metrics to keep reflecting real stats (#7317)
```
  b5c6529e
21 Aug, 2025 1 commit
- [PD] Fix nvlink transport accuracy through transferring metadata with tcp (#9261) · 25ef53f0
  Shangming Cai authored Aug 21, 2025
```
Signed-off-by: Shangming Cai <csmthu@gmail.com>
```
  25ef53f0
20 Aug, 2025 1 commit
- Fix mini lb timeout issue (#9369) · fe43e889
  fzyzcjy authored Aug 20, 2025
  
  fe43e889
19 Aug, 2025 1 commit
- [Bugfix] fix kv buffer register & dp attention & deepepmoe (#9327) · 01d47a27
  chenxu140 authored Aug 20, 2025
  
  01d47a27
18 Aug, 2025 1 commit
- [PD] Propagate internal server errors from aborted requests to clients instead... · 98b44e9e
  datdo-msft authored Aug 18, 2025
```
[PD] Propagate internal server errors from aborted requests to clients instead of blindly returning 200's (#8936)
```
  98b44e9e
17 Aug, 2025 1 commit

[PD] Support PD disaggregation with Prefill PP (#8846) · 384f8ab5

Shangming Cai authored Aug 17, 2025


Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
Signed-off-by: Shangming Cai <csmthu@gmail.com>
Co-authored-by: root <huzhiyuan@xiaohongshu.com>
Co-authored-by: Ying Sheng <sqy1415@gmail.com>
Co-authored-by: Francis <38564764+ssssnow@users.noreply.github.com>
Co-authored-by: zitto <zhjc1124@gmail.com>

384f8ab5

13 Aug, 2025 3 commits
- Clean up allocators (#9134) · 9e426466
  Lianmin Zheng authored Aug 13, 2025
```
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  9e426466
- [PD] feat: mooncake use batch reg/dereg (#8910) · 4a16a71c
  Teng Ma authored Aug 14, 2025
```
Co-authored-by: Shangming Cai <csmthu@gmail.com>
```
  4a16a71c
- [PD] optimize kv cache transfer directly using batch transfer (#9149) · a16923ef
  Francis authored Aug 14, 2025
```
Co-authored-by: Shangming Cai <csmthu@gmail.com>
```
  a16923ef
11 Aug, 2025 2 commits
- 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
07 Aug, 2025 1 commit
- [Feat] QWen-1M context support[2/2]: Update block sparse attention backend (#5949) · b7cd7430
  PGFLMG authored Aug 07, 2025
  
  b7cd7430
05 Aug, 2025 1 commit
- [PD] Refactor parallel sizes and add pp support for mooncake (#8571) · d98a4913
  Shangming Cai authored Aug 05, 2025
```
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
```
  d98a4913
03 Aug, 2025 1 commit

[Improvements] Merge health check route (#8444) · 6f9baf10

ybyang authored Aug 03, 2025


Signed-off-by: ybyang <ybyang7@iflytek.com>
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
Co-authored-by: Kan Wu <wukanustc@gmail.com>

6f9baf10

01 Aug, 2025 1 commit
- [fix] fix pd disagg error of vlms (#8094) · 2d401bd9
  萝卜菜 authored Aug 02, 2025
  
  2d401bd9
31 Jul, 2025 2 commits
- [bug] remove pdlb from minilb since its no longer available (#8634) · 5c14515f
  Simo Lin authored Jul 31, 2025
  
  5c14515f
- [PD] Use batch transfer for rdma transport and add notes for mnnvl usage (#8595) · 016fd251
  Shangming Cai authored Jul 31, 2025
```
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
```
  016fd251
29 Jul, 2025 1 commit
- Split the scheduler into multiple mixin classes to reduce the file size (#8483) · a4c3b121
  Lianmin Zheng authored Jul 29, 2025
  
  a4c3b121
28 Jul, 2025 1 commit

[PD] Fix abort_request for PD disaggregation (#8352) · 2fd5c704

Shangming Cai authored Jul 28, 2025


Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
Co-authored-by: ybyang <10629930+whybeyoung@users.noreply.github.com>

2fd5c704

27 Jul, 2025 1 commit
- [Bugfix] Prevent PD server crash from invalid grammar (#8062) · 22e00eeb
  Shangming Cai authored Jul 28, 2025
```
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
```
  22e00eeb
25 Jul, 2025 1 commit
- [P/D] Support ipv6 in P/D scenario (#7858) · 1b9cea5a
  Stepan Kargaltsev authored Jul 25, 2025
```
Co-authored-by: Shangming Cai <caishangming@linux.alibaba.com>
```
  1b9cea5a
19 Jul, 2025 1 commit
- [PD] Support non-MLA models PD different TP with DP attention (#7931) · 1403ea56
  Shangming Cai authored Jul 19, 2025
```
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
```
  1403ea56
13 Jul, 2025 2 commits
- SWA Prefix Cache (#7367) · 9379da77
  Hanming Lu authored Jul 13, 2025
```
Co-authored-by: Ying Sheng <sqy1415@gmail.com>
```
  9379da77
- Tiny fix mooncake log warning wrong output (#7952) · c46e069d
  fzyzcjy authored Jul 13, 2025
  
  c46e069d
12 Jul, 2025 1 commit
- Revert "[PD Disaggregation] replace transfer with batch transfer for better... · 880221bd
  fzyzcjy authored Jul 12, 2025
```
Revert "[PD Disaggregation] replace transfer with batch transfer for better performance (#7236)" (#7968)
```
  880221bd
11 Jul, 2025 1 commit
- [feature] kv transfer support of ascend npu (#7795) · 86044712
  ronnie_zheng authored Jul 11, 2025
```
Co-authored-by: liupeng <liupeng374@huawei.com>
```
  86044712
09 Jul, 2025 2 commits
- Remove unused imports (#7898) · f9df11ae
  almaslof authored Jul 09, 2025
  
  f9df11ae
- [PD] Add guidance for prefill bootstrap timeout (#7846) · 64c5907e
  Shangming Cai authored Jul 09, 2025
```
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
```
  64c5907e
05 Jul, 2025 2 commits
- DP Attention with Auto DeepEP Dispatch (#7222) · 8fc910db
  Cheng Wan authored Jul 05, 2025
  
  8fc910db
- [Fix] Alloc return type error (#7778) · af564774
  Caproni authored Jul 05, 2025
```
Signed-off-by: Capronir <839972205@qq.com>
```
  af564774
03 Jul, 2025 1 commit
- Fix num_tokens_pre_allocated in disaggregation log (#7714) · 1bebd315
  Ziming Huang authored Jul 03, 2025
  
  1bebd315
28 Jun, 2025 2 commits

[PD] Respect sampling_params.max_new_tokens when PD disaggregation is activated (#7598) · eb429b88
Shangming Cai authored Jun 28, 2025
```
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
```
eb429b88

Hybrid kv cache for LLaMA4 (#6563) · eb6c2c16

tarinkk authored Jun 27, 2025


Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
Co-authored-by: tarinkk <rt572@physics.rutger.edu>
Co-authored-by: tarinkk <rt572@rutgers.physics.edu>
Co-authored-by: Hanming Lu <69857889+hanming-lu@users.noreply.github.com>

eb6c2c16

26 Jun, 2025 2 commits
- [PD][NIXL] Set is_sorted=False to fix NIXL_ERR_NOT_FOUND (#7330) · bb9b608c
  Trevor Morris authored Jun 26, 2025
  
  bb9b608c
- [PD] Raise error for incompatible mooncake version and some minor fixes (#7527) · 5c214257
  Shangming Cai authored Jun 26, 2025
```
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
```
  5c214257
25 Jun, 2025 3 commits
- feat: add return hidden_states at async generation (#7507) · 20beb370
  eigen authored Jun 25, 2025
  
  20beb370
- [PD] Add different TP sizes support for no-MLA models (#6793) · e21aa1df
  Hongbo Xu authored Jun 25, 2025
```
Co-authored-by: shangmingc <csmthu@gmail.com>
Co-authored-by: Shangming Cai <caishangming@linux.alibaba.com>
```
  e21aa1df
- clean duplicate code (#7512) · afeed465
  linzhuo authored Jun 25, 2025
  
  afeed465