Commits · 2c11f9c2eba40e922a0e5a6a4205cc37b17d9165 · change / sglang · GitLab

19 Apr, 2025 1 commit
- chore: upgrade sgl-kernel 0.0.9.post2 (#5540) · 2c11f9c2
  Yineng Zhang authored Apr 18, 2025
  
  2c11f9c2
18 Apr, 2025 11 commits
- Revert "Avoid computing lse in Ragged Prefill when there's no prefix.… (#5544) · a6f892e5
  Yineng Zhang authored Apr 18, 2025
  
  a6f892e5
- fix util import (#5542) · 08b518d5
  Yineng Zhang authored Apr 18, 2025
  
  08b518d5
- [Model] Adding Qwen3 and Qwen3MoE (#4693) · 4db463b1
  yhyang201 authored Apr 19, 2025
  
  4db463b1
- Avoid computing lse in Ragged Prefill when there's no prefix. (#5476) · bfa39224
  Wenxuan Tan authored Apr 18, 2025
```
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
```
  bfa39224
- fix bug of VLLM_AVAILABLE not defined (#5497) · e465b08d
  liwenju0 authored Apr 18, 2025
  
  e465b08d
- fix kimi vl running bug after rebase main (#5461) · bed05878
  Xiaoyu Zhang authored Apr 18, 2025
  
  bed05878
- use sglang_per_token_group_quant_fp8 from sgl-kernel instead of trion kernel (#5473) · b2a189dd
  strgrb authored Apr 18, 2025
```
Co-authored-by: Zhang Kaihong <zhangkaihong.zkh@alibaba-inc.com>
```
  b2a189dd
- Introduce moe_dense_tp_size to fix dense layer errors in DeepSeek V3 + 4x8xH100 (#4836) · 53dcf388
  fzyzcjy authored Apr 18, 2025
  
  53dcf388
- Configuration qwen2_moe.py - qkv_bias now in transformers (#5512) · 1effba4c
  Michael Feil authored Apr 17, 2025
  
  1effba4c
- Fix: fix the exception 'the memory capacity is unbalanced. Some GPUs … (#5426) · 27e9538a
  mlmz authored Apr 18, 2025
```
Co-authored-by: ocss884 <ocss.lin@gmail.com>
```
  27e9538a
- Fix: Incorrect parameters passed to forward_batch_generation (#5506) (#5511) · 211c7b31
  u4lr451 authored Apr 18, 2025
  
  211c7b31
17 Apr, 2025 8 commits
- [Bug fix] use correct func path in deepseek (#5496) · 06d0a3d9
  Xuchun Shang authored Apr 17, 2025
```
Signed-off-by: Xuchun Shang <xuchun.shang@linux.alibaba.com>
```
  06d0a3d9
- Refactor DeepSeek decoder layer branches (#5205) · 8beb356f
  fzyzcjy authored Apr 17, 2025
  
  8beb356f
- Enable local attention during decode (#5479) · c776234b
  Chang Su authored Apr 17, 2025
  
  c776234b
- Feat/support encoder model (like bert) (#4887) · 3bface15
  woodx authored Apr 17, 2025
  
  3bface15
- Deprecate enable-flashinfer-mla and enable-flashmla (#5480) · 6fb29ffd
  Baizhou Zhang authored Apr 17, 2025
  
  6fb29ffd
- Deprecate disable-mla (#5481) · 4fb05583
  Baizhou Zhang authored Apr 17, 2025
  
  4fb05583
- [Model Support] unsloth/Phi-4-mini bnb model (#4982) · 8f783c19
  eigen authored Apr 16, 2025
```
Co-authored-by: yhyang201 <yhyang201@gmail.com>
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
Co-authored-by: Chayenne <zhaochen20@outlook.com>
Co-authored-by: Yineng Zhang <me@zhyncs.com>
```
  8f783c19
- [verl] Modify the update_weights func to align with verl's resharding (#5345) · 90faf901
  BearBiscuit authored Apr 17, 2025
```
Co-authored-by: Chayenne <zhaochen20@outlook.com>
```
  90faf901
16 Apr, 2025 8 commits
- Clean up imports (#5467) · 177320a5
  Lianmin Zheng authored Apr 16, 2025
  
  177320a5
- Fix several minor issues in PD disaggregation (#5444) · 6aca5834
  Cheng Wan authored Apr 15, 2025
  
  6aca5834
- chore: bump v0.4.5.post1 (#5445) · 5b5c7237
  Yineng Zhang authored Apr 15, 2025
  
  5b5c7237
- Support MHA with chunked prefix cache for DeepSeek chunked prefill (#5113) · a42736bb
  Baizhou Zhang authored Apr 15, 2025
  
  a42736bb
- [Bug fix] need record start time in pd mode (#5425) · dd83e7e9
  ybyang authored Apr 16, 2025
  
  dd83e7e9
- [Minor] Move torch.compile patch to a better place (#5397) · 0769b14b
  Lianmin Zheng authored Apr 15, 2025
  
  0769b14b
- Support BNB quantization for llama/mllama (#5038) · bc24205b
  ryang authored Apr 16, 2025
```
Co-authored-by: Yuhao Yang <yyh073@foxmail.com>
```
  bc24205b
- Fix ignore_eos parameter when loading a chat template (#5264) · 27a009bb
  Chang Su authored Apr 15, 2025
  
  27a009bb
15 Apr, 2025 12 commits
- chore: upgrade sgl-kernel 0.0.9.post1 (#5436) · 8ec0bb7d
  Yineng Zhang authored Apr 15, 2025
  
  8ec0bb7d
- feat: update model_specific_adjustment (#5344) · fa909dc3
  Yineng Zhang authored Apr 15, 2025
```
Co-authored-by: hebiao064 <hebiaobuaa@gmail.com>
```
  fa909dc3
- [PD] Remove unused bootstrap param and fix port table type (#5423) · f1b3b75f
  shangmingc authored Apr 15, 2025
  
  f1b3b75f
- Distinguish bootstrap key only in decode server (#5422) · 33b16ad1
  Liangsheng Yin authored Apr 15, 2025
  
  33b16ad1
- [PD] Fix dynamic port support and MLA buffer for Mooncake (#5415) · ffde65a0
  shangmingc authored Apr 15, 2025
```
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
Co-authored-by: ybyang <ybyang7@iflytek.com>
```
  ffde65a0
- Fix broadcast use cuda device lead to memory capacity unbalanced (#5416) · 471650de
  lambert0312 authored Apr 15, 2025
  
  471650de
- Support dynamic connection and TP 16 (#5351) · d06a83fb
  Yuan Luo authored Apr 15, 2025
```
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
```
  d06a83fb
- [FIX] Fix concatenation error in capture_bs when open... · 5d134401
  Zhaoyang Hao authored Apr 15, 2025
```
[FIX] Fix concatenation error in capture_bs when open --disable-cuda-graph-padding and without MTP (#5412)
```
  5d134401
- Fix bench_serving with random-ids (#5214) · 3dfc6023
  Yuhong Guo authored Apr 15, 2025
  
  3dfc6023
- Tiny fix DeepseekScalingRotaryEmbedding always use forward_native (#5406) · 15e91d72
  fzyzcjy authored Apr 15, 2025
  
  15e91d72
- chore: upgrade sgl-kernel 0.0.9 (#5401) · 8aab7fdb
  Yineng Zhang authored Apr 14, 2025
  
  8aab7fdb
- [fix/misc] remove duplicate row in deepseek v2 model (#5279) · ee9d6ca6
  Yangcheng Li authored Apr 15, 2025
  
  ee9d6ca6