Commits · 8f783c1943af25e5bbccff628ba4385579b044e1 · change / sglang

17 Apr, 2025 2 commits

[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 13 commits
- Clean up imports (#5467) · 177320a5
  Lianmin Zheng authored Apr 16, 2025
  
  177320a5
- add multi-lora feature in README.md (#5463) · d7bc19a4
  Ying Sheng authored Apr 16, 2025
  
  d7bc19a4
- Update cutlass dependency. (#5447) · 85ec0440
  Elfie Guo authored Apr 15, 2025
  
  85ec0440
- [doc] Update benchmark_and_profiling.md (#5449) · 06a1656e
  Xiaoyu Zhang authored Apr 16, 2025
  
  06a1656e
- 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
- [Docs] Update start/install.md (#5398) · b64b88e7
  Michael Yao authored Apr 16, 2025
  
  b64b88e7
- Support BNB quantization for llama/mllama (#5038) · bc24205b
  ryang authored Apr 16, 2025
```
Co-authored-by: Yuhao Yang <yyh073@foxmail.com>
```
  bc24205b
- add attention backend supporting matrix in the doc (#5211) · 3efc8e2d
  mRSun15 authored Apr 15, 2025
```
Co-authored-by: Stefan He <hebiaobuaa@gmail.com>
```
  3efc8e2d
- Fix ignore_eos parameter when loading a chat template (#5264) · 27a009bb
  Chang Su authored Apr 15, 2025
  
  27a009bb
15 Apr, 2025 25 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
- BLackwell cutlass mla: Add check for bad page size/block num combinations (#5431) · e8f62b20
  Trevor Morris authored Apr 15, 2025
  
  e8f62b20
- fix: solve release issue (#5434) · 88defc4d
  Yineng Zhang authored Apr 15, 2025
  
  88defc4d
- chore: bump sgl-kernel v0.0.9.post1 (#5430) · 6f509d55
  Yineng Zhang authored Apr 15, 2025
  
  6f509d55
- bugfix: fix merge_state_v2 cuda graph (#5419) · 12ef7e3b
  DefTruth authored Apr 16, 2025
  
  12ef7e3b
- [minor] cleanup cmakelists.txt (#5420) · 838fa0f2
  Lianmin Zheng authored Apr 15, 2025
  
  838fa0f2
- [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
- [misc] fix ci flaky case (#5352) · f88f7e19
  JieXin Liang authored Apr 15, 2025
  
  f88f7e19
- 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
- chore: bump sgl-kernel 0.0.9 (#5400) · e940dc4f
  Yineng Zhang authored Apr 14, 2025
  
  e940dc4f
- kernel: support slightly faster merge_state_v2 cuda kernel (#5381) · 388e15c0
  DefTruth authored Apr 15, 2025
  
  388e15c0
- fix: update pr-test-sgl-kernel (#5399) · 11421a3f
  Yineng Zhang authored Apr 14, 2025
  
  11421a3f
- chore: upgrade DeepGEMM (#5395) · 6c41fcf0
  Yineng Zhang authored Apr 14, 2025
  
  6c41fcf0
- [fix/misc] remove duplicate row in deepseek v2 model (#5279) · ee9d6ca6
  Yangcheng Li authored Apr 15, 2025
  
  ee9d6ca6
- Add H20 dtype fp8_w8a8 shared experts fused MoE kernel tuning configs for DeepSeek V3/R1 (#5291) · 2dd64894
  Ximingwang-09 authored Apr 15, 2025
```
Co-authored-by: ximing.wxm <ximing.wxm@antgroup.com>
```
  2dd64894
- Add A800 shared experts fused MoE kernel tuning configs for DeepSeek V3/R1 (#5368) · 61e7c4dd
  lambert0312 authored Apr 15, 2025
  
  61e7c4dd
- minor clean up of sgl-kernel/CMakeLists.txt (#5393) · dae79444
  Lianmin Zheng authored Apr 14, 2025
  
  dae79444