Commits · bdde237562ebd70944aef94873a96f765578b048 · change / sglang

"vscode:/vscode.git/clone" did not exist on "266db2066daa510c88c050a0f70433fcb78e6c51"

14 Apr, 2025 7 commits
- [perf] experimental enhance fp8 per-tensor quant (#5370) · bdde2375
  JieXin Liang authored Apr 15, 2025
  
  bdde2375
- [PD Bug] fix MLA get_contiguous_buf_infos error (#5384) · e9fc2ac7
  ybyang authored Apr 14, 2025
  
  e9fc2ac7
- Fix PD disaggregation bugs (#5326) · 44afde82
  Liangsheng Yin authored Apr 14, 2025
  
  44afde82
- Support for Qwen2.5-VL Model in bitsandbytes Format (#5003) · 072df753
  yhyang201 authored Apr 14, 2025
  
  072df753
- Fix DeepSeek DP Attention + torch compile (#5367) · defede50
  fzyzcjy authored Apr 14, 2025
```
Co-authored-by: ispobock <ispobaoke@163.com>
```
  defede50
- Free metadata_buffer_index after transfer finished (#5364) · fc728719
  Yongtong Wu authored Apr 14, 2025
  
  fc728719
- Free metadata_buffer_index after transfer finished (#5364) · 14e8bd88
  Yongtong Wu authored Apr 14, 2025
  
  14e8bd88
13 Apr, 2025 12 commits
- [DeepEP] Reduce routed scaling overhead (#5277) · adca585b
  yulei authored Apr 14, 2025
```
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
```
  adca585b
- feat: update experiment_runner (#5360) · 39d90449
  Yineng Zhang authored Apr 13, 2025
  
  39d90449
- fix #5322 (#5359) · 39e41138
  Yineng Zhang authored Apr 13, 2025
  
  39e41138
- fix MLATokenToKVPoolHost get_size_per_token bug (#5161) · 5fbafbb8
  huangtingwei authored Apr 14, 2025
```
Co-authored-by: AniZpZ <zhuangsen.zp@antgroup.com>
```
  5fbafbb8
- [PD] Add transfer backend abstraction (#5328) · a9499885
  Byron Hsu authored Apr 13, 2025
  
  a9499885
- Fix typo: infight -> inflight (#5357) · f7655790
  Liangsheng Yin authored Apr 14, 2025
  
  f7655790
- chore: upgrade sgl-kernel 0.0.8.post3 (#5342) · f58b929a
  Yineng Zhang authored Apr 13, 2025
  
  f58b929a
- docs: update adoption and sponsorship list with Oracle (#5343) · c1270aab
  Yineng Zhang authored Apr 12, 2025
  
  c1270aab
- Fix: Ensure tensors for dist.broadcast match NCCL backend device (#5322) · 8311b07f
  mlmz authored Apr 13, 2025
  
  8311b07f
- misc: update sagemaker Dockerfile (#5341) · c1380257
  Yineng Zhang authored Apr 12, 2025
  
  c1380257
- feat: adapt merge_state (#5337) · b62e7e99
  Yineng Zhang authored Apr 12, 2025
  
  b62e7e99
- fix: determine if flashinfer is installed (#5336) · 7d3b7c87
  Yineng Zhang authored Apr 12, 2025
  
  7d3b7c87
12 Apr, 2025 19 commits
- ci: update release node (#5333) · 75015bb6
  Yineng Zhang authored Apr 12, 2025
  
  75015bb6
- chore: bump sgl-kernel v0.0.8.post3 (#5332) · b371f7cd
  Yineng Zhang authored Apr 12, 2025
  
  b371f7cd
- fix: solve cu118 issue for cutlass mla (#5331) · 812e82f3
  Yineng Zhang authored Apr 12, 2025
  
  812e82f3
- [Feat] Add sparse attn to sgl-kernel (#5327) · 4879e50c
  PGFLMG authored Apr 13, 2025
  
  4879e50c
- Support server based rollout in Verlengine (#4848) · bc92107b
  tianlian yi authored Apr 13, 2025
```
Co-authored-by: Jin Pan <jpan236@wisc.edu>
Co-authored-by: Chayenne <zhaochen20@outlook.com>
Co-authored-by: Jinn <47354855+jhinpan@users.noreply.github.com>
```
  bc92107b
- refine fused_moe tuning docs (#5294) · 3e4794aa
  Xiaoyu Zhang authored Apr 13, 2025
  
  3e4794aa
- Delete python/sglang/srt/layers/moe/fused_moe_triton/configs/E=257,N=… (#5321) · 690ec205
  Xiaoyu Zhang authored Apr 13, 2025
  
  690ec205
- Fix: docs/backend/structured_outputs.ipynb (#4884) · 2074a2e6
  thyecust authored Apr 12, 2025
  
  2074a2e6
- feat: use fa3 mla by default on hopper (#5210) · 57de7c6b
  Yineng Zhang authored Apr 12, 2025
```
Co-authored-by: yundai424 <yundai424@gmail.com>
Co-authored-by: hebiao064 <hebiaobuaa@gmail.com>
```
  57de7c6b
- chore: bump sgl-kernel v0.0.8.post2 (#5317) · 115ae2e7
  Yineng Zhang authored Apr 11, 2025
  
  115ae2e7
- Fix fa3 window size setup (#5316) · aea98512
  Qingquan Song authored Apr 11, 2025
  
  aea98512
- Add flash_attn_varlen_func to sgl-kernel (#5315) · e4155e96
  Baizhou Zhang authored Apr 11, 2025
  
  e4155e96
- Fix w8a8_int8 model shared experts fusion load weights error (#5120) · 1b1b47a9
  lambert0312 authored Apr 12, 2025
  
  1b1b47a9
- update variable naming and comments for rocm (#5299) · 3c9740d2
  Zhaoyi Li authored Apr 12, 2025
  
  3c9740d2
- misc: cleanup 3rdparty (#5311) · 2eb55770
  Yineng Zhang authored Apr 11, 2025
  
  2eb55770
- Blackwell Cutlass MLA kernel (#5142) · f65b8d5c
  Trevor Morris authored Apr 11, 2025
  
  f65b8d5c
- Adjust ci test threshold (#5271) · 5ad05719
  Ke Bao authored Apr 12, 2025
  
  5ad05719
- [VLM] Adopt fast image processor by default (#5065) · 34ef6c81
  Mick authored Apr 12, 2025
  
  34ef6c81
- fix: use deepgemm only on hopper (#5310) · 61172091
  Yineng Zhang authored Apr 11, 2025
  
  61172091
11 Apr, 2025 2 commits
- fix: update flash attn (#5308) · 4f288113
  Yineng Zhang authored Apr 11, 2025
  
  4f288113
- fix: remove cublas_grouped_gemm (#5307) · 136b8e6a
  Yineng Zhang authored Apr 11, 2025
  
  136b8e6a