Commits · 01dd39bac1b5e73f609e59edf7f107d1ca044edc · change / sglang

"torchvision/transforms/v2/_auto_augment.py" did not exist on "54a2d4e8f7a4568823532d4342f6ba13e7339dce"

18 May, 2025 15 commits
- refactor: minor refactors regarding multimodal processing (#6187) · 01dd39ba
  Mick authored May 18, 2025
  
  01dd39ba
- Do not use FA3 for mistral (#6379) · b3f3d610
  Lianmin Zheng authored May 17, 2025
  
  b3f3d610
- chore: upgrade sgl-kernel v0.1.3 (#6377) · f07c6a00
  Yineng Zhang authored May 17, 2025
  
  f07c6a00
- Fix CI tests (#6362) · 4bb816d4
  Lianmin Zheng authored May 17, 2025
  
  4bb816d4
- [Fix Chat API] add request id for chat/completion for tracing (#6364) · c250939e
  ybyang authored May 18, 2025
  
  c250939e
- fix: allow `launch_dummy_health_check_server` to start inside of running asyncio loop (#6330) · b6909aa2
  ishandhanani authored May 17, 2025
  
  b6909aa2
- Add expert distribution APIs for engine (#6290) · f8728357
  fzyzcjy authored May 18, 2025
  
  f8728357
- Reland tiny refactor DefaultModelLoader.Source (#6041) · 73187152
  fzyzcjy authored May 18, 2025
  
  73187152
- Fix expert distribution recorder and profiler command stuck forever (#6284) · 40865665
  fzyzcjy authored May 18, 2025
  
  40865665
- Support custom DeepEP tuning config (#6257) · fd08c048
  fzyzcjy authored May 18, 2025
  
  fd08c048
- Tiny refactor bench_serving to extract RequestFuncOutput.init_new (#6108) · 26ebb849
  fzyzcjy authored May 18, 2025
  
  26ebb849
- Tiny refactor bench_serving to improve extensibility (#6134) · 02973cd9
  fzyzcjy authored May 18, 2025
  
  02973cd9
- Support outputing details for bench_serving (#6107) · 6d95a35a
  fzyzcjy authored May 18, 2025
  
  6d95a35a
- Fix stop_profile does not wait for finishing (#4741) · 01d2838c
  fzyzcjy authored May 18, 2025
  
  01d2838c
- [fix] illegal memory in _fwd_kernel_ep_scatter_2 and _fwd_kernel_ep_gather (#6348) · e3b8a722
  xutizhou authored May 18, 2025
  
  e3b8a722
17 May, 2025 9 commits
- Use monotonic clock for interval measurement (#6211) · 3cf1473a
  Lifu Huang authored May 17, 2025
```
Signed-off-by: Lifu Huang <lifu.hlf@gmail.com>
```
  3cf1473a
- Speed up when having padding tokens in DeepEP (#6175) · 27168308
  fzyzcjy authored May 18, 2025
  
  27168308
- [router] Add /list_workers endpoint to router (#6366) · e3bed74a
  Zilin Zhu authored May 18, 2025
  
  e3bed74a
- docs: Update the MD files (#6373) · e9ef39d2
  Vincent Zhong authored May 17, 2025
```
Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>
```
  e9ef39d2
- perf: Optimize local attention memory allocation in FlashAttentionBackend (#6356) · 205d5cb4
  Chang Su authored May 17, 2025
  
  205d5cb4
- chore: bump sgl-kernel v0.1.3 (#6368) · 3d7f7a43
  Yineng Zhang authored May 17, 2025
  
  3d7f7a43
- Minor code cleanup refactor for DeepSeek models (#6324) · 2df9d40a
  fzyzcjy authored May 17, 2025
  
  2df9d40a
- Fix one wasted kernel in DeepSeek and minor refactor (#6316) · 8dc191f2
  fzyzcjy authored May 17, 2025
  
  8dc191f2
- model(vlm): mistral 3.1 (#5099) · 64825b83
  Kiv Chen authored May 16, 2025
```
Co-authored-by: KivenChen <sleigh-queue-0y@icloud.com>
```
  64825b83
16 May, 2025 9 commits
- docs: update readme (#6361) · 69748d08
  Yineng Zhang authored May 16, 2025
  
  69748d08
- Fix amd ci (#6360) · dcc0a456
  Lianmin Zheng authored May 16, 2025
  
  dcc0a456
- [Minor] cleanup unused imports (#6358) · c2b7ddca
  Lianmin Zheng authored May 16, 2025
  
  c2b7ddca
- Update CODEOWNERS (#6359) · abebd939
  Lianmin Zheng authored May 16, 2025
  
  abebd939
- feat: add dp attention support for Qwen 2/3 MoE models, fixes #6088 (#6121) · 4bd2952a
  Fr4nk1in authored May 17, 2025
```
Co-authored-by: King.Zevin <zevin@mail.ustc.edu.cn>
Co-authored-by: Yi Zhang <1109276519@qq.com>
```
  4bd2952a
- [2/2] Add python wrapper for CUTLASS FP8 Blockscale MoE Kernel. (#5694) · 6fc93575
  Elfie Guo authored May 16, 2025
  
  6fc93575
- [Fix] Improve dependencies for Blackwell image (#6334) · 839fb31e
  Baizhou Zhang authored May 16, 2025
  
  839fb31e
- Support precomputed multimodal features for Qwen-VL and Gemma3 models. (#6136) · f19a9204
  Yury Sulsky authored May 16, 2025
```
Co-authored-by: Yury Sulsky <ysulsky@tesla.com>
```
  f19a9204
- Upgrade CUTLASS 4.0 (#6336) · c23a7072
  Elfie Guo authored May 15, 2025
```
Co-authored-by: zhyncs <me@zhyncs.com>
```
  c23a7072
15 May, 2025 7 commits
- Minor improvements of TokenizerManager / health check (#6327) · e07a6977
  Lianmin Zheng authored May 15, 2025
  
  e07a6977
- Fix lora bench (#6302) · cd8d4b9d
  Qiaolin Yu authored May 15, 2025
  
  cd8d4b9d
- Reduce MoE memory usage (#6147) · f194e14f
  fzyzcjy authored May 16, 2025
  
  f194e14f
- Fix gpu mem check on CPU (#6317) · cfc9f9ab
  Yi Liu authored May 16, 2025
```
Signed-off-by: yiliu30 <yi4.liu@intel.com>
```
  cfc9f9ab
- Add fp8 gemm kernel for CPU in sgl-kernel and add gemm UT (#6216) · fb4959b2
  Chunyuan WU authored May 16, 2025
```
Co-authored-by: YanbingJiang <yanbing.jiang@intel.com>
Co-authored-by: mingfeima <mingfei.ma@intel.com>
```
  fb4959b2
- [misc] remove redundant platform codes (#6298) · 9a405274
  JieXin Liang authored May 15, 2025
  
  9a405274
- [Feat] Support FlashMLA backend with MTP and FP8 KV cache (#6109) · 2e4babdb
  quinnrong94 authored May 15, 2025
```
Co-authored-by: Yingyi <yingyihuang2000@outlook.com>
Co-authored-by: neiltian <neiltian@tencent.com>
Co-authored-by: lukec <118525388+sleepcoo@users.noreply.github.com>
Co-authored-by: kexueyu <kexueyu@tencent.com>
Co-authored-by: vincentmeng <vincentmeng@tencent.com>
Co-authored-by: pengmeng <pengmeng@tencent.com>
```
  2e4babdb