Commits · 935cda944b82d4828e9efb6606cd449afa4cd71c · change / sglang

"torchvision/csrc/vscode:/vscode.git/clone" did not exist on "dea1afbf5e69afb33d2501f5a129fc1085a474ce"

03 Mar, 2025 15 commits
- Misc clean up; Remove the support of jump forward (#4032) · 935cda94
  Lianmin Zheng authored Mar 03, 2025
  
  935cda94
- Reorganize python source files in sgl-kernel with multiple files (#4027) · 110e0066
  Lianmin Zheng authored Mar 03, 2025
  
  110e0066
- Reorganize c++ source files in sgl-kernel with multiple folders (#4025) · 6b45a21d
  Lianmin Zheng authored Mar 03, 2025
  
  6b45a21d
- Update metrics documentation (#3264) · a7000a76
  Yudi Xue authored Mar 03, 2025
  
  a7000a76
- remove cache configs in model definitions (#4031) · 1a8f995c
  Lianmin Zheng authored Mar 03, 2025
  
  1a8f995c
- Clean up custom allreduce (#4029) · a3ab768a
  Lianmin Zheng authored Mar 03, 2025
  
  a3ab768a
- Improve code styles (#4021) · 66301e12
  Lianmin Zheng authored Mar 03, 2025
  
  66301e12
- Support penalty in overlap mode; return logprob with chunked prefill; improve... · ac238727
  Lianmin Zheng authored Mar 03, 2025
```
Support penalty in overlap mode; return logprob with chunked prefill; improve benchmark scripts (#3988)
Co-authored-by: SangBin Cho <rkooo567@gmail.com>
Co-authored-by: dhou-xai <dhou@x.ai>
Co-authored-by: Hanming Lu <hanming_lu@berkeley.edu>
```
  ac238727
- Optimize Triton Kernel of Group GEMM in DeepGEMM Benchmark (#4014) · 0194948f
  Stefan He authored Mar 02, 2025
  
  0194948f
- Fix nightly-test CI (#3826) · b4d34cd3
  yinfan98 authored Mar 03, 2025
  
  b4d34cd3
- Add examples to token-in-token-out for LLM (#4010) · 728e175f
  Chayenne authored Mar 02, 2025
  
  728e175f
- Revert "Add fast decode plan for flashinfer mla" (#4008) · 9e1014cf
  Lianmin Zheng authored Mar 02, 2025
  
  9e1014cf
- Add fast decode plan for flashinfer mla (#3987) · fa561067
  Baizhou Zhang authored Mar 02, 2025
  
  fa561067
- [feat] add small vocab table for eagle's draft model[1]. (#3822) · 7fbab730
  Zhousx authored Mar 03, 2025
```
Co-authored-by: Achazwl <323163497@qq.com>
Co-authored-by: Chayenne <zhaochen20@outlook.com>
```
  7fbab730
- Add Benchmark for DeepGEMM Group GEMM (#3993) · b7e274f2
  Stefan He authored Mar 02, 2025
  
  b7e274f2
02 Mar, 2025 7 commits
- Enable custom AR for AMD GPUs and maintain it in sgl-kernel (#3406) · 9cf40772
  Hubert Lu authored Mar 02, 2025
  
  9cf40772
- Add accuracy test for TP torch compile (#3994) · d3fe9bae
  Ke Bao authored Mar 03, 2025
  
  d3fe9bae
- Fix all gather torch compile (#3992) · 00ce7e31
  Ke Bao authored Mar 02, 2025
```
Co-authored-by: yizhang2077 <1109276519@qq.com>
```
  00ce7e31
- fix typo in deep gemm benchmarking(#3991) · 50f28f65
  Xiaoyu Zhang authored Mar 02, 2025
  
  50f28f65
- add deepgemm and sglang fp8 block-wise gemm benchmark (#3893) · 90a55e25
  Xiaoyu Zhang authored Mar 02, 2025
  
  90a55e25
- Update CODEOWNERS (#3989) · 407e2b92
  Lianmin Zheng authored Mar 01, 2025
  
  407e2b92
- Refactor: Move return_hidden_states to the generate input (#3985) · 40782f05
  Qiaolin Yu authored Mar 01, 2025
```
Co-authored-by: Beichen-Ma <mabeichen12@gmail.com>
```
  40782f05
01 Mar, 2025 8 commits
- Revert "[MOE] enable efficient moe_alignment multi-blocks execution (3x~6x)" (#3982) · 18bb216c
  Chayenne authored Feb 28, 2025
  
  18bb216c
- Docs: add special warning to engine docs (#3979) · 6b859e7d
  Chayenne authored Feb 28, 2025
  
  6b859e7d
- rename FunctionCallReqInput to ParseFunctionCallReq (#3976) · 930da877
  Chayenne authored Feb 28, 2025
  
  930da877
- Docs: Add redline to highlight main process (#3977) · 3f8a4414
  Chayenne authored Feb 28, 2025
  
  3f8a4414
- Docs: add type hint to smapling parameters (#3975) · aceb4201
  Chayenne authored Feb 28, 2025
  
  aceb4201
- [Feature]Support ragged prefill in flashinfer mla backend (#3967) · 90a4b7d9
  Baizhou Zhang authored Feb 28, 2025
```
Co-authored-by: Yineng Zhang <me@zhyncs.com>
Co-authored-by: pankajroark <pankajroark@users.noreply.github.com>
```
  90a4b7d9
- update flashinfer-python version · f3b99f73
  Yineng Zhang authored Feb 28, 2025
  
  f3b99f73
- Update cutlass dependency (#3966) · 9e74ee91
  Elfie Guo authored Feb 28, 2025
  
  9e74ee91
28 Feb, 2025 8 commits
- Remove unused imports from rocm mla kernel. (#3963) · 77a6c9d2
  Chaitanya Sri Krishna Lolla authored Feb 28, 2025
  
  77a6c9d2
- [Feature] SPMD for SGLang + Verl (#3852) · e3e0bc50
  fzyzcjy authored Mar 01, 2025
  
  e3e0bc50
- [Feature] integrate Structural Tag in xgrammar backend for function calling (#3566) · bac414ab
  mlmz authored Feb 28, 2025
```
Co-authored-by: shuaills <shishuaiuoe@gmail.com>
```
  bac414ab
- [Bugfix] Fix tokenizer_manager not getting 400 when req is too long (#3678) · eec3f6d1
  Chang Su authored Feb 27, 2025
```
Co-authored-by: voidxb <unkown>
```
  eec3f6d1
- set a strict sgl-kernel version (#3950) · 90bc26a8
  Chayenne authored Feb 27, 2025
  
  90bc26a8
- Fix bench_serving not recognizing OPENAI_API_KEY (#3870) · ec0a72c2
  Kebe authored Feb 28, 2025
```
Signed-off-by: Kebe <mail@kebe7jun.com>
```
  ec0a72c2
- [MOE] enable efficient moe_alignment multi-blocks execution (3x~6x) (#3613) · 1c96fa86
  yiakwy-xpu-ml-framework-team authored Feb 28, 2025
  
  1c96fa86
- [feat] Add Vertex AI compatible prediction route for /generate (#3866) · bc20e93f
  KCFindstr authored Feb 27, 2025
  
  bc20e93f
27 Feb, 2025 2 commits
- Fix the doc link for sampling params (#3861) · d3887852
  Qiaolin Yu authored Feb 27, 2025
  
  d3887852
- upgrade flashinfer v0.2.2.post1 (#3934) · 564bdf29
  Yineng Zhang authored Feb 27, 2025
  
  564bdf29