Commits · 76fa2d152c112688b9c9450cb1fcb10a0f85207b · change / sglang

"vscode:/vscode.git/clone" did not exist on "cb83f2f87346b2bb86007a7593cefaa3eee95385"

05 Feb, 2025 3 commits
- Fix lora flashinfer import bug on ROCM (#3312) · 76fa2d15
  Baizhou Zhang authored Feb 05, 2025
  
  76fa2d15
- [ROCm] Logic to decide whether to used manually unrolled kernel. (#3306) · 7ab84948
  Wen-Heng (Jack) Chung authored Feb 04, 2025
  
  7ab84948
- Use forward_cuda to execute custom op for hip platform (#3305) · 4885b908
  kk authored Feb 05, 2025
```
Co-authored-by: wunhuang <wunhuang@amd.com>
```
  4885b908
04 Feb, 2025 7 commits
- [ROCm] Manually unroll _w8a8_block_fp8_matmul kernel on AMD GPU. (#3299) · c2723a42
  Wen-Heng (Jack) Chung authored Feb 04, 2025
  
  c2723a42
- [ROCm] Add tuning configs for AMD Radeon Graphics. (#3294) · c7256ca8
  Wen-Heng (Jack) Chung authored Feb 04, 2025
  
  c7256ca8
- update flashinfer install index url (#3293) · 6186a8f8
  Yineng Zhang authored Feb 05, 2025
  
  6186a8f8
- Update Triton decode backend interface (#3292) · a07364cc
  Ke Bao authored Feb 04, 2025
  
  a07364cc
- ROCm: sgl-kernel enablement starting with sgl_moe_align_block (#3287) · 2c1a695f
  HAI authored Feb 04, 2025
  
  2c1a695f
- upgrade flashinfer v0.2.0.post2 (#3288) · d39899e8
  Yineng Zhang authored Feb 04, 2025
```
Co-authored-by: pankajroark <pankajroark@users.noreply.github.com>
```
  d39899e8
- [Feature] Define backends and add Triton backend for Lora (#3161) · 70817a7e
  Baizhou Zhang authored Feb 03, 2025
```
Co-authored-by: Ying Sheng <sqy1415@gmail.com>
```
  70817a7e
03 Feb, 2025 8 commits
- Update server args doc (#3273) · 7b5a3741
  simveit authored Feb 04, 2025
```
Co-authored-by: Shi Shuai <126407087+shuaills@users.noreply.github.com>
```
  7b5a3741
- add Atlas Cloud for Adoption and Sponsorship (#3276) · 4b6f62e2
  Yineng Zhang authored Feb 04, 2025
  
  4b6f62e2
- add Nebius for Adoption and Sponsorship (#3274) · 897e2e25
  Yineng Zhang authored Feb 04, 2025
  
  897e2e25
- adding Triton configs for DeepSeekV3 on Blackwell (#3272) · d54cee14
  kushanam authored Feb 03, 2025
  
  d54cee14
- add copyright for sgl-kernel (#3270) · 00fa7d04
  Yineng Zhang authored Feb 03, 2025
  
  00fa7d04
- refactor EAGLE 2 (#3269) · 013021b6
  Yineng Zhang authored Feb 03, 2025
```
Co-authored-by: Ying Sheng <sqy1415@gmail.com>
Co-authored-by: merrymercy <lianminzheng@gmail.com>
Co-authored-by: Ying1123 <sqy1415@gmail.com>
```
  013021b6
- optimize test_fused_moe style (#3268) · 3c8ac78d
  Xiaoyu Zhang authored Feb 03, 2025
  
  3c8ac78d
- Add a Doc about guide on nvidia jetson #3182 (#3205) · 455bfe8d
  Liangjun Song authored Feb 03, 2025
```
Co-authored-by: Shi Shuai <126407087+shuaills@users.noreply.github.com>
Co-authored-by: zhaochenyang20 <zhaochen20@outlook.com>
```
  455bfe8d
02 Feb, 2025 5 commits
- Bug: Fix min_p sampling crash when using flashinfer backend (#3207) · 28b0a62b
  zifeitong authored Feb 02, 2025
```
Co-authored-by: zhaochenyang20 <zhaochen20@outlook.com>
```
  28b0a62b
- ROCm: bump 6.3.0 (#3259) · 566d61d9
  HAI authored Feb 02, 2025
  
  566d61d9
- Docs: Update accuracy evaluation (#3261) · 55f5fc68
  Chayenne authored Feb 02, 2025
  
  55f5fc68
- docs/accuracy evaluation (#3114) · c27c378a
  simveit authored Feb 02, 2025
```
Co-authored-by: Shi Shuai <126407087+shuaills@users.noreply.github.com>
Co-authored-by: zhaochenyang20 <zhaochen20@outlook.com>
```
  c27c378a
- Tune paged attention parameters for AMD GPU. (#3255) · d9eb9358
  Wen-Heng (Jack) Chung authored Feb 01, 2025
  
  d9eb9358
01 Feb, 2025 7 commits
- use srt VocabParallelEmbedding (#3252) · 959dca4f
  Yineng Zhang authored Feb 01, 2025
  
  959dca4f
- Update README · f2b3a318
  Yineng Zhang authored Feb 01, 2025
  
  f2b3a318
- add contact us in README (#3251) · ad674097
  Yineng Zhang authored Feb 01, 2025
  
  ad674097
- support QuickGELU (#3250) · 8db776f0
  Yineng Zhang authored Feb 01, 2025
  
  8db776f0
- update and simplify CustomOp (#3249) · 4eb4b401
  Yineng Zhang authored Feb 01, 2025
  
  4eb4b401
- update ENV to ROCm dockers (#3248) · 17dbf976
  HAI authored Feb 01, 2025
  
  17dbf976
- Add test for fp8 torch compile (#3246) · 53179026
  Ke Bao authored Feb 01, 2025
  
  53179026
31 Jan, 2025 10 commits
- [Docs] Add more details to profiling docs (#3221) · d7c0b32f
  Wenxuan Tan authored Jan 31, 2025
  
  d7c0b32f
- add tuning block wise fp8 (#3242) · 7b020cca
  Yineng Zhang authored Feb 01, 2025
```
Co-authored-by: HandH1998 <007aabbcc411@gmail.com>
```
  7b020cca
- update cutlass dependency (#3240) · 7876279e
  Yineng Zhang authored Feb 01, 2025
  
  7876279e
- update sgl-kernel version for sglang (#3238) · 34e405e0
  Yineng Zhang authored Feb 01, 2025
  
  34e405e0
- Optimize MoE topk with torch compile (#3236) · 1ebe1d6d
  Ke Bao authored Feb 01, 2025
  
  1ebe1d6d
- compatible with flashinfer v0.2 (#3235) · 7811bfda
  Yineng Zhang authored Feb 01, 2025
  
  7811bfda
- Docs: Quick fix for Speculative_decoding doc (#3228) · 656f7fc1
  Jhin authored Jan 31, 2025
```
Co-authored-by: Chayenne <zhaochenyang@ucla.edu>
Co-authored-by: Chayenne <zhaochen20@outlook.com>
```
  656f7fc1
- chore: bump v0.4.2.post1 (#3233) · cf0f7eaf
  Yineng Zhang authored Jan 31, 2025
  
  cf0f7eaf
- support 12.5 CUDA runtime (#3231) · b49d6d0f
  Yineng Zhang authored Jan 31, 2025
  
  b49d6d0f
- Fix block wise fp8 torch compile (#3232) · c02e3139
  Ke Bao authored Jan 31, 2025
  
  c02e3139