minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[MUSA][9/N] Add FA3 attention backend support through MATE (MUSA AI Tensor Engine) (#22051)

Browse Source 
Co-authored-by: zhiguo.qin <zhiguo.qin@mthreads.com>
This commit is contained in:
ori
2026-04-10 14:18:39 -07:00
committed by GitHub
co-authored by zhiguo.qin
parent 6af34b95b6
commit f7a1740101
8 changed files with 958 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/pyproject_other.toml
+4 -1
View File
@@ -114,8 +114,11 @@ srt_musa = [
"sglang[runtime_common]",
"torch",
"torch_musa",
"torchada>=0.1.45",
"torchada>=0.1.48",
"mthreads-ml-py",
"mate",
"mate-deep_gemm",
"mate-flash-attention",
"numpy<2.0",
]