Bump FlashInfer to 0.6.15 and revert regressions (#31502)

Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>
This commit is contained in:
Mohammad Miadh Angkad
2026-07-17 00:50:12 -07:00
committed by GitHub
co-authored by Brayden Zhong
parent e835512303
commit d67aa05697
7 changed files with 20 additions and 15 deletions
+1 -1
View File
@@ -31,7 +31,7 @@ dependencies = [
"einops",
"fastapi",
"flash-attn-4==4.0.0b15",
"flashinfer_python[cu13]==0.6.14", # keep it aligned with jit-cache version in Dockerfile
"flashinfer_python[cu13]==0.6.15", # keep it aligned with jit-cache version in Dockerfile
"gguf",
"humming-kernels[cu13]==0.1.10",
"interegular",