Bump FlashInfer to 0.6.17 and remove Kimi K3 workarounds (#33997)

This commit is contained in:
Mohammad Miadh Angkad
2026-08-12 02:17:26 -07:00
committed by GitHub
parent 2d76d537e5
commit 00e57d74f0
19 changed files with 84 additions and 6496 deletions
+1 -1
View File
@@ -33,7 +33,7 @@ dependencies = [
"einops",
"fastapi",
"flash-attn-4>=4.0.0b18",
"flashinfer_python[cu13]==0.6.15.post1", # keep it aligned with jit-cache version in Dockerfile
"flashinfer_python[cu13]==0.6.17", # keep it aligned with jit-cache version in Dockerfile
"gguf",
"humming-kernels[cu13]==0.1.10",
"interegular",