Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-09-20 01:31:13 +02:00
Code Issues Packages Projects Releases Wiki Activity

check pv_matmul_dtype = "enabled"

Browse Source
This commit is contained in:
Disty0
2026-07-15 19:46:11 +03:00
parent 7e8309f2d4
commit 943f9c2f57
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/sdnq/kernels/triton_atten.py
+1 -1
View File
@@ -203,7 +203,7 @@ def quantize_attn(
) -> tuple[torch.Tensor]:
if matmul_dtype in {"auto", "enabled", "uint8"}:
matmul_dtype = "int8"
if pv_matmul_dtype == "uint8":
if pv_matmul_dtype in {"enabled", "uint8"}:
pv_matmul_dtype = "int8"
if scale is None:
scale = q.shape[-1] ** -0.5