Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-09-18 16:54:33 +02:00
Code Issues Packages Projects Releases Wiki Activity

Remove redundant shape check

Browse Source
This commit is contained in:
Disty0
2025-05-29 14:58:00 +03:00
parent 14893b7617
commit 2351efb8f7
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/model_quant_sdnq.py
+1 -1
View File
@@ -327,7 +327,7 @@ def int8_matmul(
def quantized_linear_forward_fp8_matmul(self, input: torch.FloatTensor) -> torch.FloatTensor:
if input.shape[-1] % 16 != 0 or self.weight.shape[0] % 16 != 0 or self.weight.shape[1] % 16 != 0:
if self.weight.shape[0] % 16 != 0 or self.weight.shape[1] % 16 != 0:
return torch.nn.functional.linear(input, self.sdnq_decompressor(self.weight, skip_quantized_matmul=True), self.bias)
return fp8_matmul(input, self.weight, self.bias, self.sdnq_decompressor.scale)