Unverified Commit 89f3feae authored by Casper's avatar Casper Committed by GitHub
Browse files

Fix init quant (#136)

parent eea08aa6
......@@ -332,7 +332,7 @@ class AwqQuantizer:
clear_memory()
if "attention_mask" in layer_kwargs.keys():
if layer_kwargs.get("attention_mask") is not None:
layer_kwargs["attention_mask"] = layer_kwargs["attention_mask"].to("cuda")
return modules, layer_kwargs, inps
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment