Skip to content

GitLab

Commit 04633c47 authored by zhuwenwen's avatar zhuwenwen
Browse files

fix awq index of qwen

parent 708d897e
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
vllm/model_executor/models/qwen.py
View file @ 04633c47
...@@ -350,7 +350,7 @@ class QWenLMHeadModel(nn.Module): ...@@ -350,7 +350,7 @@ class QWenLMHeadModel(nn.Module):
weight.data=weight.data.reshape(ori_shape[1],-1) weight.data=weight.data.reshape(ori_shape[1],-1)
if self.quant_method == "awq": if self.quant_method == "awq":
from lmslim import quant_ops as _ops from lmslim import quant_ops as _ops
lay_key_words = [ lay_key_words = [
"attn.c_attn.qweight", "attn.c_attn.qweight",
......
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