Skip to content

GitLab

Unverified Commit e497b8ae authored by Jee Jee Li's avatar Jee Jee Li Committed by GitHub
Browse files

[Misc] Skip loading extra bias for Qwen2-MOE GPTQ models (#8329)

parent 94144e72
Hide whitespace changes
Inline Side-by-side
Showing with 8 additions and 2 deletions
vllm/model_executor/models/qwen2_moe.py
View file @ e497b8ae
......@@ -469,7 +469,8 @@ class Qwen2MoeForCausalLM(nn.Module):
continue
name = name.replace(weight_name, param_name)
# Skip loading extra bias for GPTQ models.
if name.endswith(".bias") and name not in params_dict:
if ((name.endswith(".bias") or name.endswith("_bias"))
and name not in params_dict):
continue
# Skip layers on other devices.
if is_pp_missing_parameter(name, self):
......@@ -490,6 +491,10 @@ class Qwen2MoeForCausalLM(nn.Module):
# Skip layers on other devices.
if is_pp_missing_parameter(name, self):
continue
# Skip loading extra bias for GPTQ models.
if ((name.endswith(".bias") or name.endswith("_bias"))
and name not in params_dict):
continue
param = params_dict[name]
weight_loader = param.weight_loader
weight_loader(param,
......@@ -500,7 +505,8 @@ class Qwen2MoeForCausalLM(nn.Module):
break
else:
# Skip loading extra bias for GPTQ models.
if name.endswith(".bias") and name not in params_dict:
if ((name.endswith(".bias") or name.endswith("_bias"))
and name not in params_dict):
continue
# Skip layers on other devices.
if is_pp_missing_parameter(name, self):
......
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