Add GPTQ support for Gemma (#3200)

vllm/model_executor/models/gemma.py

@@ -325,11 +325,17 @@ class GemmaForCausalLM(nn.Module):
                 if shard_name not in name:
                     continue
                 name = name.replace(shard_name, param_name)
+                # Skip loading extra bias for GPTQ models.
+                if name.endswith(".bias") and name not in params_dict:
+                    continue
                 param = params_dict[name]
                 weight_loader = param.weight_loader
                 weight_loader(param, loaded_weight, shard_id)
                 break
             else:
+                # Skip loading extra bias for GPTQ models.
+                if name.endswith(".bias") and name not in params_dict:
+                    continue
                 # GemmaRMSNorm is different from Llama's in that it multiplies
                 # (1 + weight) to the output, instead of just weight.
                 if "norm.weight" in name: