[BugFix] gemma loading after quantization or LoRA. (#3553)

vllm/model_executor/models/gemma.py

@@ -340,6 +340,10 @@ class GemmaForCausalLM(nn.Module):
                 weight_loader(param, loaded_weight, shard_id)
                 break
             else:
+                # lm_head is not used in vllm as it is tied with embed_token.
+                # To prevent errors, skip loading lm_head.weight.
+                if "lm_head.weight" in name:
+                    continue
                 # Skip loading extra bias for GPTQ models.
                 if name.endswith(".bias") and name not in params_dict:
                     continue