diff --git a/python/llm/src/ipex_llm/vllm/xpu/model_convert.py b/python/llm/src/ipex_llm/vllm/xpu/model_convert.py index 89a8fa67..d8ece358 100644 --- a/python/llm/src/ipex_llm/vllm/xpu/model_convert.py +++ b/python/llm/src/ipex_llm/vllm/xpu/model_convert.py @@ -89,7 +89,8 @@ def get_load_function(low_bit): ) if "qwen" in self.model_config.model.lower() or \ "baichuan" in self.model_config.model.lower() or \ - "glm" in self.model_config.model.lower(): + "codegeex4-all" in self.model_config.model.lower() or \ + "chatglm" in self.model_config.model.lower(): self.model.apply(padding_mlp) from ipex_llm import optimize_model import os