diff --git a/vllm/model_executor/model_loader.py b/vllm/model_executor/model_loader.py index 7fca7ebd..b18f9922 100644 --- a/vllm/model_executor/model_loader.py +++ b/vllm/model_executor/model_loader.py @@ -41,6 +41,7 @@ _MODEL_REGISTRY = { _MODEL_CLASSES_SUPPORT_QUANTIZATION = [ LlamaForCausalLM, MistralForCausalLM, + YiForCausalLM, ]