From ba590105bf17b0226e63a3eb92e3e24a9649fc0d Mon Sep 17 00:00:00 2001 From: Robert Shaw <114415538+robertgshaw2-neuralmagic@users.noreply.github.com> Date: Tue, 25 Jun 2024 21:20:30 -0400 Subject: [PATCH] Update loader.py --- vllm/model_executor/model_loader/loader.py | 1 + 1 file changed, 1 insertion(+) diff --git a/vllm/model_executor/model_loader/loader.py b/vllm/model_executor/model_loader/loader.py index d5d9a49480550..11f5758797916 100644 --- a/vllm/model_executor/model_loader/loader.py +++ b/vllm/model_executor/model_loader/loader.py @@ -61,6 +61,7 @@ def _get_quantization_config( f"{model_config.dtype} is not supported for quantization " f"method {model_config.quantization}. Supported dtypes: " f"{supported_dtypes}") + return quant_config elif model_config.sparsity is not None: