diff --git a/vllm/config/model.py b/vllm/config/model.py index 9413810674..6db60cee50 100644 --- a/vllm/config/model.py +++ b/vllm/config/model.py @@ -584,6 +584,15 @@ class ModelConfig: architectures, self.runner_type, self.convert ) + if ( + is_pooling_model + and not is_generative_model + and self.runner_type in ("draft", "generate") + ): + raise ValueError( + f"Embedding models do not support `--runner {self.runner_type}`. " + "Use `--runner pooling` or `--runner auto` for embedding models." + ) if self.runner_type == "generate" and not is_generative_model: generate_converts = _RUNNER_CONVERTS["generate"] if self.convert_type not in generate_converts: