[HTTP Server] Make model param optional in request (#13568)

2025-02-21 21:55:50 -08:00
parent 8c0dd3d4df
commit 0ffdf8ce0c
9 changed files with 61 additions and 18 deletions
--- a/vllm/entrypoints/openai/serving_completion.py
+++ b/vllm/entrypoints/openai/serving_completion.py
@@ -166,7 +166,7 @@ class OpenAIServingCompletion(OpenAIServing):

        result_generator = merge_async_iterators(*generators)

-        model_name = self.models.model_name(lora_request)
+        model_name = self._get_model_name(request.model, lora_request)
        num_prompts = len(engine_prompts)

        # Similar to the OpenAI API, when n != best_of, we do not stream the