[Core] [Frontend] Priority scheduling for embeddings and in the OpenAI-API (#8965)

2024-10-01 11:58:06 +02:00
parent 1fe0a4264a
commit 35bd215168
8 changed files with 53 additions and 5 deletions
--- a/vllm/entrypoints/openai/serving_completion.py
+++ b/vllm/entrypoints/openai/serving_completion.py
@@ -148,6 +148,7 @@ class OpenAIServingCompletion(OpenAIServing):
                    lora_request=lora_request,
                    prompt_adapter_request=prompt_adapter_request,
                    trace_headers=trace_headers,
+                    priority=request.priority,
                )

                generators.append(generator)