[Core] [Frontend] Priority scheduling for embeddings and in the OpenAI-API (#8965)
This commit is contained in:
@@ -148,6 +148,7 @@ class OpenAIServingEmbedding(OpenAIServing):
|
||||
pooling_params,
|
||||
request_id_item,
|
||||
lora_request=lora_request,
|
||||
priority=request.priority,
|
||||
)
|
||||
|
||||
generators.append(generator)
|
||||
|
||||
Reference in New Issue
Block a user