From 3cce5bd9476d44dc00eb414bb6b61036585858ac Mon Sep 17 00:00:00 2001 From: Jackmin801 Date: Wed, 24 Dec 2025 23:43:19 +0000 Subject: [PATCH] reuse old request when same lora is reloaded Signed-off-by: Jackmin801 --- vllm/entrypoints/openai/serving_models.py | 21 ++++++++------------- 1 file changed, 8 insertions(+), 13 deletions(-) diff --git a/vllm/entrypoints/openai/serving_models.py b/vllm/entrypoints/openai/serving_models.py index 6b03fa72fc594..ede418f09937d 100644 --- a/vllm/entrypoints/openai/serving_models.py +++ b/vllm/entrypoints/openai/serving_models.py @@ -142,10 +142,14 @@ class OpenAIServingModels: return error_check_ret lora_path = request.lora_path - unique_id = self.lora_id_counter.inc(1) - lora_request = LoRARequest( - lora_name=lora_name, lora_int_id=unique_id, lora_path=lora_path - ) + if lora_name in self.lora_requests: + lora_request = self.lora_requests[lora_name] + lora_request.lora_path = lora_path + else: + unique_id = self.lora_id_counter.inc(1) + lora_request = LoRARequest( + lora_name=lora_name, lora_int_id=unique_id, lora_path=lora_path + ) if base_model_name is not None and self.is_base_model(base_model_name): lora_request.base_model_name = base_model_name @@ -197,15 +201,6 @@ class OpenAIServingModels: status_code=HTTPStatus.BAD_REQUEST, ) - # Check if the lora adapter with the given name already exists - if request.lora_name in self.lora_requests: - return create_error_response( - message=f"The lora adapter '{request.lora_name}' has already been " - "loaded.", - err_type="InvalidUserInput", - status_code=HTTPStatus.BAD_REQUEST, - ) - return None async def _check_unload_lora_adapter_request(