xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-05-18 10:46:58 +08:00
Code Issues Packages Projects Releases Wiki Activity

reuse old request when same lora is reloaded

Browse Source 
Signed-off-by: Jackmin801 <ongjackm@gmail.com>
This commit is contained in:
Jackmin801 2025-12-24 23:43:19 +00:00
parent 09dc7c690c
commit 3cce5bd947
1 changed files with 8 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
vllm/entrypoints/openai/serving_models.py
View File

@ -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(