xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-07-28 13:54:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

use new request object so that errors dont update request

Browse Source 
Signed-off-by: Jackmin801 <ongjackm@gmail.com>
This commit is contained in:
Jackmin801 2025-12-25 00:22:35 +00:00
parent 0616d19f8b
commit 0718a782ee
1 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
vllm/entrypoints/openai/serving_models.py
View File

@ -142,14 +142,14 @@ class OpenAIServingModels:
return error_check_ret return error_check_ret
lora_path = request.lora_path lora_path = request.lora_path
if lora_name in self.lora_requests: lora_int_id = (
lora_request = self.lora_requests[lora_name] self.lora_requests[lora_name].lora_int_id
lora_request.lora_path = lora_path if lora_name in self.lora_requests
else: else self.lora_id_counter.inc(1)
unique_id = self.lora_id_counter.inc(1) )
lora_request = LoRARequest( lora_request = LoRARequest(
lora_name=lora_name, lora_int_id=unique_id, lora_path=lora_path lora_name=lora_name, lora_int_id=lora_int_id, lora_path=lora_path
) )
if base_model_name is not None and self.is_base_model(base_model_name): if base_model_name is not None and self.is_base_model(base_model_name):
lora_request.base_model_name = base_model_name lora_request.base_model_name = base_model_name