[Bugfix] Fix VLLMNotFoundError when using LoRA adapter name in poolin… (#44410)

Signed-off-by: Ted Mostly <wanghenshui@qq.com>
This commit is contained in:
Ted Mostly
2026-06-04 02:22:03 +00:00
committed by GitHub
parent ceb0111a90
commit 0c1e6f63f5
2 changed files with 62 additions and 0 deletions
+1
View File
@@ -283,6 +283,7 @@ class PoolingServingBase(ABC):
request = ctx.request
if request.model in self.models.lora_requests:
ctx.lora_request = self.models.lora_requests[request.model]
return None
# Currently only support default modality specific loras
# if we have exactly one lora matched on the request.