[LoRA] Add support for pinning lora adapters in the LRU cache (#5603)

This commit is contained in:
rohithkrn
2024-06-21 15:42:46 -07:00
committed by GitHub
parent 7187507301
commit f5dda63eb5
13 changed files with 171 additions and 5 deletions

View File

@@ -1009,6 +1009,9 @@ class LLMEngine:
def list_loras(self) -> Set[int]:
return self.model_executor.list_loras()
def pin_lora(self, lora_id: int) -> bool:
return self.model_executor.pin_lora(lora_id)
def check_health(self) -> None:
self.model_executor.check_health()