🐛 Implement add_lora in old AsyncLLMEngine

Signed-off-by: Joe Runde <[email protected]>
vllm-project · Jan 3, 2025 · f6c940d · f6c940d
1 parent a8745c0
commit f6c940d
Showing 1 changed file with 4 additions and 0 deletions.
diff --git a/vllm/engine/async_llm_engine.py b/vllm/engine/async_llm_engine.py
@@ -1257,6 +1257,10 @@ async def stop_profile(self) -> None:
         else:
             self.engine.model_executor._run_workers("stop_profile")
 
+    async def add_lora(self, lora_request: LoRARequest) -> None:
+        """Load a new LoRA adapter into the engine for future requests."""
+        self.engine.add_lora(lora_request)
+
 
 # TODO(v1): Remove this class proxy when V1 goes default.
 if envs.VLLM_USE_V1: