[Bugfix] Validate lora adapters to avoid crashing server (#11727)

Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>

vllm/v1/engine/async_llm.py

@@ -339,3 +339,7 @@ class AsyncLLM(EngineClient):
     @property
     def dead_error(self) -> BaseException:
         return Exception()  # TODO: implement
+
+    async def add_lora(self, lora_request: LoRARequest) -> None:
+        """Load a new LoRA adapter into the engine for future requests."""
+        raise NotImplementedError("LoRA not yet supported in V1")