[V1] LoRA - Enable Serving Usecase (#12883)

Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>

vllm/v1/worker/gpu_worker.py

@@ -15,6 +15,7 @@ from vllm.distributed import (ensure_model_parallel_initialized,
                               init_distributed_environment,
                               set_custom_all_reduce)
 from vllm.logger import init_logger
+from vllm.lora.request import LoRARequest
 from vllm.model_executor import set_random_seed
 from vllm.platforms import current_platform
 from vllm.utils import GiB_bytes
@@ -234,6 +235,9 @@ class Worker(WorkerBase):
         else:
             self.profiler.stop()
 
+    def add_lora(self, lora_request: LoRARequest) -> bool:
+        return self.model_runner.add_lora(lora_request)
+
     def check_health(self) -> None:
         # worker will always be healthy as long as it's running.
         return

vllm/v1/worker/lora_model_runner_mixin.py

@@ -127,3 +127,8 @@ class LoRAModelRunnerMixin:
 
             # __exit__ code
             self.lora_manager.remove_all_adapters()
+
+    def add_lora(self, lora_request: LoRARequest) -> bool:
+        if not self.lora_manager:
+            raise RuntimeError("LoRA is not enabled.")
+        return self.lora_manager.add_adapter(lora_request)