[Frontend] [Core] Add Tensorizer support for V1, LoRA adapter serialization and deserialization (#17926)

Signed-off-by: Sanger Steel <sangersteel@gmail.com>

vllm/v1/worker/gpu_worker.py

@@ -31,6 +31,7 @@ from vllm.v1.worker.worker_base import WorkerBase
 logger = init_logger(__name__)
 
 if TYPE_CHECKING:
+    from vllm.model_executor.model_loader.tensorizer import TensorizerConfig
     from vllm.v1.core.sched.output import SchedulerOutput
 
 
@@ -326,6 +327,13 @@ class Worker(WorkerBase):
             max_size=max_size,
         )
 
+    def save_tensorized_model(
+        self,
+        tensorizer_config: "TensorizerConfig",
+    ) -> None:
+        self.model_runner.save_tensorized_model(
+            tensorizer_config=tensorizer_config, )
+
 
 def init_worker_distributed_environment(
     vllm_config: VllmConfig,