Import turbomind in gradio server only when it is needed (#303)

lmdeploy/serve/async_engine.py

@@ -6,7 +6,6 @@ import random
 from contextlib import contextmanager
 from typing import Literal, Optional
 
-from lmdeploy import turbomind as tm
 from lmdeploy.model import MODELS, BaseModel
 
 
@@ -30,6 +29,7 @@ class AsyncEngine:
     """
 
     def __init__(self, model_path, instance_num=32, tp=1) -> None:
+        from lmdeploy import turbomind as tm
         from lmdeploy.turbomind.tokenizer import Tokenizer
         tokenizer_model_path = osp.join(model_path, 'triton_models',
                                         'tokenizer')