fix pre-commit formatting

Author: Bojun-Feng

doc/source/getting_started/using_xinference.rst

@@ -27,7 +27,7 @@ Starting the Supervisor
 On the server where you want to run the Xinference supervisor, run the following command:
 
 .. code-block:: bash
-  
+
   xinference-supervisor -H "${supervisor_host}"
 
 Replace ${supervisor_host} with the actual host of your supervisor server.
@@ -38,8 +38,7 @@ Starting the Workers
 On each of the other servers where you want to run Xinference workers, run the following command:
 
 .. code-block:: bash
-  
+
   xinference-worker -e "http://${supervisor_host}:9997"
 
 Once Xinference is running, an endpoint will be accessible for model management via CLI or Xinference client.
-

xinference/model/llm/__init__.py

@@ -43,8 +43,8 @@ def _install():
     from .pytorch.core import PytorchChatModel, PytorchModel
     from .pytorch.falcon import FalconPytorchChatModel, FalconPytorchModel
     from .pytorch.llama_2 import LlamaPytorchChatModel, LlamaPytorchModel
-    from .pytorch.vicuna import VicunaPytorchChatModel
     from .pytorch.rwkv import RWKVPilePytorchModel
+    from .pytorch.vicuna import VicunaPytorchChatModel
     from .vllm.core import VLLMChatModel, VLLMModel
 
     # register llm classes.

xinference/model/llm/pytorch/rwkv.py

@@ -39,7 +39,7 @@ def __init__(
 
     def _load_model(self, kwargs: dict):
         try:
-            from transformers import RwkvForCausalLM, AutoTokenizer
+            from transformers import AutoTokenizer, RwkvForCausalLM
         except ImportError:
             error_message = "Failed to import module 'transformers'"
             installation_guide = [
@@ -75,4 +75,3 @@ def match(
         if "generate" not in llm_family.model_ability:
             return False
         return True
-

xinference/model/llm/pytorch/utils.py

@@ -587,6 +587,7 @@ def generate_stream_chatglm(
 
     yield completion_chunk, completion_usage
 
+
 @torch.inference_mode()
 def generate_stream_rwkv(
     model,