Update README.md

README.md

@@ -106,7 +106,7 @@ with torch.no_grad():
     print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```
 
-使用 VLLM后端进行推理:
+使用 vLLM后端进行推理:
 
 ```python
 from transformers import AutoTokenizer
@@ -116,9 +116,6 @@ from vllm import LLM, SamplingParams
 # max_model_len, tp_size = 1048576, 4
 
 # GLM-4-9B-Chat
-from transformers import AutoTokenizer
-from vllm import LLM, SamplingParams
-
 # 如果遇见 OOM 现象，建议减少max_model_len，或者增加tp_size
 max_model_len, tp_size = 131072, 1
 model_name = "THUDM/glm-4-9b-chat"