Update README.md

README.md

@@ -70,7 +70,7 @@ prompts = tokenizer.apply_chat_template(messages, tokenize=False)
 
 llm = LLM(model=model_id, tensor_parallel_size=number_gpus)
 
-outputs = llm.generate(prompt, sampling_params)
+outputs = llm.generate(prompts, sampling_params)
 
 generated_text = outputs[0].outputs[0].text
 print(generated_text)