update offline_inference.py

examples/offline_inference.py

 from vllm import LLM, SamplingParams
 
-# Sample prompts.
-prompts = [
+if __name__ == '__main__':
+    # Sample prompts.
+    prompts = [
         "Hello, my name is",
         "The president of the United States is",
         "The capital of France is",
         "The future of AI is",
-]
-# Create a sampling params object.
-sampling_params = SamplingParams(temperature=0.8, top_p=0.95, max_tokens=16)
+    ]
+    # Create a sampling params object.
+    sampling_params = SamplingParams(temperature=0.8, top_p=0.95, max_tokens=16)
 
-# Create an LLM.
-llm = LLM(model="facebook/opt-125m",tensor_parallel_size=1, distributed_executor_backend="ray", dtype="float16",trust_remote_code=True, enforce_eager=True)
-# Generate texts from the prompts. The output is a list of RequestOutput objects
-# that contain the prompt, generated text, and other information.
-outputs = llm.generate(prompts, sampling_params)
-# Print the outputs.
-for output in outputs:
+    # Create an LLM.
+    llm = LLM(model="facebook/opt-125m",tensor_parallel_size=1, distributed_executor_backend="ray", dtype="float16",trust_remote_code=True, enforce_eager=True)
+    # Generate texts from the prompts. The output is a list of RequestOutput objects
+    # that contain the prompt, generated text, and other information.
+    outputs = llm.generate(prompts, sampling_params)
+    # Print the outputs.
+    for output in outputs:
         prompt = output.prompt
         generated_text = output.outputs[0].text
         print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
\ No newline at end of file