update offline_inference.py

examples/offline_inference.py

@@ -9,10 +9,10 @@ if __name__ == '__main__':
         "The future of AI is",
     ]
     # Create a sampling params object.
-    sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
+    sampling_params = SamplingParams(temperature=0.8, top_p=0.95, max_tokens=16)
 
     # Create an LLM.
-    llm = LLM(model="facebook/opt-125m",trust_remote_code=True, dtype="float16", enforce_eager=True)
+    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)