Add infer_vllm.py

infer_vllm.py

+from vllm import LLM, SamplingParams
+
+if __name__ == '__main__':
+    # Sample prompts.
+    prompts = [
+        "I believe the meaning of life is",
+    ]
+    # Create a sampling params object.
+    sampling_params = SamplingParams(temperature=0, top_p=0.95, max_tokens=24)
+
+    # Create an LLM.
+    llm = LLM(model="checkpoint/miniCPM-bf16",trust_remote_code=True, dtype="float16", 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}")