Update README.md

README.md

@@ -29,22 +29,32 @@ pip install vllm --pre --extra-index-url https://wheels.vllm.ai/nightly
 ```Py
 from vllm import LLM, SamplingParams
 
-llm = LLM(model="pytorch/Phi-4-mini-instruct-float8dq", trust_remote_code=True)
-
-messages = [
-    {"role": "system", "content": "You are a helpful AI assistant."},
-    {"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"},
-    {"role": "assistant", "content": "Sure! Here are some ways to eat bananas and dragonfruits together: 1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey. 2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey."},
-    {"role": "user", "content": "What about solving an 2x + 3 = 7 equation?"},
+# Sample prompts.
+prompts = [
+    "Hello, my name is",
+    "The president of the United States is",
+    "The capital of France is",
+    "The future of AI is",
 ]
-
-sampling_params = SamplingParams(
-  max_tokens=500,
-  temperature=0.0,
-)
-
-output = llm.chat(messages=messages, sampling_params=sampling_params)
-print(output[0].outputs[0].text)
+# Create a sampling params object.
+sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
+
+
+if __name__ == '__main__':
+    # Create an LLM.
+    llm = LLM(model="pytorch/Phi-4-mini-instruct-float8dq")
+    # 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.
+    print("\nGenerated Outputs:\n" + "-" * 60)
+    for output in outputs:
+        prompt = output.prompt
+        generated_text = output.outputs[0].text
+        print(f"Prompt:    {prompt!r}")
+        print(f"Output:    {generated_text!r}")
+        print("-" * 60)
 ```
 
 ## Serving