Sync from v0.13

examples/offline_inference/simple_profiling.py

@@ -0,0 +1,52 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+import time
+
+from vllm import LLM, SamplingParams
+
+# 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)
+
+
+def main():
+    # Create an LLM.
+    llm = LLM(
+        model="facebook/opt-125m",
+        tensor_parallel_size=1,
+        profiler_config={
+            "profiler": "torch",
+            "torch_profiler_dir": "./vllm_profile",
+        },
+    )
+
+    llm.start_profile()
+
+    # 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)
+
+    llm.stop_profile()
+
+    # Print the outputs.
+    print("-" * 50)
+    for output in outputs:
+        prompt = output.prompt
+        generated_text = output.outputs[0].text
+        print(f"Prompt: {prompt!r}\nGenerated text: {generated_text!r}")
+        print("-" * 50)
+
+    # Add a buffer to wait for profiler in the background process
+    # (in case MP is on) to finish writing profiling output.
+    time.sleep(10)
+
+
+if __name__ == "__main__":
+    main()