Files
podman/scripts/bench-lmstudio.py
2025-11-24 19:55:22 +01:00

8 lines
188 B
Python

import requests
import time
# Benchmark LLM inference
response = requests.post("http://localhost:1234/v1/completions", json={
"prompt": "Hello, how are you?",
"max_tokens": 100
})