Files
turboquant/benchmarks/run_benchmarks.py

76 lines
2.5 KiB
Python

import json
import time
import requests
import os
from typing import List, Dict
# ═══════════════════════════════════════════
# TURBOQUANT BENCHMARKING SUITE (Issue #16)
# ═══════════════════════════════════════════
# This script runs a standardized set of prompts against the local inference
# engine (Ollama) and logs the results. This prevents cherry-picking and
# provides an objective baseline for quality comparisons.
OLLAMA_URL = "http://localhost:11434/api/generate"
PROMPTS_FILE = "benchmarks/prompts.json"
RESULTS_FILE = f"benchmarks/results_{int(time.time())}.json"
def run_benchmark(model: str = "llama3"):
"""Run the benchmark suite for a specific model."""
if not os.path.exists(PROMPTS_FILE):
print(f"Error: {PROMPTS_FILE} not found.")
return
with open(PROMPTS_FILE, 'r') as f:
prompts = json.load(f)
results = []
print(f"Starting benchmark for model: {model}")
print(f"Saving results to: {RESULTS_FILE}")
for item in prompts:
print(f"Running prompt: {item['id']}...")
start_time = time.time()
try:
response = requests.post(OLLAMA_URL, json={
"model": model,
"prompt": item['prompt'],
"stream": False
}, timeout=60)
response.raise_for_status()
data = response.json()
end_time = time.time()
results.append({
"id": item['id'],
"prompt": item['prompt'],
"response": data.get("response"),
"latency": end_time - start_time,
"tokens_per_second": data.get("eval_count", 0) / (data.get("eval_duration", 1) / 1e9) if data.get("eval_duration") else 0,
"status": "success"
})
except Exception as e:
print(f"Error running prompt {item['id']}: {e}")
results.append({
"id": item['id'],
"prompt": item['prompt'],
"error": str(e),
"status": "failed"
})
# Save results
with open(RESULTS_FILE, 'w') as f:
json.dump({
"model": model,
"timestamp": time.time(),
"results": results
}, f, indent=2)
print("Benchmark complete.")
if __name__ == "__main__":
# Default to llama3 for testing
run_benchmark("llama3")