deploy/verify_api_ready.py

import requests
import json
import time

def verify_vllm():
    url = "http://localhost:8001/v1/models"
    print(f"Checking vLLM status at {url}...")
    
    start_time = time.time()
    while True:
        try:
            response = requests.get(url, timeout=5)
            if response.status_code == 200:
                models = [m["id"] for m in response.json()["data"]]
                if "iquest-coder-40b-loop" in models:
                    print("\n✅ API is READY with model: iquest-coder-40b-loop")
                    print(json.dumps(response.json(), indent=2))
                    break
        except Exception:
            pass
        
        elapsed = int(time.time() - start_time)
        print(f"\rStill loading weights... ({elapsed}s elapsed)", end="", flush=True)
        time.sleep(5)
        
        if elapsed > 300: # 5 minute timeout
            print("\n❌ Timeout waiting for vLLM to start.")
            break

if __name__ == "__main__":
    verify_vllm()