| |
| """ |
| Test script to verify deployment fallback mechanisms work correctly. |
| """ |
|
|
| import sys |
| import logging |
|
|
| logging.basicConfig(level=logging.INFO) |
| logger = logging.getLogger(__name__) |
|
|
| def test_quantization_detection(): |
| """Test quantization detection logic without actual model loading.""" |
| |
| |
| from backend_service import get_quantization_config |
| |
| test_cases = [ |
| |
| ("microsoft/DialoGPT-medium", None, "Standard model, no quantization"), |
| ("deepseek-ai/DeepSeek-R1-0528-Qwen3-8B", None, "Standard model, no quantization"), |
| |
| |
| ("unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit", "quantized", "4-bit quantized model"), |
| ("unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF", "quantized", "GGUF quantized model"), |
| ("something-4bit-test", "quantized", "Generic 4-bit model"), |
| ("test-bnb-model", "quantized", "BitsAndBytes model"), |
| ] |
| |
| results = [] |
| |
| logger.info("🧪 Testing quantization detection logic...") |
| logger.info("="*60) |
| |
| for model_name, expected_type, description in test_cases: |
| logger.info(f"\n📝 Testing: {model_name}") |
| logger.info(f" Expected: {description}") |
| |
| try: |
| quant_config = get_quantization_config(model_name) |
| |
| if expected_type is None: |
| |
| if quant_config is None: |
| logger.info(f"✅ PASS: No quantization detected (as expected)") |
| results.append((model_name, "PASS", "Correctly detected standard model")) |
| else: |
| logger.error(f"❌ FAIL: Unexpected quantization config: {quant_config}") |
| results.append((model_name, "FAIL", f"Unexpected quantization: {quant_config}")) |
| else: |
| |
| if quant_config is not None: |
| logger.info(f"✅ PASS: Quantization detected: {quant_config}") |
| results.append((model_name, "PASS", f"Correctly detected quantization: {quant_config}")) |
| else: |
| logger.error(f"❌ FAIL: Expected quantization but got None") |
| results.append((model_name, "FAIL", "Expected quantization but got None")) |
| |
| except Exception as e: |
| logger.error(f"❌ ERROR: Exception during test: {e}") |
| results.append((model_name, "ERROR", str(e))) |
| |
| |
| logger.info("\n" + "="*60) |
| logger.info("📊 QUANTIZATION DETECTION TEST SUMMARY") |
| logger.info("="*60) |
| |
| pass_count = 0 |
| for model_name, status, details in results: |
| if status == "PASS": |
| status_emoji = "✅" |
| pass_count += 1 |
| elif status == "FAIL": |
| status_emoji = "❌" |
| else: |
| status_emoji = "⚠️" |
| |
| logger.info(f"{status_emoji} {model_name}: {status}") |
| if status != "PASS": |
| logger.info(f" Details: {details}") |
| |
| total_count = len(results) |
| logger.info(f"\n📈 Results: {pass_count}/{total_count} tests passed") |
| |
| if pass_count == total_count: |
| logger.info("🎉 All quantization detection tests passed!") |
| return True |
| else: |
| logger.warning("⚠️ Some quantization detection tests failed") |
| return False |
|
|
| def test_imports(): |
| """Test that we can import required modules.""" |
| |
| logger.info("🧪 Testing imports...") |
| |
| try: |
| from backend_service import get_quantization_config |
| logger.info("✅ Successfully imported get_quantization_config") |
| |
| |
| from transformers import AutoTokenizer, AutoModelForCausalLM |
| logger.info("✅ Successfully imported transformers") |
| |
| |
| try: |
| from transformers import BitsAndBytesConfig |
| logger.info("✅ BitsAndBytesConfig import successful") |
| except ImportError as e: |
| logger.info(f"📝 BitsAndBytesConfig import failed (expected in some environments): {e}") |
| |
| return True |
| |
| except Exception as e: |
| logger.error(f"❌ Import test failed: {e}") |
| return False |
|
|
| if __name__ == "__main__": |
| logger.info("🚀 Starting deployment fallback mechanism tests...") |
| |
| |
| import_success = test_imports() |
| if not import_success: |
| logger.error("❌ Import tests failed, cannot continue") |
| sys.exit(1) |
| |
| |
| quant_success = test_quantization_detection() |
| |
| if quant_success: |
| logger.info("\n🎉 All deployment fallback tests passed!") |
| logger.info("💡 Your deployment should handle quantized models gracefully") |
| sys.exit(0) |
| else: |
| logger.error("\n❌ Some tests failed") |
| sys.exit(1) |
|
|
