del

scripts/README.md

@@ -107,78 +107,3 @@ python scripts/download_models.py
 - `api_client_test.log`: API client test results
 - `simple_usage_test.log`: Simple usage test results
 
-## Troubleshooting
-
-### Common Issues
-
-1. **Server fails to start**
-   - Check if port is available
-   - Verify model path is correct
-   - Check conda environment is activated
-
-2. **Health check fails**
-   - Server may need more time to start
-   - Check server logs for errors
-   - Verify port is not blocked
-
-3. **Import errors**
-   - Ensure vllm_omni is properly installed
-   - Check conda environment activation
-   - Verify all dependencies are installed
-
-4. **Model not found**
-   - Verify model path exists
-   - Check model directory structure
-   - Use absolute paths if needed
-
-### Debug Mode
-
-For detailed debugging, run tests with verbose output:
-
-```bash
-# Enable debug mode
-export VLLM_OMNI_DEBUG=1
-./scripts/test_serving.sh
-```
-
-## Integration with CI/CD
-
-These scripts can be integrated into CI/CD pipelines:
-
-```yaml
-# Example GitHub Actions workflow
-- name: Test vLLM-omni
-  run: |
-    conda activate vllm_omni
-    ./scripts/test_serving.sh
-```
-
-## Performance Expectations
-
-### Quick Test
-- **Duration**: ~30-60 seconds
-- **Memory**: ~2-4GB RAM
-- **CPU**: Moderate usage during model loading
-
-### Comprehensive Test
-- **Duration**: ~2-5 minutes
-- **Memory**: ~2-4GB RAM
-- **CPU**: Moderate usage during model loading and generation
-
-## Contributing
-
-When adding new tests:
-
-1. **Update test_serving.sh** for comprehensive testing
-2. **Update quick_test.sh** for essential functionality
-3. **Update this README** with new test descriptions
-4. **Test both scripts** before committing changes
-
-## Support
-
-For issues with testing scripts:
-
-1. Check the troubleshooting section above
-2. Review log files for detailed error information
-3. Ensure all prerequisites are met
-4. Test with different ports if port conflicts occur