Infinity Service</strong>: deploy end-to-end optimized inference pipelines for state of the art Transformers Models. </p> </li> <li> <p> <strong>Hardware Partner Program</strong>: access State of the Art hardware and hardware-specific machine learning optimization techniques for production performance. </p> </li> <li> <p> <strong>Inference Endpoints</strong>: easily deploy machine learning models on dedicated, secure and autoscaling infrastructure </p> </li> </ul> <p>