With TorchScript, PyTorch provides ease-of-use and flexibility in eager mode, while seamlessly transitioning to graph mode for speed, optimization, and functionality in C++ runtime environments. In this talk, Michael Suo (Software Engineer, Meta AI) covers our journey enabling PyTorch eager mode execution in production at Meta. He'll also discuss the technical challenges involved in packaging, distributing, deploying, and executing Python PyTorch models, and how optimization and compilation technologies fit into a "Python-first" production world.