Model Serving for Deep Learning - Hagay Lupesko, Amazon AI

Deep Learning has been delivering state of the art results across a growing number of problems and domains. Correspondingly, Deep Learning models are being deployed across a growing number of applications and use cases. In this talk, you will learn about what deploying deep neural networks to production mean, design considerations and challenges for model serving, and how the open source project Model Serving for Apache MXNet is designed to address these challenges.

Key Takeaways

  • Model Serving is key in productionizing deep learning models.
  • The challenges serving deep learning models at scale.
  • Model Server for MXNet is an open source framework to handle the undifferentiated heavy lifting.

Comments

No comments to display.