We built BentoML on a little known framework called Starlette (which we discovered is the same framework that FastAPI is built off of) for a couple reasons:
1. It provides performance primitives like async endpoints and basic HTTP functionality
2. It isn’t opinionated about validation, compute or scaling (which all need special attention for ML systems)
https://l.bentoml.com/breaking-up-with-flask-and-fastapi
1. It provides performance primitives like async endpoints and basic HTTP functionality
2. It isn’t opinionated about validation, compute or scaling (which all need special attention for ML systems)
https://l.bentoml.com/breaking-up-with-flask-and-fastapi