
Episode 479: Luis Ceze on the Apache TVM Machine Learning Compiler
Software Engineering Radio - the podcast for professional software developers
00:00
TvM: A Compiler That Takes in a Model and Gives You Talket Architecture
T v m, in some sense, is a compiler that takes in a model and then gives you talket architecture. Traditionally, compilers have this whole concept of having a front end and a back end. So can you talk about what t v m does in that context? Like as a classical compilation, let' say tht you have a moto in intenser flow. Yu. Cannot have a modo in a generic form called onyx. That's is been wrong for some time, and now it's keeps getting better and better.
Transcript
Play full episode