Tensor subclasses and PT2 Podcast By cover art

Tensor subclasses and PT2

Tensor subclasses and PT2

Listen for free

View show details

About this listen

 Tensor subclasses allow you to add extend PyTorch with new types of tensors without having to write any C++. They have been used to implement DTensor, FP8, Nested Jagged Tensor and Complex Tensor. Recent work by Brian Hirsh means that we can compile tensor subclasses in PT2, eliminating their overhead. The basic mechanism by which this compilation works is a desugaring process in AOTAutograd. There are some complications involving views, dynamic shapes and tangent metadata mismatch.
adbl_web_global_use_to_activate_webcro805_stickypopup
No reviews yet