Tensor subclasses and PT2
Feb 24 2024
Length: 13 mins
Podcast

Failed to add items

Sorry, we are unable to add the item because your shopping cart is already at capacity.

Add to Cart failed.

Please try again later

Add to Wish List failed.

Please try again later

Remove from wishlist failed.

Please try again later

Adding to library failed

Please try again

Follow podcast failed

Please try again

Unfollow podcast failed

Please try again

Tensor subclasses and PT2

Listen for free

View show details

Summary
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.

Show more Show less

Show more Show less

What listeners say about Tensor subclasses and PT2

Average customer ratings

Reviews - Please select the tabs below to change the source of reviews.

Audible.com reviews

Amazon reviews

No Reviews are Available

Report a review on Amazon