Add multi_tensor_unscale_l2norm_cuda#1727
Merged
Merged
Conversation
Collaborator
|
We manually verified this PR and it worked. Please go ahead merging this PR. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR adds multi_tensor_unscale_l2norm_cuda, which is used to fuse gradient unscaling (with AMP) and L2 norm computation of the gradients.
To retain the original precision of the gradients (especially FP16), unscaling is only accounted for in the norm computation and is not applied to the gradients themselves.