Support layernorm recompute for fused hstu layer#59
Merged
shijieliu merged 4 commits intoNVIDIA:mainfrom Jun 9, 2025
Merged
Conversation
Collaborator
Author
|
please track CI status. |
shijieliu
reviewed
Jun 5, 2025
Collaborator
Author
|
Updated CI |
shijieliu
approved these changes
Jun 9, 2025
3 tasks
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
This PR addresses #6 . Now only input layer norm is recomputed, which incurs slight ~1% perf drop in backward on A100-PCIe-80G given dim_per_heads=128, num_heads=4,seqlen=4096, batchsize=32, embedding_dim=512.
Checklist