[fused_rmsnorm] Avoid conditional on dynamic stride #300
Conversation
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
facebook-github-bot
added
the
CLA Signed
This was referenced May 3, 2024
|
i think i abandoned this becuase even with this fix the PP tracer would not work due to other issues with the fused-rmsnorm custom op registration. did we figure out a solution there? or are we totally giving up on fused_rmsnorm and switching to compile? cc @lessw2020 |
|
abandoned |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Stack from ghstack (oldest at bottom):
The conditional expression forces evaluation of a symbolic quantity,
which is not a problem in eager but prevents tracing/export and blocks
using Pipeline Parallelism via tracing frontend.
Tensor.contiguous operator already handles returning
selfif thestriding of self is already contiguous.
Fixes pytorch/PiPPy#1108