Adapt Splash Attention from TorchPrime #8911
Merged
Conversation
This file contains 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
|
Looks like some comments still need to be addressed -- LMK whenever I should TAL! |
Yes, I am working on getting rid of the |
tengyifei
approved these changes
Apr 10, 2025
|
Oh, interesting that the test failed for the cache miss count. Looks like the HLO cache can be reused between test functions. |
|
Hi @tengyifei , I created issue #8963 to track the hashing issue. Will follow up in a separate PR for the fix. |
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Outdated suggestions cannot be applied.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.
Adapt the PR AI-Hypercomputer/torchprime#145 from TorchPrime into PTXLA. Also simplified the code to use jit hashing from #8878.
In addition, fix a small bug in xla_builder.call_jax when the input arg contains both None and other hashable types in sequence.