Integrate ragged paged attn to pytorch/xla #8692
Merged
+433
−3
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
…ew3i/xla into integrate-ragged-paged-attn
vanbasten23
reviewed
Feb 10, 2025
vanbasten23
reviewed
Feb 10, 2025
vanbasten23
reviewed
Feb 10, 2025
vanbasten23
reviewed
Feb 10, 2025
vanbasten23
reviewed
Feb 10, 2025
vanbasten23
reviewed
Feb 10, 2025
|
LGTM. This is great. Thanks @bythew3i |
vanbasten23
approved these changes
Feb 12, 2025
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Outdated suggestions cannot be applied.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.
Note: the jax checkify in ragged paged attention kernel will insert several scalar refs to both inputs (end of prefetch) and outputs (begining of the original output). This affects how we re-construct xla.tpu_custom_call in with payload as we need take those scalars into account.
Tested:
python test/test_pallas.py -v -k PallasTest.test_ragged_paged_attention_wrapper