Fix an edge case issue when storing output in the paged attention.#8431
Merged
vanbasten23 merged 4 commits intomasterfrom Dec 5, 2024
Merged
Fix an edge case issue when storing output in the paged attention.#8431vanbasten23 merged 4 commits intomasterfrom
vanbasten23 merged 4 commits intomasterfrom
Conversation
Liyang90
approved these changes
Dec 4, 2024
Collaborator
Author
|
Thanks for the review, Liyang! |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fix an edge case for the condition to run
def store_to_output()in the internal flash attention.(1) If kv_len=512, kv_seq_len_per_kv_compute_blk=256, then last kv_blk_idx that we need to store_to_output is 1.
(2) If kv_len=513, kv_seq_len_per_kv_compute_blk=256, then last kv_blk_idx that we need to store_to_output is 2.
Without the fix, the case (1) would fail.
Test plan:
python pytorch/xla/test/test_tpu_paged_attention_kernel.py PagedAttentionKernelTest.test_paged_attention_store_to_output_correctly