[KVCache] Attention func accepting over-padded qkv and output NDArray #17401
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
This PR enhances the `AttentionWithFusedQKV` function of `PagedKVCache` so that it can now accept input `qkv_data` and `o_data` that have padding along the sequence dimension. We introduce this enhancement to allow more flexibility for the caller of PagedKVCache to decide whether to pad the input qkv/o NDArrays or not.
tqchen
approved these changes
Sep 22, 2024
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Outdated suggestions cannot be applied.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.
This PR enhances the
AttentionWithFusedQKVfunction ofPagedKVCacheso that it can now accept inputqkv_dataando_datathat have padding along the sequence dimension.We introduce this enhancement to allow more flexibility for the caller of PagedKVCache to decide whether to pad the input qkv/o NDArrays or not.