TriePagedAttentionCache - 2 #628
Closed
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
20 tasks
renxida
force-pushed
the
trie-2
branch
2 times, most recently
from
3d42b83 to
74adaab
Compare
|
Replaced by #632 |
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Outdated suggestions cannot be applied.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.
See an earlier draft of this PR at #600
Instead of using a radix tree, a block trie is more appropriate for our paged attention. We can always add back the one feature that distinguishes a radix tree from this implementation (merging tree nodes on long un-branching paths)
This PR depends on #608 and #565 and should not be reviewed until they are merged.