[KVCache] Add tree attention with paged cache support #17326
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
vinx13
force-pushed
the
feat/tree-attn
branch
2 times, most recently
from
0e0ad43 to
619fefd
Compare
vinx13
force-pushed
the
feat/tree-attn
branch
from
619fefd to
fe49099
Compare
MasterJH5574
approved these changes
Sep 3, 2024
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Outdated suggestions cannot be applied.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.
This adds support for tree attention with tokens in the kv cache. KVCache is now stateful w.r.t the tree state, multiple decoding rounds can be performed with tree mask and the accepted tokens can be committed at once at the end.
cc @MasterJH5574 @tqchen