[Feat] ESA supports asynchronous retrieval and loading. #199
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
wangwenxin0312
force-pushed
the
dev_esa_v2
branch
4 times, most recently
from
1f81086 to
8052026
Compare
wangwenxin0312
force-pushed
the
dev_esa_v2
branch
from
8052026 to
06563dc
Compare
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Outdated suggestions cannot be applied.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.
Purpose
What this PR does / why we need it?
Adds asynchronous retrieval and loading support to ESA with NfsStore adaptation, enabling sparse computation during the decode stage and improving tpot performance.
Modifications
Does this PR introduce any user-facing change?
unified-cache-management/ucm/ucm_sparse/retrieval: C++ implementation of retrievalunified-cache-management/ucm/ucm_sparse/esa.py: asynchronous implementation of Example Sparse Attention (ESA), works out of the boxTest
How was this patch tested?
Tested with the NFS connector, enabling the ESA feature.
