[RL] [KVCache] let cache transfer managers update key prefix after weight update and add unit tests#7083
Open
liyonghua0910 wants to merge 2 commits intoPaddlePaddle:developfrom
Open
Conversation
|
Thanks for your contribution! |
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## develop #7083 +/- ##
==========================================
Coverage ? 73.74%
==========================================
Files ? 402
Lines ? 56462
Branches ? 8909
==========================================
Hits ? 41637
Misses ? 11876
Partials ? 2949
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Motivation
This PR updates the mooncake
key_prefixduringupdate_weights.Previously,
key_prefixwas only refreshed inresume. To make cache metadata align with the new model version earlier, this PR adds one more refresh inupdate_weights, while keeping the existing refresh inresume.Modifications
EngineService._control_update_weights()update_weightshandler inCacheTransferManagerresumerefreshingkey_prefixupdate_weightsandresumepathsUsage or Command
No new API.
Behavior after this PR:
update_weightsrefresheskey_prefixresumealso refresheskey_prefixAccuracy Tests
N/A
Checklist