Support unfixed kv heads number #1416
Merged
+84
−55
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
github-actions
bot
added
category: continuous batching
|
Please, fix failed tests for speculative decoding and prompt lookup - they are failed because of changes on continuous batching impl. Also, please update what is specific in decilm model so we need such changes? |
mangguo321
force-pushed
the
mang/fix_decilm-7b-instruct_failure
branch
from
d7dd723 to
db866ee
Compare
ilya-lavrenov
approved these changes
Dec 27, 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Outdated suggestions cannot be applied.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.
Fix decilm-7b-instruct benchmark test failure. The number heads per layer is not fixed in decilm-7b-instruct model, current code can not handle such case. JIRA ticket CVS-157864.