[llama] Update kv cache to have read/write functions #280
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
rsuderman
force-pushed
the
kv_cache_refactor
branch
from
36c54aa to
7d87c28
Compare
rsuderman
force-pushed
the
kv_cache_refactor
branch
2 times, most recently
from
372d8f1 to
3444f6d
Compare
sogartar
requested changes
Oct 21, 2024
|
We needed this so badly, thanks Rob |
rsuderman
force-pushed
the
kv_cache_refactor
branch
from
3444f6d to
9bd8a53
Compare
Made the interfaces of both caches line up. This allows us to interface with the caches via their utility functions instead of modifying the model behavior. Some roughness still exists in their parameters but the irrelevant details are ignored for each implementation. Need to still add some slicing / ignoring on the page ids to make more flexible.
rsuderman
force-pushed
the
kv_cache_refactor
branch
from
9bd8a53 to
9b9b088
Compare
sogartar
approved these changes
Oct 28, 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Outdated suggestions cannot be applied.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.
Made the interfaces of both caches line up. This allows us to interface with the caches via their utility functions instead of modifying the model behavior. Some roughness still exists in their parameters but the irrelevant details are ignored for each implementation.
Need to still add some slicing / ignoring on the page ids to make more flexible.