Adding cached KVs #266
Merged
Adding cached KVs #266
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
TODO: Update tests
|
TODO: update tests |
|
For visibility: updates to lit-parrot caching |
|
@carmocca what is the difference between |
|
I opened #313 to track it. I wouldn't try to merge them here. |
carmocca
reviewed
May 22, 2023
carmocca
approved these changes
May 22, 2023
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Outdated suggestions cannot be applied.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 PR adds the option to cache KVs for inference.
Cached KVs portion of splitting #240 into 2 PRs
main changes:
added KV caching
moved rope cache to the whole model from each attention layer
added mask cache to use for attention masking with cached kvs.
fix ops and tensors that would cause recompilation.
Similar to Lightning-AI/litgpt#51
Fixes #197
Fixes #309