Improve Llama.eval efficiency#1476
Merged
abetlen merged 2 commits intoabetlen:mainfrom May 24, 2024
thoughtp0lice:main
Merged
Conversation
thoughtp0lice
changed the title
Owner
|
@thoughtp0lice thank you, that's perfect! |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
In llama_cpp/llama.py, the eval function converts return value of
self._ctx.get_logits(), which is a CtypesArray, to list then copy it intoself.scores. Here the CtypesArray is directly converted to a numpy array which speeds up the conversion and copying. The speed-up is especially noticeable on smaller models with faster inference time.