Bugfixes surrounding torch dtypes and QOL updates for torch #53
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
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Outdated suggestions cannot be applied.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 does the following:
Bugfixes the conflicting torch dtypes in the attention computation by casting the returned key and values from the kv cache to the input types. This matches the JAX implementation where key, values are stored in fp32 and fp16 respectively post ROPE. (thanks @tensorqt for bringing this up) (should also close Torch doesn't work on mac. #50)
qol fixes surrounding
torch_main.pycleaning up imports and setting up prompt testing similar tomain.pyFixes changes from Bugfix to varentropy calculation #17 being overwritten