Add partial RMSnorm "pRMSNorm" variation #153
Merged
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
This was described in the RMSNorm paper as being able to accomplish the same task as RMSNorm usually with only performing calculations on the first 6% of entries. This is because the average of the RMSNorm changes more slowly the more items are added, and the RMSNorm authors noted that the tokens they measured had around the same value.
Add variation of pRMSNorm that simply sets a max number of tokens to utilize for the RMSNorm normalization. This should be much easier to implement in hardware.
|
Looks good |
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Outdated suggestions cannot be applied.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 was described in the RMSNorm paper as being able to accomplish the same task as RMSNorm usually with only performing calculations on the first 6% of entries.
This is because the average of the RMSNorm changes more slowly the more items are added, and the RMSNorm authors noted that the tokens they measured had around the same value.