update to explict RMSNorm#449
Open
mserranos wants to merge 5 commits into
Open
Conversation
JRosenkranz
reviewed
Jul 14, 2025
| emb_v = self.config.emb_dim // self.config.nheads | ||
|
|
||
| self.ln = LayerNormParameterized( | ||
| self.ln = RMSNorm( |
Collaborator
There was a problem hiding this comment.
I think these params need to be updated. The pytorch contract is:
RMSNorm(normalized_shape, eps=None, elementwise_affine=True, device=None, dtype=None)
Collaborator
Author
There was a problem hiding this comment.
well, I wish that we could switch directly to torch.nn.RMSNorm, but currently that gives some deeptools compilation problems. For the time being this is our "RMSNorm" which is similar to the torch.nn.RMSNorm but it is decomposed
differently.
Collaborator
Author
There was a problem hiding this comment.
maybe we should call this GraniteRMSNorm, this is not a general RMSNorm in the sense of torch.nn.RMSNorm
Signed-off-by: Mauricio J Serrano <mserrano@us.ibm.com>
Signed-off-by: Mauricio J Serrano <mserrano@us.ibm.com>
Signed-off-by: Mauricio J Serrano <mserrano@us.ibm.com>
Signed-off-by: kcirred <16872435+kcirred@users.noreply.github.com> Signed-off-by: Mauricio J Serrano <mserrano@us.ibm.com>
409d9e3 to
17b6583
Compare
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
We would like to clean up the code a little bit by switching to an explicit RMSNorm