Process separate q/k/v weights in MHA converter #1020
Closed
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
Summary: ATT. The converter was not ready for the `not self._qkv_same_embed_dim` case [here](/~https://github.com/pytorch/pytorch/blob/80ed3e9ccdaab20814b4156611a19043aaaaef03/torch/nn/modules/activation.py#L1074) with separate q/k/v weights. Here we cover this case. Intenral: This causes a failure in the AIT lowering of the IGCTR MC model. See the post: https://fb.workplace.com/groups/gpuinference/permalink/2872581106223872/ . Differential Revision: D61155566
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D61155566 |
|
This pull request has been merged in 7b41778. |
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Outdated suggestions cannot be applied.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.
Summary:
ATT. The converter was not ready for the
not self._qkv_same_embed_dimcase here with separate q/k/v weights. Here we cover this case.Intenral:
This causes a failure in the AIT lowering of the IGCTR MC model. See the post: https://fb.workplace.com/groups/gpuinference/permalink/2872581106223872/ .
Differential Revision: D61155566