[PyTorch] Merge k_channels
and v_channels
back to kv_channels
#1094
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Outdated suggestions cannot be applied.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.
Description
This PR merges
k_channels
andv_channels
back tokv_channels
inDotProductAttention.__init__()
to avoid breaking backward compatibility, but it allows users to pass in a tuple(int, int)
in MLA (multi-latent attention) cases.We will add support for MLA in
MultiHeadAttention
andTransformerLayer
in future PRs.Type of change
Changes
Please list the changes introduced in this PR:
k_channels
andv_channels
back tokv_channels
inDotProductAttention
Checklist: