Add GroupQueryAttention on CPU in model builder #420
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
yufenglee
reviewed
May 8, 2024
yufenglee
reviewed
May 8, 2024
yufenglee
approved these changes
May 9, 2024
kunal-vaishnavi
added a commit
that referenced
this pull request
May 10, 2024
### Description This PR adds support for packing the bias after a packed QKV MatMul. ### Motivation and Context This PR is a follow up to [this PR](#420).
baijumeswani
pushed a commit
that referenced
this pull request
May 10, 2024
### Description This PR adds `GroupQueryAttention` to ONNX models generated for CPU. ### Motivation and Context This PR is a follow up to [this PR](#270).
baijumeswani
pushed a commit
that referenced
this pull request
May 10, 2024
### Description This PR adds support for packing the bias after a packed QKV MatMul. ### Motivation and Context This PR is a follow up to [this PR](#420).
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Outdated suggestions cannot be applied.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.
Description
This PR adds
GroupQueryAttentionto ONNX models generated for CPU.Motivation and Context
This PR is a follow up to this PR.