Cherry-pick LLaMA GQA mask to rel-1.16.2 (round 4) #18350
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
### Description GQA now only works with Flash Attention with Attention Mask input, allowing for batched input. Note: This PR Disables Memory Efficient Attention, only allowing Flash Attention kernel to be used. ### Motivation and Context Allows GQA to work with batched input. --------- Co-authored-by: Yufeng Li <liyufeng1987@gmail.com>
This PR updates replacing MHA with GQA and updates the LLaMA scripts for the modified GQA op. It is related to the changes in [this PR](#18283). ### Motivation and Context This PR allows us to run LLaMA with the GQA op end-to-end using ragged batching (i.e. batched inputs of different lengths).
kunal-vaishnavi
approved these changes
Nov 8, 2023
yufenglee
approved these changes
Nov 8, 2023
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Outdated suggestions cannot be applied.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
Cherry-pick LLaMA GQA attention mask and script changes to 1.16.2 release branch.
Motivation and Context