[ops] Add a sharded attention operation for SDPA #381
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
KyleHerndon
approved these changes
Oct 30, 2024
rsuderman
force-pushed
the
sharded_attention
branch
2 times, most recently
from
f5a2327 to
8d5cb89
Compare
Existing implementation invokes the `torch` sdpa operator directly. Rewired to invoke via the `ops` system for a sharded sdpa operation. This includes a sharded implementation that compares the two versions.
rsuderman
force-pushed
the
sharded_attention
branch
from
8d5cb89 to
cb15e76
Compare
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Outdated suggestions cannot be applied.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.
Existing implementation invokes the
torchsdpa operator directly. Rewired to invoke via theopssystem for a sharded sdpa operation. This includes a sharded implementation that compares the two versions.