Static attention IO manager #8486
Merged
Conversation
This file contains hidden or 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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/8486
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit d4e2e2b with merge base f936c99 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D69624077 |
iseeyuan
approved these changes
Feb 14, 2025
Contributor
iseeyuan
left a comment
iseeyuan
left a comment
There was a problem hiding this comment.
LGTM. Please add runner file in the following PR to cover the tests.
sxu
force-pushed
the
export-D69624077
branch
from
8a28199 to
d3eedde
Compare
sxu
added a commit
to sxu/executorch
that referenced
this pull request
Feb 16, 2025
Summary: Pull Request resolved: pytorch#8486 Helper class that manages I/O tensors for KV caches, attention masks, and RoPE frequencies. Data types of these tensors are templated to support quantized data. Reviewed By: iseeyuan Differential Revision: D69624077
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D69624077 |
Summary: Helper class that manages I/O tensors for KV caches, attention masks, and RoPE frequencies. Data types of these tensors are templated to support quantized data. Reviewed By: iseeyuan Differential Revision: D69624077
sxu
force-pushed
the
export-D69624077
branch
from
d3eedde to
d4e2e2b
Compare
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D69624077 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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: Helper class that manages I/O tensors for KV caches, attention masks, and RoPE frequencies. Data types of these tensors are templated to support quantized data.
Differential Revision: D69624077