pad dequantized paged fp8 kv with zeros #4780
Closed
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
✅ Deploy Preview for pytorch-fbgemm-docs ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
|
This pull request was exported from Phabricator. Differential Revision: D80977902 |
bottler
added a commit
to bottler/FBGEMM-1
that referenced
this pull request
Aug 27, 2025
Summary: X-link: facebookresearch/FBGEMM#1803 Pad zeros after the end of used sequences to avoid nans in flash attention 3, in the dequantization of fp8 paged kv-cache. This is analogous to the non-paged case which was tackled in D69522001. Differential Revision: D80977902
bottler
force-pushed
the
export-D80977902
branch
from
5a83a60 to
c353791
Compare
bottler
added a commit
to bottler/FBGEMM-1
that referenced
this pull request
Aug 27, 2025
Summary: X-link: facebookresearch/FBGEMM#1803 Pad zeros after the end of used sequences to avoid nans in flash attention 3, in the dequantization of fp8 paged kv-cache. This is analogous to the non-paged case which was tackled in D69522001. Differential Revision: D80977902
bottler
force-pushed
the
export-D80977902
branch
from
c353791 to
b5046be
Compare
|
This pull request was exported from Phabricator. Differential Revision: D80977902 |
bottler
added a commit
to bottler/FBGEMM-1
that referenced
this pull request
Aug 27, 2025
Summary: Pull Request resolved: pytorch#4780 X-link: facebookresearch/FBGEMM#1803 Pad zeros after the end of used sequences to avoid nans in flash attention 3, in the dequantization of fp8 paged kv-cache. This is analogous to the non-paged case which was tackled in D69522001. Differential Revision: D80977902
bottler
force-pushed
the
export-D80977902
branch
from
b5046be to
6b58c11
Compare
|
This pull request was exported from Phabricator. Differential Revision: D80977902 |
1 similar comment
|
This pull request was exported from Phabricator. Differential Revision: D80977902 |
Summary: Pull Request resolved: pytorch#4780 X-link: facebookresearch/FBGEMM#1803 Pad zeros after the end of used sequences to avoid nans in flash attention 3, in the dequantization of fp8 paged kv-cache. This is analogous to the non-paged case which was tackled in D69522001. Differential Revision: D80977902
bottler
force-pushed
the
export-D80977902
branch
from
6b58c11 to
3cb21bd
Compare
|
This pull request was exported from Phabricator. Differential Revision: D80977902 |
|
This pull request has been merged in 699954b. |
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.
Summary: Pad zeros after the end of used sequences to avoid nans in flash attention 3, in the dequantization of fp8 paged kv-cache. This is analogous to the non-paged case which was tackled in D69522001.
Differential Revision: D80977902