Support zero-size inputs in FP8 cuda quantize kernel #3448
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
|
This pull request was exported from Phabricator. Differential Revision: D66727399 |
✅ Deploy Preview for pytorch-fbgemm-docs ready!
To edit notification comments on pull requests, go to your Netlify site configuration. |
Summary: X-link: facebookresearch/FBGEMM#533 For MOE, if tokens are not routed (in dynamic case), we could have some experts running 0 tokens, found by jasonjk-park This Diff supports zero-size inputs in FP8 cuda quantize kernel in this case Reviewed By: jasonjk-park Differential Revision: D66727399
jiawenliu64
force-pushed
the
export-D66727399
branch
from
f1b3fef to
9981cae
Compare
|
This pull request was exported from Phabricator. Differential Revision: D66727399 |
|
This pull request has been merged in 1a0d837. |
q10
pushed a commit
to q10/FBGEMM
that referenced
this pull request
Apr 10, 2025
Summary: X-link: pytorch#3448 Pull Request resolved: facebookresearch/FBGEMM#533 For MOE, if tokens are not routed (in dynamic case), we could have some experts running 0 tokens, found by jasonjk-park This Diff supports zero-size inputs in FP8 cuda quantize kernel in this case Reviewed By: jasonjk-park Differential Revision: D66727399 fbshipit-source-id: e4d760edace6b9e0cc6a1018f88e03b8a19b0ce6
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Outdated suggestions cannot be applied.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:
For MOE, if tokens are not routed (in dynamic case), we could have some experts running 0 tokens, found by Jason
This Diff supports zero-size inputs in FP8 cuda quantize kernel in this case
Differential Revision: D66727399