Enable direct MX4→BF16 dequantization to reduce memory #5206
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
Summary: X-link: meta-pytorch/torchrec#3602 X-link: facebookresearch/FBGEMM#2202 Add output_dtype parameter to MX4 dequantization stack to support direct conversion to BF16/FP16, avoiding expensive FP32 intermediate step. Differential Revision: D87826479
Contributor
|
@armandsauzay has exported this pull request. If you are a Meta employee, you can view the originating Diff in D87826479. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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:
X-link: meta-pytorch/torchrec#3602
X-link: https://github.com/facebookresearch/FBGEMM/pull/2202
Add output_dtype parameter to MX4 dequantization stack to support direct
conversion to BF16/FP16, avoiding expensive FP32 intermediate step.
Differential Revision: D87826479