Add INT8 and INT4 support to P2P benchmark. #918
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
Summary: Add two options: 1) default, which transfers quantized tensor directly; 2) --include_quantization, which start with FP16 tensor, quantize, transfer, and finally dequantize to FP16 tensor. Also, add a option to sweep through data types and shapes. Caveat: INT4 dequantization is not numerically correct, but adding as a proxy for performance measurement. Reviewed By: brad-mengchi Differential Revision: D31098854 fbshipit-source-id: f7dd6ec6d57967aec9593108b8a9ecf52c947d4c
|
This pull request was exported from Phabricator. Differential Revision: D31098854 |
q10
pushed a commit
to q10/FBGEMM
that referenced
this pull request
Apr 10, 2025
Summary: X-link: pytorch#3841 Pull Request resolved: facebookresearch/FBGEMM#918 qk norm applies L2 norm, not rms norm. So we just use k_norm instead of k_rms_norm. Reviewed By: jasonjk-park, Aya-ZIbra Differential Revision: D71268903 fbshipit-source-id: aa5ad2ea795a718843d6c15a9dee03e9b332b860
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Outdated suggestions cannot be applied.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:
Add two options:
Also, add a option to sweep through data types and shapes.
Caveat: INT4 dequantization is not numerically correct, but adding as a proxy for performance measurement.
Reviewed By: brad-mengchi
Differential Revision: D31098854