Skip to content

Use F14Map instead of std::map in CodeCache.h, and reuse Ctile buffer in ExecuteU8S8.cc #670

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from

Conversation

dskhudia
Copy link
Contributor

Differential Revision: D30466385

… in ExecuteU8S8.cc

Differential Revision: D30466385

fbshipit-source-id: a2d29c13d1c7ef9aaae5b99102fdddcea958aad8
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D30466385

@facebook-github-bot
Copy link
Contributor

This pull request has been merged in d5e66bf.

q10 pushed a commit to q10/FBGEMM that referenced this pull request Apr 10, 2025
Summary:
Pull Request resolved: facebookresearch/FBGEMM#670

X-link: pytorch#3584

Seq INT4 -> INT4 STBE look up is supported in the diff stack: https://www.internalfb.com/diff/D61305978 .

This diff supports:

1. The dequanitzation of INT4 -> INT4 STBE look up onto Cuda for all float types
2. Extends the dequantization of INT4 > INT4 STBE look up onto CPU for BF16

The main gap is to handle the dequant for the case when scale bias for INT4 quantized tensor is in the front. While for CPU, just need to add the dequantization for BF16 based on dtype.

This will enable us to reduce the network overhead to remote embedding server as well as D2H data transfer from onto GPU host.

Reviewed By: jiayisuse

Differential Revision: D68187234

fbshipit-source-id: 2c082775a711f1738eb8e5b7ee9319c4d70d7240
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants