Skip to content
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.

Sign up for GitHub

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

Jump to bottom

Benchmarking updates for semi-structured sparse training #398

Merged
merged 3 commits into from
Jun 20, 2024
Merged

Benchmarking updates for semi-structured sparse training #398

merged 3 commits into from
Jun 20, 2024

Commits on Jun 18, 2024

  1. Benchmarking updates for semi-structured sparse training 

    Summary:

This PR does the following:
- adds e2e ViT benchmarks for semi-structured sparse training
- adds nn.Linear microbenchmarks
- removes extra xformers benchmarking utils I copied over
- removes MLP block benchmarks
- updated README.md with new benchmarks + accuracy benchmarks

Given we have nn.Linear microbenchmarks and e2e benchmarks, I felt that
the MLP block benchmarks were unnecessary

As a sanity check, I ran the MLP benchmarks with the new benchmarking
suite and the old one, and got the same results:

Test Plan:

Reviewers:

Subscribers:

Tasks:

Tags:
    @jcaip
    jcaip committed Jun 18, 2024
    Configuration menu
    Copy the full SHA
    cff8cfe View commit details
    Browse the repository at this point in the history

  2. update

    @jcaip
    jcaip committed Jun 18, 2024
    Configuration menu
    Copy the full SHA
    395bf2d View commit details
    Browse the repository at this point in the history

  3. add units

    @jcaip
    jcaip committed Jun 18, 2024
    Configuration menu
    Copy the full SHA
    881ae2c View commit details
    Browse the repository at this point in the history