Skip to content

Make kv_cache tests device agnostic #3961

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

PatriceVignola
Copy link
Contributor

Summary: The kv_cache tests are currently hardcoded to use CUDA, but we want to be able to hook other devices to it.

Differential Revision: D72370780

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D72370780

Copy link

netlify bot commented Apr 11, 2025

Deploy Preview for pytorch-fbgemm-docs ready!

Name Link
🔨 Latest commit 598f2df
🔍 Latest deploy log https://app.netlify.com/sites/pytorch-fbgemm-docs/deploys/67ffe9bd7d8c500008cdb475
😎 Deploy Preview https://deploy-preview-3961--pytorch-fbgemm-docs.netlify.app
📱 Preview on mobile
Toggle QR Code...

QR Code

Use your smartphone camera to open QR code link.

To edit notification comments on pull requests, go to your Netlify site configuration.

PatriceVignola added a commit to PatriceVignola/FBGEMM-1 that referenced this pull request Apr 15, 2025
Summary:

X-link: facebookresearch/FBGEMM#1044

The kv_cache tests are currently hardcoded to use CUDA, but we want to be able to hook other devices to it.

Differential Revision: D72370780
PatriceVignola added a commit to PatriceVignola/FBGEMM-1 that referenced this pull request Apr 15, 2025
Summary:

X-link: facebookresearch/FBGEMM#1044

The kv_cache tests are currently hardcoded to use CUDA, but we want to be able to hook other devices to it.

Differential Revision: D72370780
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D72370780

PatriceVignola added a commit to PatriceVignola/FBGEMM-1 that referenced this pull request Apr 15, 2025
Summary:
Pull Request resolved: pytorch#3961

X-link: facebookresearch/FBGEMM#1044

The kv_cache tests are currently hardcoded to use CUDA, but we want to be able to hook other devices to it.

Differential Revision: D72370780
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D72370780

PatriceVignola added a commit to PatriceVignola/FBGEMM-1 that referenced this pull request Apr 15, 2025
Summary:
Pull Request resolved: pytorch#3961

X-link: facebookresearch/FBGEMM#1044

The kv_cache tests are currently hardcoded to use CUDA, but we want to be able to hook other devices to it.

Differential Revision: D72370780
PatriceVignola added a commit to PatriceVignola/FBGEMM-1 that referenced this pull request Apr 15, 2025
Summary:

X-link: facebookresearch/FBGEMM#1044

The kv_cache tests are currently hardcoded to use CUDA, but we want to be able to hook other devices to it.

Differential Revision: D72370780
@PatriceVignola PatriceVignola force-pushed the export-D72370780 branch 2 times, most recently from 9719ec6 to f657ab6 Compare April 15, 2025 04:08
PatriceVignola added a commit to PatriceVignola/FBGEMM-1 that referenced this pull request Apr 15, 2025
Summary:

X-link: facebookresearch/FBGEMM#1044

The kv_cache tests are currently hardcoded to use CUDA, but we want to be able to hook other devices to it.

Differential Revision: D72370780
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D72370780

PatriceVignola added a commit to PatriceVignola/FBGEMM-1 that referenced this pull request Apr 15, 2025
Summary:
Pull Request resolved: pytorch#3961

X-link: facebookresearch/FBGEMM#1044

The kv_cache tests are currently hardcoded to use CUDA, but we want to be able to hook other devices to it.

Differential Revision: D72370780
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D72370780

PatriceVignola added a commit to PatriceVignola/FBGEMM-1 that referenced this pull request Apr 15, 2025
Summary:
Pull Request resolved: pytorch#3961

X-link: facebookresearch/FBGEMM#1044

The kv_cache tests are currently hardcoded to use CUDA, but we want to be able to hook other devices to it.

Differential Revision: D72370780
@PatriceVignola PatriceVignola force-pushed the export-D72370780 branch 2 times, most recently from b81febb to 42e02bf Compare April 16, 2025 15:52
PatriceVignola added a commit to PatriceVignola/FBGEMM-1 that referenced this pull request Apr 16, 2025
Summary:

X-link: facebookresearch/FBGEMM#1044

The kv_cache tests are currently hardcoded to use CUDA, but we want to be able to hook other devices to it.

Differential Revision: D72370780
PatriceVignola added a commit to PatriceVignola/FBGEMM-1 that referenced this pull request Apr 16, 2025
Summary:

X-link: facebookresearch/FBGEMM#1044

The kv_cache tests are currently hardcoded to use CUDA, but we want to be able to hook other devices to it.

Differential Revision: D72370780
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D72370780

PatriceVignola added a commit to PatriceVignola/FBGEMM-1 that referenced this pull request Apr 16, 2025
Summary:
Pull Request resolved: pytorch#3961

X-link: facebookresearch/FBGEMM#1044

The kv_cache tests are currently hardcoded to use CUDA, but we want to be able to hook other devices to it.

Differential Revision: D72370780
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D72370780

PatriceVignola added a commit to PatriceVignola/FBGEMM-1 that referenced this pull request Apr 16, 2025
Summary:
Pull Request resolved: pytorch#3961

X-link: facebookresearch/FBGEMM#1044

The kv_cache tests are currently hardcoded to use CUDA, but we want to be able to hook other devices to it.

Differential Revision: D72370780
@PatriceVignola PatriceVignola force-pushed the export-D72370780 branch 2 times, most recently from 948907e to 98b61b5 Compare April 16, 2025 17:18
PatriceVignola added a commit to PatriceVignola/FBGEMM-1 that referenced this pull request Apr 16, 2025
Summary:

X-link: facebookresearch/FBGEMM#1044

The kv_cache tests are currently hardcoded to use CUDA, but we want to be able to hook other devices to it.

Differential Revision: D72370780
PatriceVignola added a commit to PatriceVignola/FBGEMM-1 that referenced this pull request Apr 16, 2025
Summary:

X-link: facebookresearch/FBGEMM#1044

The kv_cache tests are currently hardcoded to use CUDA, but we want to be able to hook other devices to it.

Differential Revision: D72370780
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D72370780

PatriceVignola added a commit to PatriceVignola/FBGEMM-1 that referenced this pull request Apr 16, 2025
Summary:
Pull Request resolved: pytorch#3961

X-link: facebookresearch/FBGEMM#1044

The kv_cache tests are currently hardcoded to use CUDA, but we want to be able to hook other devices to it.

Differential Revision: D72370780
Summary:
Pull Request resolved: pytorch#3961

X-link: facebookresearch/FBGEMM#1044

The kv_cache tests are currently hardcoded to use CUDA, but we want to be able to hook other devices to it.

Differential Revision: D72370780
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D72370780

brad-mengchi pushed a commit to brad-mengchi/FBGEMM that referenced this pull request Apr 17, 2025
Summary:
Pull Request resolved: pytorch#3961

X-link: facebookresearch/FBGEMM#1044

The kv_cache tests are currently hardcoded to use CUDA, but we want to be able to hook other devices to it.

Differential Revision: D72370780
@facebook-github-bot
Copy link
Contributor

This pull request has been merged in 30d2973.

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.

4 participants