-
Notifications
You must be signed in to change notification settings - Fork 622
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
Conversation
This pull request was exported from Phabricator. Differential Revision: D72370780 |
✅ Deploy Preview for pytorch-fbgemm-docs ready!
To edit notification comments on pull requests, go to your Netlify site configuration. |
0dfd371
to
7377ea2
Compare
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
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
7377ea2
to
fc4909d
Compare
This pull request was exported from Phabricator. 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
fc4909d
to
2543862
Compare
This pull request was exported from Phabricator. 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
2543862
to
9832bb8
Compare
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
9719ec6
to
f657ab6
Compare
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
This pull request was exported from Phabricator. 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
f657ab6
to
1c22f9d
Compare
This pull request was exported from Phabricator. 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
b81febb
to
42e02bf
Compare
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
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
42e02bf
to
c90d26a
Compare
This pull request was exported from Phabricator. 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
c90d26a
to
ef2a52e
Compare
This pull request was exported from Phabricator. 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
948907e
to
98b61b5
Compare
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
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
98b61b5
to
c5e2e3f
Compare
This pull request was exported from Phabricator. 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
c5e2e3f
to
07d2053
Compare
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
This pull request was exported from Phabricator. Differential Revision: D72370780 |
07d2053
to
598f2df
Compare
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
This pull request has been merged in 30d2973. |
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