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.

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

Updated XNNPACK to v0.0.20200323 #4577

Merged
merged 10 commits into from
Mar 18, 2022

Conversation

stemann
Copy link
Contributor

@stemann stemann commented Mar 8, 2022

As referenced by Torch v1.6.0 - v1.7.1

@stemann stemann force-pushed the feature/xnnpack-20200323 branch from 8e24a8e to 29bffd3 Compare March 8, 2022 00:08
@stemann stemann marked this pull request as draft March 9, 2022 23:37
@stemann stemann force-pushed the feature/xnnpack-20200323 branch from 5a15862 to 218344e Compare March 17, 2022 10:14
@stemann stemann force-pushed the feature/xnnpack-20200323 branch from a680b4c to 0fa205a Compare March 17, 2022 16:31
@stemann stemann marked this pull request as ready for review March 17, 2022 16:32
@stemann
Copy link
Contributor Author

stemann commented Mar 17, 2022

The libraries built by all these non-versioned torch dependencies (CPUInfo, PThreadPool, XNNPACK) do not specify an SO version - this patch might be relevant: https://salsa.debian.org/deeplearning-team/xnnpack/-/blob/master/debian/patches/soversion.patch

?

@stemann
Copy link
Contributor Author

stemann commented Mar 18, 2022

The libraries built by all these non-versioned torch dependencies (CPUInfo, PThreadPool, XNNPACK) do not specify an SO version - this patch might be relevant: https://salsa.debian.org/deeplearning-team/xnnpack/-/blob/master/debian/patches/soversion.patch

?

Done

@stemann
Copy link
Contributor Author

stemann commented Mar 18, 2022

@giordano The extended platform support in this should fix a lot of the non-CUDA issues in #4554

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants