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

Mac M1 support #22

Closed
rssdev10 opened this issue Oct 29, 2022 · 8 comments
Closed

Mac M1 support #22

rssdev10 opened this issue Oct 29, 2022 · 8 comments

Comments

@rssdev10
Copy link
Contributor

Hello, is any way to update binary dependencies https://github.com/jw3126/ONNXRunTime.jl/blob/main/Artifacts.toml
by https://github.com/microsoft/onnxruntime/releases/tag/v1.13.1 ?

For Mac M1 there is a universal archive onnxruntime-osx-universal2-1.13.1.tgz with both arm64 and amd64 platforms.

@jw3126
Copy link
Owner

jw3126 commented Oct 30, 2022

Sure if it is already a tarball you can just add it to Artifacts.toml. If not we need to repackage it. Happy to guide a PR if you want to give it a shot.

@rssdev10
Copy link
Contributor Author

If I understand right, all the binaries are available. And, number of supported architectures in general is much higher compared with the previous version. But, the first step - somebody have to upload these files to https://github.com/jw3126/ONNXRunTimeArtifacts/releases/download/ .

If you explain me how to do it, I can check ONNXRunTime with both Mac architectures. But I don't have other architectures. And, if you have some script for automation generating the following descriptions and check sums, it would be good to have it too:

[[onnxruntime_cpu]]
arch = "x86_64"
git-tree-sha1 = "f07f041b61f199fa853a0e66652633c2d9007478"
lazy = true
libc = "glibc"
os = "linux"

    [[onnxruntime_cpu.download]]
    sha256 = "f386ab80e9d6d41f14ed9e61bff4acc6bf375770691bc3ba883ba0ba3cabca7f"
    url = "https://github.com/jw3126/ONNXRunTimeArtifacts/releases/download/v1.9.0-rc4/onnxruntime-linux-x64-1.9.0.tgz"

@jw3126
Copy link
Owner

jw3126 commented Oct 30, 2022

If I understand right, all the binaries are available. And, number of supported architectures in general is much higher compared with the previous version. But, the first step - somebody have to upload these files to https://github.com/jw3126/ONNXRunTimeArtifacts/releases/download/ .

Repackaging to ONNXRunTimeArtifacts should only be necessary for windows. The other binaries can be taken directly from
https://github.com/microsoft/onnxruntime/releases/tag/v1.13.1, see also #24.

@jw3126
Copy link
Owner

jw3126 commented Oct 30, 2022

With #24 merged, it should now be easier for you to add M1 support.

@jw3126
Copy link
Owner

jw3126 commented Oct 30, 2022

I use this script, in case you need to adapt it: https://github.com/jw3126/ONNXRunTimeArtifacts/blob/main/script.jl

@rssdev10
Copy link
Contributor Author

Thanks, but a minor fix for the script:

    (
    artifact_name="onnxruntime_cpu",
    download_name="onnxruntime-osx-universal2-$version.tgz",
    platform=Pkg.Artifacts.Platform("x86_64", "macos"),
    version=version,
   ),
    (
    artifact_name="onnxruntime_cpu",
    download_name="onnxruntime-osx-universal2-$version.tgz",
    platform=Pkg.Artifacts.Platform("aarch64", "macos"),
    version=version,
   ),

@rssdev10
Copy link
Contributor Author

and, with #25 that works on M1.

@jw3126
Copy link
Owner

jw3126 commented Nov 1, 2022

fixed by #25 if some issues remain, please reopen.

@jw3126 jw3126 closed this as completed Nov 1, 2022
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

No branches or pull requests

2 participants