Separate arm64 docker builds from amd64

[atalman]

As a followup after: pytorch/pytorch#125617
Add validation_runner output param to know what validation runner to use
Test:

python tools/scripts/generate_docker_release_matrix.py
{"include": [{"cuda": "11.8", "cuda_full_version": "11.8.0", "cudnn_version": "8", "image_type": "runtime", "docker": "ghcr.io/pytorch/pytorch-nightly:2.4.0.dev20240507-cuda11.8-cudnn8-runtime", "platform": "linux/amd64", "validation_runner": "linux.g5.4xlarge.nvidia.gpu"}, {"cuda": "11.8", "cuda_full_version": "11.8.0", "cudnn_version": "8", "image_type": "devel", "docker": "ghcr.io/pytorch/pytorch-nightly:2.4.0.dev20240507-cuda11.8-cudnn8-devel", "platform": "linux/amd64", "validation_runner": "linux.g5.4xlarge.nvidia.gpu"}, {"cuda": "12.1", "cuda_full_version": "12.1.1", "cudnn_version": "8", "image_type": "runtime", "docker": "ghcr.io/pytorch/pytorch-nightly:2.4.0.dev20240507-cuda12.1-cudnn8-runtime", "platform": "linux/amd64", "validation_runner": "linux.g5.4xlarge.nvidia.gpu"}, {"cuda": "12.1", "cuda_full_version": "12.1.1", "cudnn_version": "8", "image_type": "devel", "docker": "ghcr.io/pytorch/pytorch-nightly:2.4.0.dev20240507-cuda12.1-cudnn8-devel", "platform": "linux/amd64", "validation_runner": "linux.g5.4xlarge.nvidia.gpu"}, {"cuda": "12.4", "cuda_full_version": "12.4.0", "cudnn_version": "8", "image_type": "runtime", "docker": "ghcr.io/pytorch/pytorch-nightly:2.4.0.dev20240507-cuda12.4-cudnn8-runtime", "platform": "linux/amd64", "validation_runner": "linux.g5.4xlarge.nvidia.gpu"}, {"cuda": "12.4", "cuda_full_version": "12.4.0", "cudnn_version": "8", "image_type": "devel", "docker": "ghcr.io/pytorch/pytorch-nightly:2.4.0.dev20240507-cuda12.4-cudnn8-devel", "platform": "linux/amd64", "validation_runner": "linux.g5.4xlarge.nvidia.gpu"}, {"cuda": "cpu", "cuda_full_version": "", "cudnn_version": "", "image_type": "runtime", "docker": "ghcr.io/pytorch/pytorch-nightly:2.4.0.dev20240507-runtime", "platform": "linux/arm64", "validation_runner": "linux.arm64.2xlarge"}]}

[vercel]

@atalman is attempting to deploy a commit to the Meta Open Source Team on Vercel.

A member of the Team first needs to authorize it.

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

1 Ignored Deployment

Name	Status	Preview	Comments	Updated (UTC)
torchci	⬜️ Ignored (Inspect)	Visit Preview		May 7, 2024 7:01pm