diff --git a/.github/workflows/publish-example-images.yaml b/.github/workflows/publish-example-images.yaml index ebf20a721f..8e61ef9c4f 100644 --- a/.github/workflows/publish-example-images.yaml +++ b/.github/workflows/publish-example-images.yaml @@ -57,5 +57,7 @@ jobs: context: examples/mxnet/tune - component-name: pytorch-dist-mnist dockerfile: examples/pytorch/mnist/Dockerfile + context: examples/pytorch/mnist - component-name: pytorch-dist-mnist-mpi dockerfile: examples/pytorch/mnist/Dockerfile-mpi + context: examples/pytorch/mnist diff --git a/examples/pytorch/elastic/imagenet/Dockerfile b/examples/pytorch/elastic/imagenet/Dockerfile index 80c4fe07b9..25ecc49577 100644 --- a/examples/pytorch/elastic/imagenet/Dockerfile +++ b/examples/pytorch/elastic/imagenet/Dockerfile @@ -1,3 +1,6 @@ +# We need to use the nvcr.io/nvidia/pytorch image as a base image to support both linux/amd64 and linux_arm64 platforms. +# PyTorch=2.2.0, cuda=12.3.2 +# Ref: https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/rel-24-01.html#rel-24-01 ARG BASE_IMAGE=nvcr.io/nvidia/pytorch:24.01-py3 FROM $BASE_IMAGE diff --git a/examples/pytorch/mnist/Dockerfile b/examples/pytorch/mnist/Dockerfile index ce4e642f72..92e6c5e220 100644 --- a/examples/pytorch/mnist/Dockerfile +++ b/examples/pytorch/mnist/Dockerfile @@ -1,3 +1,6 @@ +# We need to use the nvcr.io/nvidia/pytorch image as a base image to support both linux/amd64 and linux_arm64 platforms. +# PyTorch=2.2.0, cuda=12.3.2 +# Ref: https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/rel-24-01.html#rel-24-01 FROM nvcr.io/nvidia/pytorch:24.01-py3 RUN pip install tensorboardX==2.6.2 diff --git a/examples/pytorch/mnist/Dockerfile-mpi b/examples/pytorch/mnist/Dockerfile-mpi index a578373911..57b69ef692 100644 --- a/examples/pytorch/mnist/Dockerfile-mpi +++ b/examples/pytorch/mnist/Dockerfile-mpi @@ -1,3 +1,6 @@ +# We need to use the nvcr.io/nvidia/pytorch image as a base image to support both linux/amd64 and linux_arm64 platforms. +# PyTorch=2.2.0, cuda=12.3.2 +# Ref: https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/rel-24-01.html#rel-24-01 FROM nvcr.io/nvidia/pytorch:24.01-py3 RUN pip install tensorboardX==2.6.2 diff --git a/examples/pytorch/smoke-dist/Dockerfile b/examples/pytorch/smoke-dist/Dockerfile index 9b54f4e91c..2760ee2e6f 100644 --- a/examples/pytorch/smoke-dist/Dockerfile +++ b/examples/pytorch/smoke-dist/Dockerfile @@ -1,3 +1,6 @@ +# We need to use the nvcr.io/nvidia/pytorch image as a base image to support both linux/amd64 and linux_arm64 platforms. +# PyTorch=2.2.0, cuda=12.3.2 +# Ref: https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/rel-24-01.html#rel-24-01 FROM nvcr.io/nvidia/pytorch:24.01-py3 RUN mkdir -p /opt/mlkube