Skip to content

[SDK] Fix Worker and Master templates for PyTorchJob #771

[SDK] Fix Worker and Master templates for PyTorchJob

[SDK] Fix Worker and Master templates for PyTorchJob #771

name: Publish Training Operator Example Images
on:
- push
- pull_request
jobs:
example:
name: Publish Image
uses: ./.github/workflows/build-and-publish-images.yaml
with:
component-name: ${{ matrix.component-name }}
# TODO (tenzen-y): Support linux/arm64 platform
platforms: linux/amd64
dockerfile: ${{ matrix.dockerfile }}
context: ${{ matrix.context }}
secrets:
DOCKERHUB_USERNAME: ${{ secrets.DOCKERHUB_USERNAME }}
DOCKERHUB_TOKEN: ${{ secrets.DOCKERHUB_TOKEN }}
strategy:
fail-fast: false
matrix:
include:
- component-name: tf-dist-mnist-test
dockerfile: examples/tensorflow/dist-mnist/Dockerfile
- component-name: tf-distributed-worker
dockerfile: examples/tensorflow/distribution_strategy/estimator-API/Dockerfile
- component-name: tf-multi-worker-strategy
dockerfile: examples/tensorflow/distribution_strategy/keras-API/Dockerfile
- component-name: tf-mnist-with-summaries
dockerfile: examples/tensorflow/mnist_with_summaries/Dockerfile
- component-name: tf-smoke
dockerfile: examples/tensorflow/tf_sample/Dockerfile
- component-name: pytorch-dist-sendrecv-test
dockerfile: examples/pytorch/smoke-dist/Dockerfile
- component-name: pytorch-elastic-example-imagenet
dockerfile: examples/pytorch/elastic/imagenet/Dockerfile
- component-name: pytorch-elastic-example-echo
dockerfile: examples/pytorch/elastic/echo/Dockerfile
- component-name: xgboost-dist-iris
dockerfile: examples/xgboost/xgboost-dist/Dockerfile
context: examples/xgboost/xgboost-dist
- component-name: lightgbm-dist-py-test
dockerfile: examples/xgboost/lightgbm-dist/Dockerfile
context: examples/xgboost/lightgbm-dist
- component-name: xgboost-dist-rabit-test
dockerfile: examples/xgboost/smoke-dist/Dockerfile
context: examples/xgboost/smoke-dist
- component-name: mxnet-gpu
dockerfile: examples/mxnet/train/Dockerfile
- component-name: mxnet-auto-tuning
dockerfile: examples/mxnet/tune/Dockerfile
context: examples/mxnet/tune
# TODO (tenzen-y): Fix the below broken Dockerfiles
# - component-name: pytorch-dist-mnist-mpi
# dockerfile: examples/pytorch/mnist/Dockerfile-mpi
# - component-name: pytorch-dist-mnist
# dockerfile: examples/pytorch/mnist/Dockerfile