FSDP Example for T5 Fine-Tuning and PyTorchJob (#2286) #1747
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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 }} | |
platforms: ${{ matrix.platforms }} | |
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 | |
platforms: linux/amd64,linux/arm64 | |
dockerfile: examples/tensorflow/dist-mnist/Dockerfile | |
- component-name: tf-distributed-worker | |
platforms: linux/amd64,linux/arm64 | |
dockerfile: examples/tensorflow/distribution_strategy/estimator-API/Dockerfile | |
- component-name: tf-multi-worker-strategy | |
platforms: linux/amd64,linux/arm64 | |
dockerfile: examples/tensorflow/distribution_strategy/keras-API/Dockerfile | |
- component-name: tf-mnist-with-summaries | |
platforms: linux/amd64,linux/arm64 | |
dockerfile: examples/tensorflow/mnist_with_summaries/Dockerfile | |
- component-name: tf-smoke | |
platforms: linux/amd64,linux/arm64 | |
dockerfile: examples/tensorflow/tf_sample/Dockerfile | |
- component-name: pytorch-dist-sendrecv-test | |
platforms: linux/amd64,linux/arm64 | |
dockerfile: examples/pytorch/smoke-dist/Dockerfile | |
- component-name: pytorch-elastic-example-imagenet | |
platforms: linux/amd64,linux/arm64 | |
dockerfile: examples/pytorch/elastic/imagenet/Dockerfile | |
- component-name: pytorch-elastic-example-echo | |
platforms: linux/amd64,linux/arm64 | |
dockerfile: examples/pytorch/elastic/echo/Dockerfile | |
- component-name: pytorch-torchrun-cpu | |
platforms: linux/amd64,linux/arm64 | |
dockerfile: examples/pytorch/cpu-demo/Dockerfile | |
context: examples/pytorch/cpu-demo | |
- component-name: xgboost-dist-iris | |
platforms: linux/amd64,linux/arm64 | |
dockerfile: examples/xgboost/xgboost-dist/Dockerfile | |
context: examples/xgboost/xgboost-dist | |
- component-name: lightgbm-dist-py-test | |
platforms: linux/amd64,linux/arm64 | |
dockerfile: examples/xgboost/lightgbm-dist/Dockerfile | |
context: examples/xgboost/lightgbm-dist | |
- component-name: xgboost-dist-rabit-test | |
platforms: linux/amd64,linux/arm64 | |
dockerfile: examples/xgboost/smoke-dist/Dockerfile | |
context: examples/xgboost/smoke-dist | |
- component-name: pytorch-dist-mnist | |
platforms: linux/amd64,linux/arm64 | |
dockerfile: examples/pytorch/mnist/Dockerfile | |
context: examples/pytorch/mnist | |
- component-name: pytorch-dist-mnist-mpi | |
platforms: linux/amd64,linux/arm64 | |
dockerfile: examples/pytorch/mnist/Dockerfile-mpi | |
context: examples/pytorch/mnist | |
- component-name: jaxjob-simple | |
platforms: linux/amd64,linux/arm64 | |
dockerfile: examples/jax/cpu-demo/Dockerfile | |
context: examples/jax/cpu-demo | |
- component-name: pytorch-deepspeed-demo | |
platforms: linux/amd64 | |
dockerfile: examples/pytorch/deepspeed-demo/Dockerfile | |
context: examples/pytorch/deepspeed-demo |