From 10bd53c7d7beec5c9543691189a58655d653f4c2 Mon Sep 17 00:00:00 2001 From: Akihiro Nitta Date: Fri, 8 Jul 2022 16:17:57 +0900 Subject: [PATCH 01/13] Refactor docker builds in CI --- .github/workflows/ci-pytorch_dockers.yml | 69 ++++++++---------------- 1 file changed, 22 insertions(+), 47 deletions(-) diff --git a/.github/workflows/ci-pytorch_dockers.yml b/.github/workflows/ci-pytorch_dockers.yml index 69d5955c5db33..859f84dcbcfdc 100644 --- a/.github/workflows/ci-pytorch_dockers.yml +++ b/.github/workflows/ci-pytorch_dockers.yml @@ -1,10 +1,8 @@ name: Docker - PyTorch -# https://www.docker.com/blog/first-docker-github-action-is-here -# https://github.com/docker/build-push-action -# see: https://help.github.com/en/actions/reference/events-that-trigger-workflows -on: # Trigger the workflow on push or pull request, but only for the master branch + +on: push: - branches: [master, "release/*"] # include release branches like release/1.0.x + branches: [master, "release/*"] pull_request: branches: [master, "release/*"] paths: @@ -26,7 +24,7 @@ concurrency: cancel-in-progress: ${{ ! (github.ref == 'refs/heads/master' || startsWith(github.ref, 'refs/heads/release/')) }} jobs: - build-PL: + pl: runs-on: ubuntu-20.04 strategy: fail-fast: false @@ -35,12 +33,8 @@ jobs: python_version: ["3.9"] pytorch_version: ["1.10", "1.11"] steps: - - name: Checkout - uses: actions/checkout@v2 - - - name: Build PL Docker - # publish master/release - uses: docker/build-push-action@v2 + - uses: actions/checkout@v2 + - uses: docker/build-push-action@v2 with: build-args: | PYTHON_VERSION=${{ matrix.python_version }} @@ -49,7 +43,7 @@ jobs: push: false timeout-minutes: 50 - build-XLA: + xla: runs-on: ubuntu-20.04 strategy: fail-fast: false @@ -58,12 +52,8 @@ jobs: python_version: ["3.7"] xla_version: ["1.11"] steps: - - name: Checkout - uses: actions/checkout@v2 - - - name: Build XLA Docker - # publish master/release - uses: docker/build-push-action@v2 + - uses: actions/checkout@v2 + - uses: docker/build-push-action@v2 with: build-args: | PYTHON_VERSION=${{ matrix.python_version }} @@ -72,7 +62,7 @@ jobs: push: false timeout-minutes: 60 - build-CUDA: + cuda: runs-on: ubuntu-20.04 strategy: fail-fast: false @@ -86,11 +76,8 @@ jobs: - {python_version: "3.9", pytorch_version: "1.10", cuda_version: "11.1", ubuntu_version: "20.04"} - {python_version: "3.9", pytorch_version: "1.11", cuda_version: "11.3.1", ubuntu_version: "20.04"} steps: - - name: Checkout - uses: actions/checkout@v2 - - name: Build CUDA Docker - # publish master/release - uses: docker/build-push-action@v2 + - uses: actions/checkout@v2 + - uses: docker/build-push-action@v2 with: build-args: | PYTHON_VERSION=${{ matrix.python_version }} @@ -101,22 +88,18 @@ jobs: push: false timeout-minutes: 95 - build-Conda: + conda: runs-on: ubuntu-20.04 strategy: fail-fast: false matrix: include: - # see: https://pytorch.org/get-started/previous-versions/ - {python_version: "3.8", pytorch_version: "1.9", cuda_version: "11.1"} - {python_version: "3.8", pytorch_version: "1.10", cuda_version: "11.1"} - {python_version: "3.9", pytorch_version: "1.11", cuda_version: "11.3.1"} steps: - - name: Checkout - uses: actions/checkout@v2 - - name: Build Conda Docker - # publish master/release - uses: docker/build-push-action@v2 + - uses: actions/checkout@v2 + - uses: docker/build-push-action@v2 with: build-args: | PYTHON_VERSION=${{ matrix.python_version }} @@ -126,7 +109,7 @@ jobs: push: false timeout-minutes: 95 - build-ipu: + ipu: runs-on: ubuntu-20.04 strategy: fail-fast: false @@ -135,11 +118,8 @@ jobs: python_version: ["3.9"] # latest pytorch_version: ["1.9"] steps: - - name: Checkout - uses: actions/checkout@v2 - - - name: Build IPU Docker - uses: docker/build-push-action@v2 + - uses: actions/checkout@v2 + - uses: docker/build-push-action@v2 with: build-args: | PYTHON_VERSION=${{ matrix.python_version }} @@ -148,9 +128,7 @@ jobs: push: false tags: pytorchlightning/pytorch_lightning:base-ipu-py${{ matrix.python_version }}-torch${{ matrix.pytorch_version }} timeout-minutes: 50 - - - name: Build IPU CI runner Docker - uses: docker/build-push-action@v2 + - uses: docker/build-push-action@v2 with: build-args: | PYTHON_VERSION=${{ matrix.python_version }} @@ -159,7 +137,7 @@ jobs: push: false timeout-minutes: 60 - build-hpu: + hpu: runs-on: ubuntu-20.04 strategy: fail-fast: false @@ -168,11 +146,8 @@ jobs: gaudi_version: ["1.5.0"] pytorch_version: ["1.11.0"] steps: - - name: Checkout - uses: actions/checkout@v2 - - - name: Build HPU CI runner Docker - uses: docker/build-push-action@v2 + - uses: actions/checkout@v2 + - uses: docker/build-push-action@v2 with: build-args: | DIST=latest From 53ac307d464fe19da473e7c154c2161b15703453 Mon Sep 17 00:00:00 2001 From: Akihiro Nitta Date: Fri, 8 Jul 2022 16:58:36 +0900 Subject: [PATCH 02/13] Reduce duplicate and merge two workflows --- .github/workflows/ci-pytorch_dockers.yml | 111 ++++++++-- .github/workflows/events-nightly.yml | 255 ----------------------- 2 files changed, 97 insertions(+), 269 deletions(-) diff --git a/.github/workflows/ci-pytorch_dockers.yml b/.github/workflows/ci-pytorch_dockers.yml index 859f84dcbcfdc..247ba476697d6 100644 --- a/.github/workflows/ci-pytorch_dockers.yml +++ b/.github/workflows/ci-pytorch_dockers.yml @@ -18,6 +18,8 @@ on: - ".github/workflows/*docker*.yml" - ".github/workflows/events-nightly.yml" - "setup.py" + schedule: + - cron: "0 0 * * *" # at the end of every day concurrency: group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref }} @@ -40,7 +42,7 @@ jobs: PYTHON_VERSION=${{ matrix.python_version }} PYTORCH_VERSION=${{ matrix.pytorch_version }} file: dockers/release/Dockerfile - push: false + push: false # pushed in release-docker.yml only when PL is released timeout-minutes: 50 xla: @@ -53,14 +55,30 @@ jobs: xla_version: ["1.11"] steps: - uses: actions/checkout@v2 + - uses: docker/setup-buildx-action@v1 + - uses: docker/login-action@v1 + if: github.event_name == 'schedule' + with: + username: ${{ secrets.DOCKER_USERNAME }} + password: ${{ secrets.DOCKER_PASSWORD }} - uses: docker/build-push-action@v2 with: build-args: | PYTHON_VERSION=${{ matrix.python_version }} XLA_VERSION=${{ matrix.xla_version }} file: dockers/base-xla/Dockerfile - push: false + push: github.event_name == 'schedule' + tags: pytorchlightning/pytorch_lightning:base-xla-py${{ matrix.python_version }}-torch${{ matrix.xla_version }} timeout-minutes: 60 + - uses: ravsamhq/notify-slack-action@v1 + if: failure() && github.event_name == 'schedule' + with: + status: ${{ job.status }} + token: ${{ secrets.GITHUB_TOKEN }} + notification_title: ${{ format('XLA; {0} py{1} for *{2}*', runner.os, matrix.python_version, matrix.xla_version) }} + message_format: '{emoji} *{workflow}* {status_message}, see <{run_url}|detail>, cc: <@U01GD29QCAV>' # kaushikb11 + env: + SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }} cuda: runs-on: ubuntu-20.04 @@ -77,6 +95,12 @@ jobs: - {python_version: "3.9", pytorch_version: "1.11", cuda_version: "11.3.1", ubuntu_version: "20.04"} steps: - uses: actions/checkout@v2 + - uses: docker/setup-buildx-action@v1 + - uses: docker/login-action@v1 + if: github.event_name == 'schedule' + with: + username: ${{ secrets.DOCKER_USERNAME }} + password: ${{ secrets.DOCKER_PASSWORD }} - uses: docker/build-push-action@v2 with: build-args: | @@ -85,8 +109,18 @@ jobs: CUDA_VERSION=${{ matrix.cuda_version }} UBUNTU_VERSION=${{ matrix.ubuntu_version }} file: dockers/base-cuda/Dockerfile - push: false + push: github.event_name == 'schedule' + tags: pytorchlightning/pytorch_lightning:base-cuda-py${{ matrix.python_version }}-torch${{ matrix.pytorch_version }} timeout-minutes: 95 + - uses: ravsamhq/notify-slack-action@v1 + if: failure() && github.event_name == 'schedule' + with: + status: ${{ job.status }} + token: ${{ secrets.GITHUB_TOKEN }} + notification_title: ${{ format('CUDA; {0} py{1} for *{2}*', runner.os, matrix.python_version, matrix.pytorch_version) }} + message_format: '{emoji} *{workflow}* {status_message}, see <{run_url}|detail>, cc: <@U01A5T7EY9M>' # akihironitta + env: + SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }} conda: runs-on: ubuntu-20.04 @@ -97,8 +131,16 @@ jobs: - {python_version: "3.8", pytorch_version: "1.9", cuda_version: "11.1"} - {python_version: "3.8", pytorch_version: "1.10", cuda_version: "11.1"} - {python_version: "3.9", pytorch_version: "1.11", cuda_version: "11.3.1"} + # nightly: add when there's a release candidate + # - {python_version: "3.9", pytorch_version: "1.12"} steps: - uses: actions/checkout@v2 + - uses: docker/setup-buildx-action@v1 + - uses: docker/login-action@v1 + if: github.event_name == 'schedule' + with: + username: ${{ secrets.DOCKER_USERNAME }} + password: ${{ secrets.DOCKER_PASSWORD }} - uses: docker/build-push-action@v2 with: build-args: | @@ -106,26 +148,41 @@ jobs: PYTORCH_VERSION=${{ matrix.pytorch_version }} CUDA_VERSION=${{ matrix.cuda_version }} file: dockers/base-conda/Dockerfile - push: false + push: github.event_name == 'schedule' + tags: pytorchlightning/pytorch_lightning:base-conda-py${{ matrix.python_version }}-torch${{ matrix.pytorch_version }} timeout-minutes: 95 + - uses: ravsamhq/notify-slack-action@v1 + if: failure() && github.event_name == 'schedule' + with: + status: ${{ job.status }} + token: ${{ secrets.GITHUB_TOKEN }} + notification_title: ${{ format('Conda; {0} py{1} for *{2}*', runner.os, matrix.python_version, matrix.pytorch_version) }} + message_format: '{emoji} *{workflow}* {status_message}, see <{run_url}|detail>, cc: <@U01A5T7EY9M>' # akihironitta + env: + SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }} ipu: runs-on: ubuntu-20.04 strategy: fail-fast: false matrix: - # the config used in 'dockers/ci-runner-ipu/Dockerfile' - python_version: ["3.9"] # latest - pytorch_version: ["1.9"] + include: + # the config used in 'dockers/ci-runner-ipu/Dockerfile' + - {python_version: "3.9", pytorch_version: "1.9"} steps: - uses: actions/checkout@v2 + - uses: docker/setup-buildx-action@v1 + - uses: docker/login-action@v1 + with: + username: ${{ secrets.DOCKER_USERNAME }} + password: ${{ secrets.DOCKER_PASSWORD }} - uses: docker/build-push-action@v2 with: build-args: | PYTHON_VERSION=${{ matrix.python_version }} PYTORCH_VERSION=${{ matrix.pytorch_version }} file: dockers/base-ipu/Dockerfile - push: false + push: github.event_name == 'schedule' tags: pytorchlightning/pytorch_lightning:base-ipu-py${{ matrix.python_version }}-torch${{ matrix.pytorch_version }} timeout-minutes: 50 - uses: docker/build-push-action@v2 @@ -134,19 +191,35 @@ jobs: PYTHON_VERSION=${{ matrix.python_version }} PYTORCH_VERSION=${{ matrix.pytorch_version }} file: dockers/ci-runner-ipu/Dockerfile - push: false - timeout-minutes: 60 + push: github.event_name == 'schedule' + tags: pytorchlightning/pytorch_lightning:ipu-ci-runner-py${{ matrix.python_version }} + timeout-minutes: 55 + - uses: ravsamhq/notify-slack-action@v1 + if: failure() && github.event_name == 'schedule' + with: + status: ${{ job.status }} + token: ${{ secrets.GITHUB_TOKEN }} + notification_title: ${{ format('IPU; {0} py{1} for *{2}*', runner.os, matrix.python_version, matrix.pytorch_version) }} + message_format: '{emoji} *{workflow}* {status_message}, see <{run_url}|detail>, cc: <@U01BULUS2BG>' # SeanNaren + env: + SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }} hpu: runs-on: ubuntu-20.04 strategy: fail-fast: false matrix: - # the config used in 'dockers/ci-runner-hpu/Dockerfile' - gaudi_version: ["1.5.0"] - pytorch_version: ["1.11.0"] + include: + # the config used in 'dockers/ci-runner-hpu/Dockerfile' + - {gaudi_version: "1.5.0", pytorch_version: "1.11.0"} steps: - uses: actions/checkout@v2 + - uses: docker/setup-buildx-action@v1 + - name: Login to DockerHub + uses: docker/login-action@v1 + with: + username: ${{ secrets.DOCKER_USERNAME }} + password: ${{ secrets.DOCKER_PASSWORD }} - uses: docker/build-push-action@v2 with: build-args: | @@ -155,4 +228,14 @@ jobs: PYTORCH_VERSION=${{ matrix.pytorch_version }} file: dockers/ci-runner-hpu/Dockerfile push: false - timeout-minutes: 60 + tags: pytorchlightning/pytorch_lightning:hpu-ci-runner-gaudi${{ matrix.gaudi_version }} + timeout-minutes: 55 + - uses: ravsamhq/notify-slack-action@v1 + if: failure() && github.event_name == 'schedule' + with: + status: ${{ job.status }} + token: ${{ secrets.GITHUB_TOKEN }} + notification_title: ${{ format('HPU; {0} py{1} for *{2}*', runner.os, matrix.gaudi_version, matrix.pytorch_version) }} + message_format: '{emoji} *{workflow}* {status_message}, see <{run_url}|detail>, cc: <@U02PV6CL144> <@U0355SJN6HK>' # arao & Mythravarun N R + env: + SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }} diff --git a/.github/workflows/events-nightly.yml b/.github/workflows/events-nightly.yml index 0325671413dbb..da7faea7f5471 100644 --- a/.github/workflows/events-nightly.yml +++ b/.github/workflows/events-nightly.yml @@ -59,258 +59,3 @@ jobs: message_format: '{emoji} *{workflow}* {status_message}, see <{run_url}|detail>, cc: <@UR9FXE6QG>' #Borda env: SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }} - - docker-XLA: - if: ${{ github.repository_owner == 'Lightning-AI' }} - runs-on: ubuntu-20.04 - strategy: - fail-fast: false - matrix: - # the config used in '.circleci/config.yml`' - python_version: ["3.7"] - xla_version: ["1.8"] - - steps: - - name: Checkout - uses: actions/checkout@v2 - - # https://github.com/docker/setup-buildx-action - # Set up Docker Buildx - to use cache-from and cache-to argument of buildx command - - uses: docker/setup-buildx-action@v1 - - name: Login to DockerHub - uses: docker/login-action@v1 - with: - username: ${{ secrets.DOCKER_USERNAME }} - password: ${{ secrets.DOCKER_PASSWORD }} - - - name: Publish XLA to Docker Hub - # publish master/release - uses: docker/build-push-action@v2 - with: - build-args: | - PYTHON_VERSION=${{ matrix.python_version }} - XLA_VERSION=${{ matrix.xla_version }} - file: dockers/base-xla/Dockerfile - push: ${{ env.PUSH_TO_HUB }} - tags: pytorchlightning/pytorch_lightning:base-xla-py${{ matrix.python_version }}-torch${{ matrix.xla_version }} - timeout-minutes: 55 - - # report failure to Slack - - name: Slack notification - if: failure() && github.event_name == 'schedule' - uses: ravsamhq/notify-slack-action@v1 - with: - status: ${{ job.status }} - token: ${{ secrets.GITHUB_TOKEN }} - notification_title: ${{ format('XLA; {0} py{1} for *{2}*', runner.os, matrix.python_version, matrix.xla_version) }} - message_format: '{emoji} *{workflow}* {status_message}, see <{run_url}|detail>, cc: <@U01GD29QCAV>' #kaushikb11 - env: - SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }} - - docker-CUDA: - if: ${{ github.repository_owner == 'Lightning-AI' }} - runs-on: ubuntu-20.04 - strategy: - fail-fast: false - matrix: - include: - # the config used in '.azure-pipelines/gpu-tests.yml' - - {python_version: "3.7", pytorch_version: "1.10", cuda_version: "11.1", ubuntu_version: "20.04"} - - {python_version: "3.7", pytorch_version: "1.11", cuda_version: "11.3.1", ubuntu_version: "20.04"} - # latest (used in Tutorials) - - {python_version: "3.8", pytorch_version: "1.9", cuda_version: "11.1", ubuntu_version: "20.04"} - - {python_version: "3.9", pytorch_version: "1.10", cuda_version: "11.1", ubuntu_version: "20.04"} - - {python_version: "3.9", pytorch_version: "1.11", cuda_version: "11.3.1", ubuntu_version: "20.04"} - steps: - - name: Checkout - uses: actions/checkout@v2 - - - uses: docker/setup-buildx-action@v1 - - name: Login to DockerHub - uses: docker/login-action@v1 - with: - username: ${{ secrets.DOCKER_USERNAME }} - password: ${{ secrets.DOCKER_PASSWORD }} - - - name: Publish CUDA to Docker Hub - # publish master/release - uses: docker/build-push-action@v2 - with: - build-args: | - PYTHON_VERSION=${{ matrix.python_version }} - PYTORCH_VERSION=${{ matrix.pytorch_version }} - CUDA_VERSION=${{ matrix.cuda_version }} - UBUNTU_VERSION=${{ matrix.ubuntu_version }} - file: dockers/base-cuda/Dockerfile - push: ${{ env.PUSH_TO_HUB }} - tags: pytorchlightning/pytorch_lightning:base-cuda-py${{ matrix.python_version }}-torch${{ matrix.pytorch_version }} - timeout-minutes: 95 - - # report failure to Slack - - name: Slack notification - if: failure() && github.event_name == 'schedule' - uses: ravsamhq/notify-slack-action@v1 - with: - status: ${{ job.status }} - token: ${{ secrets.GITHUB_TOKEN }} - notification_title: ${{ format('CUDA; {0} py{1} for *{2}*', runner.os, matrix.python_version, matrix.pytorch_version) }} - message_format: '{emoji} *{workflow}* {status_message}, see <{run_url}|detail>, cc: <@U01A5T7EY9M>' #akihironitta - env: - SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }} - - docker-Conda: - if: ${{ github.repository_owner == 'Lightning-AI' }} - runs-on: ubuntu-20.04 - strategy: - fail-fast: false - matrix: - include: - # see: https://pytorch.org/get-started/previous-versions/ - - {python_version: "3.8", pytorch_version: "1.9", cuda_version: "11.1"} - - {python_version: "3.8", pytorch_version: "1.10", cuda_version: "11.1"} - - {python_version: "3.9", pytorch_version: "1.11", cuda_version: "11.3.1"} - # nightly: add when there's a release candidate - # - {python_version: "3.9", pytorch_version: "1.12"} - - steps: - - name: Checkout - uses: actions/checkout@v2 - - - uses: docker/setup-buildx-action@v1 - - name: Login to DockerHub - uses: docker/login-action@v1 - with: - username: ${{ secrets.DOCKER_USERNAME }} - password: ${{ secrets.DOCKER_PASSWORD }} - - - name: Publish Conda to Docker Hub - # publish master/release - uses: docker/build-push-action@v2 - with: - build-args: | - PYTHON_VERSION=${{ matrix.python_version }} - PYTORCH_VERSION=${{ matrix.pytorch_version }} - CUDA_VERSION=${{ matrix.cuda_version }} - file: dockers/base-conda/Dockerfile - push: ${{ env.PUSH_TO_HUB }} - tags: pytorchlightning/pytorch_lightning:base-conda-py${{ matrix.python_version }}-torch${{ matrix.pytorch_version }} - timeout-minutes: 95 - - # report failure to Slack - - name: Slack notification - if: failure() && github.event_name == 'schedule' - uses: ravsamhq/notify-slack-action@v1 - with: - status: ${{ job.status }} - token: ${{ secrets.GITHUB_TOKEN }} - notification_title: ${{ format('Conda; {0} py{1} for *{2}*', runner.os, matrix.python_version, matrix.pytorch_version) }} - message_format: '{emoji} *{workflow}* {status_message}, see <{run_url}|detail>, cc: <@U01A5T7EY9M>' #akihironitta - env: - SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }} - - docker-IPU: - if: ${{ github.repository_owner == 'Lightning-AI' }} - runs-on: ubuntu-20.04 - strategy: - fail-fast: false - matrix: - # the config used in 'dockers/ci-runner-ipu/Dockerfile' - include: - - {python_version: "3.9", pytorch_version: "1.9"} - - steps: - - name: Checkout - uses: actions/checkout@v2 - - # https://github.com/docker/setup-buildx-action - # Set up Docker Buildx - to use cache-from and cache-to argument of buildx command - - uses: docker/setup-buildx-action@v1 - - name: Login to DockerHub - uses: docker/login-action@v1 - with: - username: ${{ secrets.DOCKER_USERNAME }} - password: ${{ secrets.DOCKER_PASSWORD }} - - - name: Publish IPU base to Docker Hub - # publish master/release - uses: docker/build-push-action@v2 - with: - build-args: | - PYTHON_VERSION=${{ matrix.python_version }} - PYTORCH_VERSION=${{ matrix.pytorch_version }} - file: dockers/base-ipu/Dockerfile - push: ${{ env.PUSH_TO_HUB }} - tags: pytorchlightning/pytorch_lightning:base-ipu-py${{ matrix.python_version }}-torch${{ matrix.pytorch_version }} - timeout-minutes: 55 - - - name: Publish IPU CI runner to Docker Hub - # publish master/release - uses: docker/build-push-action@v2 - with: - build-args: | - PYTHON_VERSION=${{ matrix.python_version }} - PYTORCH_VERSION=${{ matrix.pytorch_version }} - file: dockers/ci-runner-ipu/Dockerfile - push: ${{ env.PUSH_TO_HUB }} - tags: pytorchlightning/pytorch_lightning:ipu-ci-runner-py${{ matrix.python_version }} - timeout-minutes: 55 - - # report failure to Slack - - name: Slack notification - if: failure() && github.event_name == 'schedule' - uses: ravsamhq/notify-slack-action@v1 - with: - status: ${{ job.status }} - token: ${{ secrets.GITHUB_TOKEN }} - notification_title: ${{ format('IPU; {0} py{1} for *{2}*', runner.os, matrix.python_version, matrix.pytorch_version) }} - message_format: '{emoji} *{workflow}* {status_message}, see <{run_url}|detail>, cc: <@U01BULUS2BG>' #SeanNaren - env: - SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }} - - docker-HPU: - if: ${{ github.repository_owner == 'Lightning-AI' }} - runs-on: ubuntu-20.04 - strategy: - fail-fast: false - matrix: - # the config used in 'dockers/ci-runner-hpu/Dockerfile' - include: - - {gaudi_version: "1.5.0", pytorch_version: "1.11.0"} - - steps: - - name: Checkout - uses: actions/checkout@v2 - - # https://github.com/docker/setup-buildx-action - # Set up Docker Buildx - to use cache-from and cache-to argument of buildx command - - uses: docker/setup-buildx-action@v1 - - name: Login to DockerHub - uses: docker/login-action@v1 - with: - username: ${{ secrets.DOCKER_USERNAME }} - password: ${{ secrets.DOCKER_PASSWORD }} - - - name: Publish HPU CI runner to Docker Hub - # publish master/release - uses: docker/build-push-action@v2 - with: - build-args: | - DIST=latest - GAUDI_VERSION=${{ matrix.gaudi_version }} - PYTORCH_VERSION=${{ matrix.pytorch_version }} - file: dockers/ci-runner-hpu/Dockerfile - push: ${{ env.PUSH_TO_HUB }} - tags: pytorchlightning/pytorch_lightning:hpu-ci-runner-gaudi${{ matrix.gaudi_version }} - timeout-minutes: 55 - - # report failure to Slack - - name: Slack notification - if: failure() && github.event_name == 'schedule' - uses: ravsamhq/notify-slack-action@v1 - with: - status: ${{ job.status }} - token: ${{ secrets.GITHUB_TOKEN }} - notification_title: ${{ format('HPU; {0} py{1} for *{2}*', runner.os, matrix.gaudi_version, matrix.pytorch_version) }} - message_format: '{emoji} *{workflow}* {status_message}, see <{run_url}|detail>, cc: <@U02PV6CL144> <@U0355SJN6HK>' #arao & Mythravarun N R - env: - SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }} From 3c2d72de4f6a1eab148b8947e6683c64c8bc9ffc Mon Sep 17 00:00:00 2001 From: Akihiro Nitta Date: Fri, 8 Jul 2022 17:07:36 +0900 Subject: [PATCH 03/13] push: bool expression --- .github/workflows/ci-pytorch_dockers.yml | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/.github/workflows/ci-pytorch_dockers.yml b/.github/workflows/ci-pytorch_dockers.yml index 247ba476697d6..d8f50b9c99aa6 100644 --- a/.github/workflows/ci-pytorch_dockers.yml +++ b/.github/workflows/ci-pytorch_dockers.yml @@ -67,7 +67,7 @@ jobs: PYTHON_VERSION=${{ matrix.python_version }} XLA_VERSION=${{ matrix.xla_version }} file: dockers/base-xla/Dockerfile - push: github.event_name == 'schedule' + push: ${{ github.event_name == 'schedule' }} tags: pytorchlightning/pytorch_lightning:base-xla-py${{ matrix.python_version }}-torch${{ matrix.xla_version }} timeout-minutes: 60 - uses: ravsamhq/notify-slack-action@v1 @@ -109,7 +109,7 @@ jobs: CUDA_VERSION=${{ matrix.cuda_version }} UBUNTU_VERSION=${{ matrix.ubuntu_version }} file: dockers/base-cuda/Dockerfile - push: github.event_name == 'schedule' + push: ${{ github.event_name == 'schedule' }} tags: pytorchlightning/pytorch_lightning:base-cuda-py${{ matrix.python_version }}-torch${{ matrix.pytorch_version }} timeout-minutes: 95 - uses: ravsamhq/notify-slack-action@v1 @@ -148,7 +148,7 @@ jobs: PYTORCH_VERSION=${{ matrix.pytorch_version }} CUDA_VERSION=${{ matrix.cuda_version }} file: dockers/base-conda/Dockerfile - push: github.event_name == 'schedule' + push: ${{ github.event_name == 'schedule' }} tags: pytorchlightning/pytorch_lightning:base-conda-py${{ matrix.python_version }}-torch${{ matrix.pytorch_version }} timeout-minutes: 95 - uses: ravsamhq/notify-slack-action@v1 @@ -182,7 +182,7 @@ jobs: PYTHON_VERSION=${{ matrix.python_version }} PYTORCH_VERSION=${{ matrix.pytorch_version }} file: dockers/base-ipu/Dockerfile - push: github.event_name == 'schedule' + push: ${{ github.event_name == 'schedule' }} tags: pytorchlightning/pytorch_lightning:base-ipu-py${{ matrix.python_version }}-torch${{ matrix.pytorch_version }} timeout-minutes: 50 - uses: docker/build-push-action@v2 @@ -191,7 +191,7 @@ jobs: PYTHON_VERSION=${{ matrix.python_version }} PYTORCH_VERSION=${{ matrix.pytorch_version }} file: dockers/ci-runner-ipu/Dockerfile - push: github.event_name == 'schedule' + push: ${{ github.event_name == 'schedule' }} tags: pytorchlightning/pytorch_lightning:ipu-ci-runner-py${{ matrix.python_version }} timeout-minutes: 55 - uses: ravsamhq/notify-slack-action@v1 @@ -227,7 +227,7 @@ jobs: GAUDI_VERSION=${{ matrix.gaudi_version }} PYTORCH_VERSION=${{ matrix.pytorch_version }} file: dockers/ci-runner-hpu/Dockerfile - push: false + push: ${{ github.event_name == 'schedule' }} tags: pytorchlightning/pytorch_lightning:hpu-ci-runner-gaudi${{ matrix.gaudi_version }} timeout-minutes: 55 - uses: ravsamhq/notify-slack-action@v1 From b582ed91813d07017cba0885d9b066e187960295 Mon Sep 17 00:00:00 2001 From: Akihiro Nitta Date: Fri, 8 Jul 2022 18:23:23 +0900 Subject: [PATCH 04/13] Extend timeout for ipu builds --- .github/workflows/ci-pytorch_dockers.yml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/.github/workflows/ci-pytorch_dockers.yml b/.github/workflows/ci-pytorch_dockers.yml index d8f50b9c99aa6..623bf9281a13d 100644 --- a/.github/workflows/ci-pytorch_dockers.yml +++ b/.github/workflows/ci-pytorch_dockers.yml @@ -184,7 +184,7 @@ jobs: file: dockers/base-ipu/Dockerfile push: ${{ github.event_name == 'schedule' }} tags: pytorchlightning/pytorch_lightning:base-ipu-py${{ matrix.python_version }}-torch${{ matrix.pytorch_version }} - timeout-minutes: 50 + timeout-minutes: 120 - uses: docker/build-push-action@v2 with: build-args: | @@ -193,7 +193,7 @@ jobs: file: dockers/ci-runner-ipu/Dockerfile push: ${{ github.event_name == 'schedule' }} tags: pytorchlightning/pytorch_lightning:ipu-ci-runner-py${{ matrix.python_version }} - timeout-minutes: 55 + timeout-minutes: 120 - uses: ravsamhq/notify-slack-action@v1 if: failure() && github.event_name == 'schedule' with: From 53584ab85e28fa14f27bb02c032030c0b002c513 Mon Sep 17 00:00:00 2001 From: Akihiro Nitta Date: Fri, 8 Jul 2022 18:24:37 +0900 Subject: [PATCH 05/13] Update concurrency group --- .github/workflows/ci-pytorch_dockers.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/ci-pytorch_dockers.yml b/.github/workflows/ci-pytorch_dockers.yml index 623bf9281a13d..02c49f7376d8e 100644 --- a/.github/workflows/ci-pytorch_dockers.yml +++ b/.github/workflows/ci-pytorch_dockers.yml @@ -22,7 +22,7 @@ on: - cron: "0 0 * * *" # at the end of every day concurrency: - group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref }} + group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref }}-${{ github.event_name }} cancel-in-progress: ${{ ! (github.ref == 'refs/heads/master' || startsWith(github.ref, 'refs/heads/release/')) }} jobs: From c55d167bcebcfa3c0da13459d28479afc6688237 Mon Sep 17 00:00:00 2001 From: Akihiro Nitta Date: Fri, 8 Jul 2022 18:40:00 +0900 Subject: [PATCH 06/13] Define env for push to hub --- .github/workflows/ci-pytorch_dockers.yml | 36 +++++++++++++----------- 1 file changed, 20 insertions(+), 16 deletions(-) diff --git a/.github/workflows/ci-pytorch_dockers.yml b/.github/workflows/ci-pytorch_dockers.yml index 02c49f7376d8e..8da9804d05c62 100644 --- a/.github/workflows/ci-pytorch_dockers.yml +++ b/.github/workflows/ci-pytorch_dockers.yml @@ -25,6 +25,9 @@ concurrency: group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref }}-${{ github.event_name }} cancel-in-progress: ${{ ! (github.ref == 'refs/heads/master' || startsWith(github.ref, 'refs/heads/release/')) }} +env: + PUSH_TO_HUB: ${{ github.event_name == 'schedule' }} + jobs: pl: runs-on: ubuntu-20.04 @@ -57,7 +60,7 @@ jobs: - uses: actions/checkout@v2 - uses: docker/setup-buildx-action@v1 - uses: docker/login-action@v1 - if: github.event_name == 'schedule' + if: ${{ env.PUSH_TO_HUB }} with: username: ${{ secrets.DOCKER_USERNAME }} password: ${{ secrets.DOCKER_PASSWORD }} @@ -67,11 +70,11 @@ jobs: PYTHON_VERSION=${{ matrix.python_version }} XLA_VERSION=${{ matrix.xla_version }} file: dockers/base-xla/Dockerfile - push: ${{ github.event_name == 'schedule' }} + push: ${{ env.PUSH_TO_HUB }} tags: pytorchlightning/pytorch_lightning:base-xla-py${{ matrix.python_version }}-torch${{ matrix.xla_version }} timeout-minutes: 60 - uses: ravsamhq/notify-slack-action@v1 - if: failure() && github.event_name == 'schedule' + if: failure() && ${{ env.PUSH_TO_HUB }} with: status: ${{ job.status }} token: ${{ secrets.GITHUB_TOKEN }} @@ -97,7 +100,7 @@ jobs: - uses: actions/checkout@v2 - uses: docker/setup-buildx-action@v1 - uses: docker/login-action@v1 - if: github.event_name == 'schedule' + if: ${{ env.PUSH_TO_HUB }} with: username: ${{ secrets.DOCKER_USERNAME }} password: ${{ secrets.DOCKER_PASSWORD }} @@ -109,11 +112,11 @@ jobs: CUDA_VERSION=${{ matrix.cuda_version }} UBUNTU_VERSION=${{ matrix.ubuntu_version }} file: dockers/base-cuda/Dockerfile - push: ${{ github.event_name == 'schedule' }} + push: ${{ env.PUSH_TO_HUB }} tags: pytorchlightning/pytorch_lightning:base-cuda-py${{ matrix.python_version }}-torch${{ matrix.pytorch_version }} timeout-minutes: 95 - uses: ravsamhq/notify-slack-action@v1 - if: failure() && github.event_name == 'schedule' + if: failure() && ${{ env.PUSH_TO_HUB }} with: status: ${{ job.status }} token: ${{ secrets.GITHUB_TOKEN }} @@ -137,7 +140,7 @@ jobs: - uses: actions/checkout@v2 - uses: docker/setup-buildx-action@v1 - uses: docker/login-action@v1 - if: github.event_name == 'schedule' + if: ${{ env.PUSH_TO_HUB }} with: username: ${{ secrets.DOCKER_USERNAME }} password: ${{ secrets.DOCKER_PASSWORD }} @@ -148,11 +151,11 @@ jobs: PYTORCH_VERSION=${{ matrix.pytorch_version }} CUDA_VERSION=${{ matrix.cuda_version }} file: dockers/base-conda/Dockerfile - push: ${{ github.event_name == 'schedule' }} + push: ${{ env.PUSH_TO_HUB }} tags: pytorchlightning/pytorch_lightning:base-conda-py${{ matrix.python_version }}-torch${{ matrix.pytorch_version }} timeout-minutes: 95 - uses: ravsamhq/notify-slack-action@v1 - if: failure() && github.event_name == 'schedule' + if: failure() && ${{ env.PUSH_TO_HUB }} with: status: ${{ job.status }} token: ${{ secrets.GITHUB_TOKEN }} @@ -173,6 +176,7 @@ jobs: - uses: actions/checkout@v2 - uses: docker/setup-buildx-action@v1 - uses: docker/login-action@v1 + if: ${{ env.PUSH_TO_HUB }} with: username: ${{ secrets.DOCKER_USERNAME }} password: ${{ secrets.DOCKER_PASSWORD }} @@ -182,7 +186,7 @@ jobs: PYTHON_VERSION=${{ matrix.python_version }} PYTORCH_VERSION=${{ matrix.pytorch_version }} file: dockers/base-ipu/Dockerfile - push: ${{ github.event_name == 'schedule' }} + push: ${{ env.PUSH_TO_HUB }} tags: pytorchlightning/pytorch_lightning:base-ipu-py${{ matrix.python_version }}-torch${{ matrix.pytorch_version }} timeout-minutes: 120 - uses: docker/build-push-action@v2 @@ -191,11 +195,11 @@ jobs: PYTHON_VERSION=${{ matrix.python_version }} PYTORCH_VERSION=${{ matrix.pytorch_version }} file: dockers/ci-runner-ipu/Dockerfile - push: ${{ github.event_name == 'schedule' }} + push: ${{ env.PUSH_TO_HUB }} tags: pytorchlightning/pytorch_lightning:ipu-ci-runner-py${{ matrix.python_version }} timeout-minutes: 120 - uses: ravsamhq/notify-slack-action@v1 - if: failure() && github.event_name == 'schedule' + if: failure() && ${{ env.PUSH_TO_HUB }} with: status: ${{ job.status }} token: ${{ secrets.GITHUB_TOKEN }} @@ -215,8 +219,8 @@ jobs: steps: - uses: actions/checkout@v2 - uses: docker/setup-buildx-action@v1 - - name: Login to DockerHub - uses: docker/login-action@v1 + - uses: docker/login-action@v1 + if: ${{ env.PUSH_TO_HUB }} with: username: ${{ secrets.DOCKER_USERNAME }} password: ${{ secrets.DOCKER_PASSWORD }} @@ -227,11 +231,11 @@ jobs: GAUDI_VERSION=${{ matrix.gaudi_version }} PYTORCH_VERSION=${{ matrix.pytorch_version }} file: dockers/ci-runner-hpu/Dockerfile - push: ${{ github.event_name == 'schedule' }} + push: ${{ env.PUSH_TO_HUB }} tags: pytorchlightning/pytorch_lightning:hpu-ci-runner-gaudi${{ matrix.gaudi_version }} timeout-minutes: 55 - uses: ravsamhq/notify-slack-action@v1 - if: failure() && github.event_name == 'schedule' + if: failure() && ${{ env.PUSH_TO_HUB }} with: status: ${{ job.status }} token: ${{ secrets.GITHUB_TOKEN }} From 05f5b00a5e72969e2bae14d8d5248dc96d1d7b67 Mon Sep 17 00:00:00 2001 From: Akihiro Nitta Date: Fri, 8 Jul 2022 18:40:41 +0900 Subject: [PATCH 07/13] Rename workflow --- .github/workflows/ci-pytorch_dockers.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/ci-pytorch_dockers.yml b/.github/workflows/ci-pytorch_dockers.yml index 8da9804d05c62..84c428ddc559e 100644 --- a/.github/workflows/ci-pytorch_dockers.yml +++ b/.github/workflows/ci-pytorch_dockers.yml @@ -1,4 +1,4 @@ -name: Docker - PyTorch +name: Docker on: push: From 748a6e81c2a6d30597e9ba503d828cdb6516f553 Mon Sep 17 00:00:00 2001 From: Akihiro Nitta Date: Sat, 9 Jul 2022 15:29:03 +0900 Subject: [PATCH 08/13] Fix bool expressions --- .github/workflows/ci-pytorch_dockers.yml | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) diff --git a/.github/workflows/ci-pytorch_dockers.yml b/.github/workflows/ci-pytorch_dockers.yml index 84c428ddc559e..02e3e63c31aef 100644 --- a/.github/workflows/ci-pytorch_dockers.yml +++ b/.github/workflows/ci-pytorch_dockers.yml @@ -39,6 +39,7 @@ jobs: pytorch_version: ["1.10", "1.11"] steps: - uses: actions/checkout@v2 + - uses: docker/setup-buildx-action@v1 - uses: docker/build-push-action@v2 with: build-args: | @@ -60,7 +61,7 @@ jobs: - uses: actions/checkout@v2 - uses: docker/setup-buildx-action@v1 - uses: docker/login-action@v1 - if: ${{ env.PUSH_TO_HUB }} + if: env.PUSH_TO_HUB == 'true' with: username: ${{ secrets.DOCKER_USERNAME }} password: ${{ secrets.DOCKER_PASSWORD }} @@ -74,7 +75,7 @@ jobs: tags: pytorchlightning/pytorch_lightning:base-xla-py${{ matrix.python_version }}-torch${{ matrix.xla_version }} timeout-minutes: 60 - uses: ravsamhq/notify-slack-action@v1 - if: failure() && ${{ env.PUSH_TO_HUB }} + if: failure() && env.PUSH_TO_HUB == 'true' with: status: ${{ job.status }} token: ${{ secrets.GITHUB_TOKEN }} @@ -100,7 +101,7 @@ jobs: - uses: actions/checkout@v2 - uses: docker/setup-buildx-action@v1 - uses: docker/login-action@v1 - if: ${{ env.PUSH_TO_HUB }} + if: env.PUSH_TO_HUB == 'true' with: username: ${{ secrets.DOCKER_USERNAME }} password: ${{ secrets.DOCKER_PASSWORD }} @@ -116,7 +117,7 @@ jobs: tags: pytorchlightning/pytorch_lightning:base-cuda-py${{ matrix.python_version }}-torch${{ matrix.pytorch_version }} timeout-minutes: 95 - uses: ravsamhq/notify-slack-action@v1 - if: failure() && ${{ env.PUSH_TO_HUB }} + if: failure() && env.PUSH_TO_HUB == 'true' with: status: ${{ job.status }} token: ${{ secrets.GITHUB_TOKEN }} @@ -140,7 +141,7 @@ jobs: - uses: actions/checkout@v2 - uses: docker/setup-buildx-action@v1 - uses: docker/login-action@v1 - if: ${{ env.PUSH_TO_HUB }} + if: env.PUSH_TO_HUB == 'true' with: username: ${{ secrets.DOCKER_USERNAME }} password: ${{ secrets.DOCKER_PASSWORD }} @@ -155,7 +156,7 @@ jobs: tags: pytorchlightning/pytorch_lightning:base-conda-py${{ matrix.python_version }}-torch${{ matrix.pytorch_version }} timeout-minutes: 95 - uses: ravsamhq/notify-slack-action@v1 - if: failure() && ${{ env.PUSH_TO_HUB }} + if: failure() && env.PUSH_TO_HUB == 'true' with: status: ${{ job.status }} token: ${{ secrets.GITHUB_TOKEN }} @@ -176,7 +177,7 @@ jobs: - uses: actions/checkout@v2 - uses: docker/setup-buildx-action@v1 - uses: docker/login-action@v1 - if: ${{ env.PUSH_TO_HUB }} + if: env.PUSH_TO_HUB == 'true' with: username: ${{ secrets.DOCKER_USERNAME }} password: ${{ secrets.DOCKER_PASSWORD }} @@ -199,7 +200,7 @@ jobs: tags: pytorchlightning/pytorch_lightning:ipu-ci-runner-py${{ matrix.python_version }} timeout-minutes: 120 - uses: ravsamhq/notify-slack-action@v1 - if: failure() && ${{ env.PUSH_TO_HUB }} + if: failure() && env.PUSH_TO_HUB == 'true' with: status: ${{ job.status }} token: ${{ secrets.GITHUB_TOKEN }} @@ -220,7 +221,7 @@ jobs: - uses: actions/checkout@v2 - uses: docker/setup-buildx-action@v1 - uses: docker/login-action@v1 - if: ${{ env.PUSH_TO_HUB }} + if: env.PUSH_TO_HUB == 'true' with: username: ${{ secrets.DOCKER_USERNAME }} password: ${{ secrets.DOCKER_PASSWORD }} @@ -235,7 +236,7 @@ jobs: tags: pytorchlightning/pytorch_lightning:hpu-ci-runner-gaudi${{ matrix.gaudi_version }} timeout-minutes: 55 - uses: ravsamhq/notify-slack-action@v1 - if: failure() && ${{ env.PUSH_TO_HUB }} + if: failure() && env.PUSH_TO_HUB == 'true' with: status: ${{ job.status }} token: ${{ secrets.GITHUB_TOKEN }} From 89b59018513968fb9fb8cbfaf8b448596a27af2d Mon Sep 17 00:00:00 2001 From: Akihiro Nitta Date: Sat, 9 Jul 2022 15:33:19 +0900 Subject: [PATCH 09/13] Remove unnecessary trigger paths --- .github/workflows/ci-pytorch_dockers.yml | 4 ---- 1 file changed, 4 deletions(-) diff --git a/.github/workflows/ci-pytorch_dockers.yml b/.github/workflows/ci-pytorch_dockers.yml index 02e3e63c31aef..e4a8d81a02f8a 100644 --- a/.github/workflows/ci-pytorch_dockers.yml +++ b/.github/workflows/ci-pytorch_dockers.yml @@ -6,10 +6,6 @@ on: pull_request: branches: [master, "release/*"] paths: - - "!src/lightning_app/**" # todo: implement job skip - - "!tests/tests_app/**" # todo: implement job skip - - "!tests/tests_app_examples/**" # todo: implement job skip - - "!examples/app_*" # todo: implement job skip - "dockers/**" - "!dockers/README.md" - "requirements/*" From 681b1ed0cc642d74a84efcfc751c0b803104fd2b Mon Sep 17 00:00:00 2001 From: Akihiro Nitta Date: Sat, 9 Jul 2022 15:34:28 +0900 Subject: [PATCH 10/13] Remove unused env var --- .github/workflows/events-nightly.yml | 3 --- 1 file changed, 3 deletions(-) diff --git a/.github/workflows/events-nightly.yml b/.github/workflows/events-nightly.yml index da7faea7f5471..9279b95c767ec 100644 --- a/.github/workflows/events-nightly.yml +++ b/.github/workflows/events-nightly.yml @@ -7,9 +7,6 @@ on: # At the end of every day - cron: "0 0 * * *" -env: - PUSH_TO_HUB: true - # based on https://github.com/pypa/gh-action-pypi-publish jobs: pypi-release: From 177b227e22e5cbbaed23d4f1f539af4a5179d728 Mon Sep 17 00:00:00 2001 From: Akihiro Nitta Date: Sun, 10 Jul 2022 12:08:26 +0900 Subject: [PATCH 11/13] Update job names --- .github/workflows/ci-pytorch_dockers.yml | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/.github/workflows/ci-pytorch_dockers.yml b/.github/workflows/ci-pytorch_dockers.yml index e4a8d81a02f8a..f257318b6398d 100644 --- a/.github/workflows/ci-pytorch_dockers.yml +++ b/.github/workflows/ci-pytorch_dockers.yml @@ -25,7 +25,7 @@ env: PUSH_TO_HUB: ${{ github.event_name == 'schedule' }} jobs: - pl: + build-pl: runs-on: ubuntu-20.04 strategy: fail-fast: false @@ -45,7 +45,7 @@ jobs: push: false # pushed in release-docker.yml only when PL is released timeout-minutes: 50 - xla: + build-xla: runs-on: ubuntu-20.04 strategy: fail-fast: false @@ -80,7 +80,7 @@ jobs: env: SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }} - cuda: + build-cuda: runs-on: ubuntu-20.04 strategy: fail-fast: false @@ -122,7 +122,7 @@ jobs: env: SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }} - conda: + build-conda: runs-on: ubuntu-20.04 strategy: fail-fast: false @@ -161,7 +161,7 @@ jobs: env: SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }} - ipu: + build-ipu: runs-on: ubuntu-20.04 strategy: fail-fast: false @@ -205,7 +205,7 @@ jobs: env: SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }} - hpu: + build-hpu: runs-on: ubuntu-20.04 strategy: fail-fast: false From f6d83d8401cc0dde2473b36a5a2268dd531533ac Mon Sep 17 00:00:00 2001 From: Akihiro Nitta Date: Sun, 10 Jul 2022 12:15:38 +0900 Subject: [PATCH 12/13] Trim timeout --- .github/workflows/ci-pytorch_dockers.yml | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/.github/workflows/ci-pytorch_dockers.yml b/.github/workflows/ci-pytorch_dockers.yml index f257318b6398d..317d005bd89f1 100644 --- a/.github/workflows/ci-pytorch_dockers.yml +++ b/.github/workflows/ci-pytorch_dockers.yml @@ -185,7 +185,7 @@ jobs: file: dockers/base-ipu/Dockerfile push: ${{ env.PUSH_TO_HUB }} tags: pytorchlightning/pytorch_lightning:base-ipu-py${{ matrix.python_version }}-torch${{ matrix.pytorch_version }} - timeout-minutes: 120 + timeout-minutes: 100 - uses: docker/build-push-action@v2 with: build-args: | @@ -194,7 +194,7 @@ jobs: file: dockers/ci-runner-ipu/Dockerfile push: ${{ env.PUSH_TO_HUB }} tags: pytorchlightning/pytorch_lightning:ipu-ci-runner-py${{ matrix.python_version }} - timeout-minutes: 120 + timeout-minutes: 10 - uses: ravsamhq/notify-slack-action@v1 if: failure() && env.PUSH_TO_HUB == 'true' with: @@ -230,7 +230,7 @@ jobs: file: dockers/ci-runner-hpu/Dockerfile push: ${{ env.PUSH_TO_HUB }} tags: pytorchlightning/pytorch_lightning:hpu-ci-runner-gaudi${{ matrix.gaudi_version }} - timeout-minutes: 55 + timeout-minutes: 10 - uses: ravsamhq/notify-slack-action@v1 if: failure() && env.PUSH_TO_HUB == 'true' with: From 44536ac53a991bec146f3f4be6ea8fd303ca2f01 Mon Sep 17 00:00:00 2001 From: Jirka Date: Mon, 11 Jul 2022 23:30:26 +0200 Subject: [PATCH 13/13] rename --- .../{ci-pytorch_dockers.yml => cicd-pytorch_dockers.yml} | 0 1 file changed, 0 insertions(+), 0 deletions(-) rename .github/workflows/{ci-pytorch_dockers.yml => cicd-pytorch_dockers.yml} (100%) diff --git a/.github/workflows/ci-pytorch_dockers.yml b/.github/workflows/cicd-pytorch_dockers.yml similarity index 100% rename from .github/workflows/ci-pytorch_dockers.yml rename to .github/workflows/cicd-pytorch_dockers.yml