From 1353b00df2d3e1c3a675ee70b5a618b17fbfc67f Mon Sep 17 00:00:00 2001 From: JackCaoG Date: Fri, 18 Oct 2024 19:22:20 +0000 Subject: [PATCH 1/2] disable GPU tests and build --- .github/workflows/build_and_test.yml | 78 ++++++++++++++-------------- 1 file changed, 39 insertions(+), 39 deletions(-) diff --git a/.github/workflows/build_and_test.yml b/.github/workflows/build_and_test.yml index 8576c908e0a5..86f5da94a7e4 100644 --- a/.github/workflows/build_and_test.yml +++ b/.github/workflows/build_and_test.yml @@ -40,23 +40,23 @@ jobs: secrets: gcloud-service-key: ${{ secrets.GCLOUD_SERVICE_KEY }} - build-torch-with-cuda: - name: "Build PyTorch with CUDA" - uses: ./.github/workflows/_build_torch_with_cuda.yml - needs: get-torch-commit - with: - # note that to build a torch wheel with CUDA enabled, we do not need a GPU runner. - dev-image: us-central1-docker.pkg.dev/tpu-pytorch-releases/docker/development:3.10_cuda_12.1 - torch-commit: ${{needs.get-torch-commit.outputs.torch_commit}} - runner: linux.24xlarge + # build-torch-with-cuda: + # name: "Build PyTorch with CUDA" + # uses: ./.github/workflows/_build_torch_with_cuda.yml + # needs: get-torch-commit + # with: + # # note that to build a torch wheel with CUDA enabled, we do not need a GPU runner. + # dev-image: us-central1-docker.pkg.dev/tpu-pytorch-releases/docker/development:3.10_cuda_12.1 + # torch-commit: ${{needs.get-torch-commit.outputs.torch_commit}} + # runner: linux.24xlarge - build-cuda-plugin: - name: "Build XLA CUDA plugin" - uses: ./.github/workflows/_build_plugin.yml - with: - dev-image: us-central1-docker.pkg.dev/tpu-pytorch-releases/docker/development:3.10_cuda_12.1 - secrets: - gcloud-service-key: ${{ secrets.GCLOUD_SERVICE_KEY }} + # build-cuda-plugin: + # name: "Build XLA CUDA plugin" + # uses: ./.github/workflows/_build_plugin.yml + # with: + # dev-image: us-central1-docker.pkg.dev/tpu-pytorch-releases/docker/development:3.10_cuda_12.1 + # secrets: + # gcloud-service-key: ${{ secrets.GCLOUD_SERVICE_KEY }} test-python-cpu: name: "CPU tests" @@ -70,30 +70,30 @@ jobs: secrets: gcloud-service-key: ${{ secrets.GCLOUD_SERVICE_KEY }} - test-cuda: - name: "GPU tests" - uses: ./.github/workflows/_test.yml - needs: [build-torch-xla, build-cuda-plugin, get-torch-commit] - with: - dev-image: us-central1-docker.pkg.dev/tpu-pytorch-releases/docker/development:3.10_cuda_12.1 - runner: linux.8xlarge.nvidia.gpu - timeout-minutes: 300 - collect-coverage: false - install-cuda-plugin: true - torch-commit: ${{needs.get-torch-commit.outputs.torch_commit}} - secrets: - gcloud-service-key: ${{ secrets.GCLOUD_SERVICE_KEY }} + # test-cuda: + # name: "GPU tests" + # uses: ./.github/workflows/_test.yml + # needs: [build-torch-xla, build-cuda-plugin, get-torch-commit] + # with: + # dev-image: us-central1-docker.pkg.dev/tpu-pytorch-releases/docker/development:3.10_cuda_12.1 + # runner: linux.8xlarge.nvidia.gpu + # timeout-minutes: 300 + # collect-coverage: false + # install-cuda-plugin: true + # torch-commit: ${{needs.get-torch-commit.outputs.torch_commit}} + # secrets: + # gcloud-service-key: ${{ secrets.GCLOUD_SERVICE_KEY }} - test-cuda-with-pytorch-cuda-enabled: - name: "GPU tests requiring torch CUDA" - uses: ./.github/workflows/_test_requiring_torch_cuda.yml - needs: [build-torch-with-cuda, build-torch-xla, build-cuda-plugin, get-torch-commit] - with: - dev-image: us-central1-docker.pkg.dev/tpu-pytorch-releases/docker/development:3.10_cuda_12.1 - runner: linux.8xlarge.nvidia.gpu - timeout-minutes: 300 - collect-coverage: false - torch-commit: ${{needs.get-torch-commit.outputs.torch_commit}} + # test-cuda-with-pytorch-cuda-enabled: + # name: "GPU tests requiring torch CUDA" + # uses: ./.github/workflows/_test_requiring_torch_cuda.yml + # needs: [build-torch-with-cuda, build-torch-xla, build-cuda-plugin, get-torch-commit] + # with: + # dev-image: us-central1-docker.pkg.dev/tpu-pytorch-releases/docker/development:3.10_cuda_12.1 + # runner: linux.8xlarge.nvidia.gpu + # timeout-minutes: 300 + # collect-coverage: false + # torch-commit: ${{needs.get-torch-commit.outputs.torch_commit}} test-tpu: name: "TPU tests" From 7bee0e78c4046a71b5a6ca606589e3f582336486 Mon Sep 17 00:00:00 2001 From: JackCaoG Date: Fri, 18 Oct 2024 20:22:34 +0000 Subject: [PATCH 2/2] add link to the github issue --- .github/workflows/build_and_test.yml | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/.github/workflows/build_and_test.yml b/.github/workflows/build_and_test.yml index 86f5da94a7e4..9ae26c047cfc 100644 --- a/.github/workflows/build_and_test.yml +++ b/.github/workflows/build_and_test.yml @@ -40,6 +40,7 @@ jobs: secrets: gcloud-service-key: ${{ secrets.GCLOUD_SERVICE_KEY }} + # Disable due to https://github.com/pytorch/xla/issues/8199 # build-torch-with-cuda: # name: "Build PyTorch with CUDA" # uses: ./.github/workflows/_build_torch_with_cuda.yml @@ -50,6 +51,7 @@ jobs: # torch-commit: ${{needs.get-torch-commit.outputs.torch_commit}} # runner: linux.24xlarge + # Disable due to https://github.com/pytorch/xla/issues/8199 # build-cuda-plugin: # name: "Build XLA CUDA plugin" # uses: ./.github/workflows/_build_plugin.yml @@ -70,6 +72,7 @@ jobs: secrets: gcloud-service-key: ${{ secrets.GCLOUD_SERVICE_KEY }} + # Disable due to https://github.com/pytorch/xla/issues/8199 # test-cuda: # name: "GPU tests" # uses: ./.github/workflows/_test.yml @@ -84,6 +87,7 @@ jobs: # secrets: # gcloud-service-key: ${{ secrets.GCLOUD_SERVICE_KEY }} + # Disable due to https://github.com/pytorch/xla/issues/8199 # test-cuda-with-pytorch-cuda-enabled: # name: "GPU tests requiring torch CUDA" # uses: ./.github/workflows/_test_requiring_torch_cuda.yml