diff --git a/.azure/ipu-tests.yml b/.azure/ipu-tests.yml index ae52037f60..f04547531a 100644 --- a/.azure/ipu-tests.yml +++ b/.azure/ipu-tests.yml @@ -43,23 +43,31 @@ variables: jobs: - job: testing # how long to run the job before automatically cancelling - timeoutInMinutes: "15" + timeoutInMinutes: "20" pool: graphcore-ipus workspace: clean: all steps: - - script: | - ls -la /mnt/public/packages - ls -la /opt/poplar - tar -xvzf /opt/poplar/${{ variables.poplar_sdk }}.tar.gz - displayName: "Extract Poplar SDK" - script: | set -eux + # ls -la /mnt/public/packages + ls -la /opt/poplar + tar -xzf /opt/poplar/${{ variables.poplar_sdk }}.tar.gz pip debug --verbose pip install ${{ variables.poplar_sdk }}/poptorch-*ubuntu*.whl - displayName: "Install poptorch" + displayName: "Poplar SDK: Extract & Install" + + - bash: | + # enable scripts basically just set/modify some environment variables + source ${{ variables.poplar_sdk }}/poplar-ubuntu*/enable.sh + gc-info --list-devices + printenv + python --version + pip --version + pip list + displayName: 'Image info & GraphCore' - script: | set -eux @@ -78,17 +86,18 @@ jobs: displayName: "Reset IPU devices" - bash: | - for fpath in `ls requirements/**/*.txt`; do \ + for fpath in `ls requirements/pytorch/*.txt`; do \ python ./requirements/pytorch/adjust-versions.py $fpath; \ done - pip install -e .[extra,examples,test] + pip install .[test] -f /mnt/public/packages + pip uninstall -y neptune-client # it is not clear what version is compatible pip list env: PACKAGE_NAME: "pytorch" FREEZE_REQUIREMENTS: "1" GIT_TERMINAL_PROMPT: "1" - displayName: 'Install dependencies' + displayName: 'Install package & dependencies' - bash: | python requirements/collect_env_details.py diff --git a/.github/checkgroup.yml b/.github/checkgroup.yml index 96e2d520a2..6b2a0d872a 100644 --- a/.github/checkgroup.yml +++ b/.github/checkgroup.yml @@ -173,7 +173,7 @@ subprojects: - "build-cuda (3.9, 1.12, 11.6.1)" - "build-cuda (3.9, 1.13, 11.7.1)" - "build-cuda (3.10, 2.0, 11.7.1)" - - "build-ipu (3.9, 1.13)" + - "build-ipu (3.8, 1.13)" - "build-NGC" - "build-pl (3.9, 1.11, 11.3.1)" - "build-pl (3.9, 1.12, 11.6.1)" diff --git a/.github/workflows/ci-dockers-pytorch.yml b/.github/workflows/ci-dockers-pytorch.yml index 0b9e5eb4c2..dc88facdb6 100644 --- a/.github/workflows/ci-dockers-pytorch.yml +++ b/.github/workflows/ci-dockers-pytorch.yml @@ -145,7 +145,7 @@ jobs: matrix: include: # the config used in 'dockers/ci-runner-ipu/Dockerfile' - - {python_version: "3.9", pytorch_version: "1.13"} + - {python_version: "3.8", pytorch_version: "1.13"} steps: - uses: actions/checkout@v3 - uses: docker/setup-buildx-action@v2 diff --git a/.github/workflows/ci-tests-pytorch.yml b/.github/workflows/ci-tests-pytorch.yml index 711cfa7194..42b9ab49bc 100644 --- a/.github/workflows/ci-tests-pytorch.yml +++ b/.github/workflows/ci-tests-pytorch.yml @@ -116,7 +116,9 @@ jobs: - name: Install package & dependencies run: | pip install -q pip -U - pip install .[extra,test] -U "pytest-timeout" -f ${TORCH_URL} ${TORCH_PREINSTALL} -f ${PYPI_CACHE} --prefer-binary + pip install .[extra,test] -U \ + "pytest-timeout" -r requirements/_integrations/accelerators.txt \ + -f ${TORCH_URL} ${TORCH_PREINSTALL} -f ${PYPI_CACHE} --prefer-binary pip list - name: Dump handy wheels if: github.event_name == 'push' && github.ref == 'refs/heads/master' diff --git a/requirements/_integrations/accelerators.txt b/requirements/_integrations/accelerators.txt new file mode 100644 index 0000000000..63b91bf9f2 --- /dev/null +++ b/requirements/_integrations/accelerators.txt @@ -0,0 +1,2 @@ +# validation HPU connectors +lightning-habana>=0.1.0rc0 diff --git a/requirements/pytorch/adjust-versions.py b/requirements/pytorch/adjust-versions.py index a7bced8273..07c1e34c6f 100644 --- a/requirements/pytorch/adjust-versions.py +++ b/requirements/pytorch/adjust-versions.py @@ -20,7 +20,7 @@ def find_latest(ver: str) -> Dict[str, str]: ver = re.search(r"([\.\d]+)", ver).groups()[0] # in case there remaining dot at the end - e.g "1.9.0.dev20210504" ver = ver[:-1] if ver[-1] == "." else ver - print(f"finding ecosystem versions for: {ver}") + print(f"\n\n\nfinding ecosystem versions for: {ver}") # find first match for option in VERSIONS: diff --git a/requirements/pytorch/test.txt b/requirements/pytorch/test.txt index fff7bc13af..32c37321fe 100644 --- a/requirements/pytorch/test.txt +++ b/requirements/pytorch/test.txt @@ -18,6 +18,3 @@ uvicorn<0.19.1 # for `ServableModuleValidator` tensorboard>=2.9.1, <2.12.0 # for `TensorBoardLogger` protobuf<=3.20.1 # strict # an extra is updating protobuf, this pin prevents TensorBoard failure - -# validation HPU connectors -lightning-habana>=0.1.0rc0 diff --git a/src/lightning/pytorch/loggers/neptune.py b/src/lightning/pytorch/loggers/neptune.py index 6bb206d807..07c8acb1a0 100644 --- a/src/lightning/pytorch/loggers/neptune.py +++ b/src/lightning/pytorch/loggers/neptune.py @@ -35,8 +35,9 @@ from lightning.pytorch.utilities.model_summary import ModelSummary from lightning.pytorch.utilities.rank_zero import rank_zero_only # neptune is available with two names on PyPI : `neptune` and `neptune-client` -_NEPTUNE_AVAILABLE = RequirementCache("neptune") +_NEPTUNE_AVAILABLE = RequirementCache("neptune>=1.0") _NEPTUNE_CLIENT_AVAILABLE = RequirementCache("neptune-client") + if _NEPTUNE_AVAILABLE: # >1.0 package structure import neptune