Ci cd - DO NOT SUBMIT, attempt 2

.edf/README.md

@@ -0,0 +1,31 @@
+run:
+```
+export EDF_PATH=`pwd`/.edf
+```
+This adds the repository path to the EDF search path.
+
+run:
+```
+srun -A a-a122 --environment=ubuntu2 cat /etc/os-release
+``` 
+
+# local development
+srun --environment $PWD/.edf/hirad-ci.toml -A a-a122 -p debug --pty bash 
+
+
+
+# list current images
+podman images
+
+# build according to the dockerfile into an image with tag tmpv1, from current directory.
+podman build -f ci/docker/Dockerfile -t tmpv1 .
+
+# 
+podman run -it localhost/tmpv1
+
+mkdir /capstor/scratch/cscs/mmcgloho/images
+
+# export the image into a sqsh file so it is availabe outside the interactive shell
+enroot import -x mount -o /capstor/scratch/cscs/mmcgloho/images/hirad-pytorch-25.01-py3.sqsh podman://localhost/tmpv1
+
+ls /capstor/scratch/cscs/mmcgloho/images

.edf/gemma-pytorch.toml

@@ -0,0 +1,14 @@
+image = "/iopsstor/scratch/cscs/${USER}/pytorch-24.01-py3-venv/pytorch-24.01-py3-venv.sqsh"
+
+mounts = ["/capstor", "/users","/iopsstor/scratch/cscs/mmcgloho"]
+
+writable = true
+
+[annotations]
+com.hooks.aws_ofi_nccl.enabled = "true"
+com.hooks.aws_ofi_nccl.variant = "cuda12"
+
+[env]
+FI_CXI_DISABLE_HOST_REGISTER = "1"
+FI_MR_CACHE_MONITOR = "userfaultfd"
+NCCL_DEBUG = "INFO"

.edf/hirad-ci.toml

@@ -0,0 +1,14 @@
+image = "/capstor/scratch/cscs/${USER}/images/hirad-pytorch-25.01-py3.sqsh"
+
+mounts = ["/capstor","/iopsstor"]
+
+writable = true
+
+[annotations]
+com.hooks.aws_ofi_nccl.enabled = "true"
+com.hooks.aws_ofi_nccl.variant = "cuda12"
+
+[env]
+FI_CXI_DISABLE_HOST_REGISTER = "1"
+FI_MR_CACHE_MONITOR = "userfaultfd"
+NCCL_DEBUG = "INFO"

.edf/ngc-pytorch.toml

@@ -0,0 +1,6 @@
+# https://catalog.ngc.nvidia.com/orgs/nvidia/containers/pytorch
+image = "nvcr.io#nvidia/pytorch:22.01-py3"
+mounts = ["/capstor/scratch/cscs/${USER}:/capstor/scratch/cscs/${USER}"]
+workdir = "/capstor/scratch/cscs/${USER}"
+
+# Maybe above should be iopsstor

.edf/ubuntu.toml

@@ -0,0 +1,3 @@
+image = "library/ubuntu:24.04"
+mounts = ["/capstor/scratch/cscs/mmcgloho:/capstor/scratch/cscs/mmcgloho"]
+workdir = "/capstor/scratch/cscs/mmcgloho"

.edf/ubuntu2.toml

@@ -0,0 +1,5 @@
+
+
+image = "library/ubuntu:24.04"
+mounts = ["/capstor/scratch/cscs/${USER}:/capstor/scratch/cscs/${USER}"]
+workdir = "/capstor/scratch/cscs/${USER}"

.gitignore

@@ -0,0 +1,188 @@
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+# output files
+*.out
+*.torch
+plots/*
+*.npz
+
+# conda
+.conda/*
+
+# temp
+temp.*
+
+# local script
+interpolate.sh
+core_clariden-ln002_241188
+