metax.yml

# Metax Hardware Configuration for TE-FL
# This file defines CI/CD settings for Metax-based testing
# This file defines environment variables, volumes, and test filters for TE tests.

hardware_name: metax
display_name: 'Metax Tests'

# CI image for Metax dev env
# ci_image: localhost:5000/megatron-lm-with-te:v1

# CI image for online env
ci_image: harbor.baai.ac.cn/flagscale/megatron-lm-with-te:202603231839

# Runner labels for self-hosted Metax node
# runner_labels:
#   - self-hosted
#   - Linux
#   - X64
#   - metax
#   - dev

# Runner labels for online env
runner_labels:
  - mx-4g-cicd-te

# Container volumes
container_volumes:
  - /nfs/metax_fs:/nfs/metax_fs

# Container options
container_options: >-
  --hostname=te_cicd
  --ipc=host
  --privileged=true
  --shm-size=100gb
  --ulimit memlock=-1
  --user root
  --ulimit nofile=65535:65535
  --group-add video
  -e PLATFORM=metax
  -e TORCH_DISTRIBUTED_BACKEND=mccl
  -e LD_LIBRARY_PATH=/opt/maca/lib:/usr/local/lib:$LD_LIBRARY_PATH

# Platform-specific environment setup script
setup_script: .github/scripts/setup_metax.sh

# Build environment variables (platform-specific)
build_env:
  TE_FL_SKIP_CUDA: '1'
  NVTE_WITH_MACA: '1'
  CUDA_HOME: /opt/maca
  MACA_HOME: /opt/maca

# Device types to run tests on
device_types:
  - c500

# Test matrix configuration
test_matrix:
  unit:
    devices:
      - c500
    # Ignored test files for unit tests
    # These files will be skipped when running pytest
    ignored_tests:
      # example: tests/unit_tests/test_example.py
      # - tests/unit_tests/test_inference.py
      # - tests/unit_tests/test_rl_utils.py