metax.yml

# Metax Hardware Configuration for TE-FL
# This file defines CI/CD settings for Metax-based testing
# Test configurations are defined in tests/test_utils/config/platforms/metax.yaml

hardware_name: metax
display_name: 'Metax Tests'

ci_image: localhost:5000/megatron-lm-with-te:v1
# ci_image: harbor.baai.ac.cn/flagscale/megatron-lm-with-te:202603231839

runner_labels:
  - self-hosted
  - Linux
  - X64
  - metax
  - dev
# runner_labels:
#   - mx-4g-cicd-te

container_volumes:
  - /nfs/metax_fs:/nfs/metax_fs
  - /dev/dri:/dev/dri
  - /dev/mxcd:/dev/mxcd
  - /dev/infiniband:/dev/infiniband

container_options: >-
  --uts=host
  --ipc=host
  --privileged=true
  --group-add video
  --shm-size=100gb
  --ulimit memlock=-1
  --security-opt seccomp=unconfined
  --security-opt apparmor=unconfined
  --device=/dev/dri
  --device=/dev/mxcd
  --device=/dev/infiniband
  --user root
  --ulimit nofile=65535:65535
  -e PLATFORM=metax
  -e TORCH_DISTRIBUTED_BACKEND=mccl
  -e LD_LIBRARY_PATH=/opt/maca/lib:/usr/local/lib:$LD_LIBRARY_PATH

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

  # functional:
  #   train:
  #     - device: c500
  #       task: train
  #       model: deepseek
  #       case: tp2_pp2_ep2