142 lines
4.3 KiB
Django/Jinja
142 lines
4.3 KiB
Django/Jinja
{# vllm-omni customized version
|
|
Based on: https://github.com/vllm-project/ci-infra/blob/main/buildkite/test-template-amd.j2
|
|
Last synced: 2025-12-15
|
|
Modifications: Removed unused CUDA/NVIDIA logic, keeping only AMD tests
|
|
#}
|
|
{% set docker_image_amd = "rocm/vllm-omni:$BUILDKITE_COMMIT" %}
|
|
{% set default_working_dir = "/app/vllm-omni" %}
|
|
|
|
{% if env %}
|
|
env:
|
|
{% for name in env %}
|
|
{{ name }}: "{{ env[name] }}"
|
|
{% endfor %}
|
|
{% endif %}
|
|
steps:
|
|
- group: "AMD Tests"
|
|
depends_on: ~
|
|
steps:
|
|
- label: "AMD: :docker: build image"
|
|
depends_on: ~
|
|
soft_fail: false
|
|
commands:
|
|
- "docker build -f docker/Dockerfile.rocm -t {{ docker_image_amd }} --target test --build-arg ARG_PYTORCH_ROCM_ARCH=gfx942 --progress plain ."
|
|
- "docker push {{ docker_image_amd }}"
|
|
key: "amd-build"
|
|
env:
|
|
DOCKER_BUILDKIT: "1"
|
|
retry:
|
|
automatic:
|
|
- exit_status: -1 # Agent was lost
|
|
limit: 2
|
|
- exit_status: -10 # Agent was lost
|
|
limit: 2
|
|
- exit_status: 128 # Git connectivity issues
|
|
limit: 2
|
|
- exit_status: 1 # Machine occasionally fail
|
|
limit: 1
|
|
agents:
|
|
queue: amd-cpu
|
|
|
|
{% for step_group in steps %}
|
|
{% if step_group.group %}
|
|
- group: "{{ step_group.group }}"
|
|
{% if step_group.depends_on %}
|
|
depends_on: {{ step_group.depends_on }}
|
|
{% endif %}
|
|
steps:
|
|
{% for step in step_group.steps %}
|
|
{% if step.mirror_hardwares and mirror_hw in step.mirror_hardwares %}
|
|
- label: "{{ step.agent_pool }}: {{ step.label }}"
|
|
depends_on: amd-build
|
|
agents:
|
|
{% if step.agent_pool %}
|
|
queue: amd_{{ step.agent_pool }}
|
|
{% else %}
|
|
queue: amd_mi325_1
|
|
{% endif %}
|
|
{% set cmd_body = (step.command or (step.commands | join("\n"))) | trim %}
|
|
{% set indented_cmd = cmd_body | replace("\n", "\n ") %}
|
|
command: bash .buildkite/scripts/hardware_ci/run-amd-test.sh
|
|
env:
|
|
DOCKER_BUILDKIT: "1"
|
|
{% if step.env %}
|
|
{% for name in step.env %}
|
|
{{ name }}: "{{ step.env[name] }}"
|
|
{% endfor %}
|
|
{% endif %}
|
|
TEST_COMMAND: |-
|
|
(command rocm-smi || true) && cd {{ (step.working_dir or default_working_dir) | safe }}
|
|
{% if env %}
|
|
{% for name in env %}
|
|
export {{ name }}="{{ env[name] }}"
|
|
{% endfor %}
|
|
{% endif %}
|
|
{% if step.env %}
|
|
{% for name in step.env %}
|
|
export {{ name }}="{{ step.env[name] }}"
|
|
{% endfor %}
|
|
{% endif %}
|
|
{% if "mi250" in step.agent_pool %}
|
|
python3 -m pip uninstall -y amd-aiter
|
|
{% endif %}
|
|
{{ indented_cmd | safe }}
|
|
priority: 100
|
|
{% if step.timeout_in_minutes %}
|
|
timeout_in_minutes: {{ step.timeout_in_minutes }}
|
|
{% endif %}
|
|
{% if step.grade and step.grade == "Blocking" %}
|
|
soft_fail: false
|
|
{% else %}
|
|
soft_fail: true
|
|
{% endif%}
|
|
{% endif %}
|
|
{% endfor %}
|
|
{% elif step_group.mirror_hardwares and mirror_hw in step_group.mirror_hardwares %}
|
|
{% set step = step_group %}
|
|
- label: "{{ step.agent_pool }}: {{ step.label }}"
|
|
depends_on: amd-build
|
|
agents:
|
|
{% if step.agent_pool %}
|
|
queue: amd_{{ step.agent_pool }}
|
|
{% else %}
|
|
queue: amd_mi325_1
|
|
{% endif %}
|
|
{% set cmd_body = (step.command or (step.commands | join("\n"))) | trim %}
|
|
{% set indented_cmd = cmd_body | replace("\n", "\n ") %}
|
|
command: bash .buildkite/scripts/hardware_ci/run-amd-test.sh
|
|
env:
|
|
DOCKER_BUILDKIT: "1"
|
|
{% if step.env %}
|
|
{% for name in step.env %}
|
|
{{ name }}: "{{ step.env[name] }}"
|
|
{% endfor %}
|
|
{% endif %}
|
|
TEST_COMMAND: |-
|
|
(command rocm-smi || true) && cd {{ (step.working_dir or default_working_dir) | safe }}
|
|
{% if env %}
|
|
{% for name in env %}
|
|
export {{ name }}="{{ env[name] }}"
|
|
{% endfor %}
|
|
{% endif %}
|
|
{% if step.env %}
|
|
{% for name in step.env %}
|
|
export {{ name }}="{{ step.env[name] }}"
|
|
{% endfor %}
|
|
{% endif %}
|
|
{% if "mi250" in step.agent_pool %}
|
|
python3 -m pip uninstall -y amd-aiter
|
|
{% endif %}
|
|
{{ indented_cmd | safe }}
|
|
priority: 100
|
|
{% if step.timeout_in_minutes %}
|
|
timeout_in_minutes: {{ step.timeout_in_minutes }}
|
|
{% endif %}
|
|
{% if step.grade and step.grade == "Blocking" %}
|
|
soft_fail: false
|
|
{% else %}
|
|
soft_fail: true
|
|
{% endif%}
|
|
{% endif %}
|
|
{% endfor %}
|