54 lines
2.0 KiB
Django/Jinja
54 lines
2.0 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 = "public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT-rocm-omni" %}
|
|
{% set default_working_dir = "/app/vllm-omni" %}
|
|
|
|
- group: "AMD Tests"
|
|
depends_on: ~
|
|
steps:
|
|
- label: "AMD: :docker: build image"
|
|
depends_on: ~
|
|
soft_fail: false
|
|
commands:
|
|
- "source .buildkite/scripts/docker_login_ecr_public.sh && safe_docker_login_ecr_public"
|
|
- "docker build -f docker/Dockerfile.rocm -t {{ docker_image_amd }} --target final --progress plain ."
|
|
- "docker push {{ docker_image_amd }}"
|
|
key: "amd-build"
|
|
env:
|
|
DOCKER_BUILDKIT: "1"
|
|
retry:
|
|
automatic:
|
|
- exit_status: -1 # Agent was lost
|
|
limit: 1
|
|
- exit_status: -10 # Agent was lost
|
|
limit: 1
|
|
- exit_status: 1 # Machine occasionally fail
|
|
limit: 1
|
|
agents:
|
|
queue: cpu_queue_premerge
|
|
|
|
{% for step in 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 %}
|
|
command: bash .buildkite/scripts/hardware_ci/run-amd-test.sh "(command rocm-smi || true) && cd {{ (step.working_dir or default_working_dir) | safe }} ; {{ step.command or (step.commands | join(" && ")) | safe }}"
|
|
env:
|
|
DOCKER_BUILDKIT: "1"
|
|
priority: 100
|
|
{% if step.grade and step.grade == "Blocking" %}
|
|
soft_fail: false
|
|
{% else %}
|
|
soft_fail: true
|
|
{% endif%}
|
|
{% endif %}
|
|
{% endfor %}
|