Files
vllm-omni/.buildkite/test-nightly.yaml
T
b81e0a8abf [Test] Add example test cases for omni online (#1086)
Signed-off-by: wangyu31577 <wangyu31577@hundsun.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Signed-off-by: yenuo26 <410167048@qq.com>
Co-authored-by: wangyu31577 <wangyu31577@hundsun.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-02-09 20:08:46 +08:00

69 lines
2.3 KiB
YAML

steps:
- label: ":docker: Build image"
key: image-build
commands:
- "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
- "docker build --file docker/Dockerfile.ci -t vllm-omni-ci ."
- "docker tag vllm-omni-ci public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT"
- "docker push public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT"
agents:
queue: "cpu_queue_premerge"
- label: "Omni Model Test with H100"
timeout_in_minutes: 60
depends_on: image-build
if: build.env("NIGHTLY") == "1"
commands:
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
- pytest -s -v tests/e2e/online_serving/test_qwen3_omni_expansion.py
- pytest -s -v tests/examples/online_serving/test_qwen3_omni.py
agents:
queue: "mithril-h100-pool"
plugins:
- kubernetes:
podSpec:
containers:
- image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
resources:
limits:
nvidia.com/gpu: 2
volumeMounts:
- name: devshm
mountPath: /dev/shm
- name: hf-cache
mountPath: /root/.cache/huggingface
env:
- name: HF_HOME
value: /root/.cache/huggingface
nodeSelector:
node.kubernetes.io/instance-type: gpu-h100-sxm
volumes:
- name: devshm
emptyDir:
medium: Memory
- name: hf-cache
hostPath:
path: /mnt/hf-cache
type: DirectoryOrCreate
- label: "Omni Model Test"
timeout_in_minutes: 60
depends_on: image-build
commands:
- export VLLM_LOGGING_LEVEL=DEBUG
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
- pytest -s -v tests/examples/online_serving/test_qwen2_5_omni.py
agents:
queue: "gpu_4_queue" # g6.12xlarge instance on AWS, has 4 L4 GPU
plugins:
- docker#v5.2.0:
image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
always-pull: true
propagate-environment: true
environment:
- "HF_HOME=/fsx/hf_cache"
volumes:
- "/fsx/hf_cache:/fsx/hf_cache"