[Test] Add qwen3-omni tests for audio_in_video and one word prompt (#2097)

Signed-off-by: yenuo26 <410167048@qq.com>
Signed-off-by: wangyu <410167048@qq.com>
Signed-off-by: wangyu <53896905+yenuo26@users.noreply.github.com>
Co-authored-by: Alicia <115451386+congw729@users.noreply.github.com>
This commit is contained in:
wangyuandAlicia authored and GitHub committed 2026-03-31 14:30:12 +08:00
1 parent 1734c1ec23
commit c1a978ae8d
4 files changed
+331 -87

No files matched your search

+36 -38
View File
@@ -216,44 +216,42 @@ steps:
volumes:
- "/fsx/hf_cache:/fsx/hf_cache"
# - label: "Omni Model Test with H100"
# depends_on: upload-ready-pipeline
# commands:
# - |
# timeout 20m bash -c '
# export VLLM_WORKER_MULTIPROC_METHOD=spawn
# export VLLM_TEST_CLEAN_GPU_MEMORY="1"
# # - pytest -s -v tests/e2e/offline_inference/test_qwen3_omni.py
# pytest -s -v tests/e2e/online_serving/test_qwen3_omni.py -m "core_model" --run-level "core_model"
# '
# agents:
# queue: "mithril-h100-pool"
# plugins:
# - kubernetes:
# podSpec:
# containers:
# - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
# resources:
# limits:
# nvidia.com/gpu: 2
# volumeMounts:
# - name: devshm
# mountPath: /dev/shm
# - name: hf-cache
# mountPath: /root/.cache/huggingface
# env:
# - name: HF_HOME
# value: /root/.cache/huggingface
# nodeSelector:
# node.kubernetes.io/instance-type: gpu-h100-sxm
# volumes:
# - name: devshm
# emptyDir:
# medium: Memory
# - name: hf-cache
# hostPath:
# path: /mnt/hf-cache
# type: DirectoryOrCreate
- label: "Omni Model Test with H100"
depends_on: upload-ready-pipeline
commands:
- |
timeout 20m bash -c '
export VLLM_WORKER_MULTIPROC_METHOD=spawn
pytest -s -v tests/e2e/online_serving/test_qwen3_omni.py -m "core_model" --run-level "core_model"
'
agents:
queue: "mithril-h100-pool"
plugins:
- kubernetes:
podSpec:
containers:
- image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$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: "MiMo-Audio E2E Test with H100"
depends_on: upload-ready-pipeline