env: VLLM_WORKER_MULTIPROC_METHOD: spawn HF_HUB_DOWNLOAD_TIMEOUT: 300 HF_HUB_ETAG_TIMEOUT: 60 steps: - label: "Simple Unit Test" depends_on: upload-ready-pipeline commands: - "timeout 20m pytest -v -s -m 'core_model and cpu' --cov=vllm_omni --cov-branch --cov-report=term-missing --cov-report=html --cov-report=xml" agents: queue: "gpu_1_queue" plugins: - docker#v5.2.0: image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT always-pull: true propagate-environment: true environment: - "HF_HOME=/fsx/hf_cache" - "HF_TOKEN" volumes: - "/fsx/hf_cache:/fsx/hf_cache" - label: "CUDA Unit Test with single card" depends_on: upload-ready-pipeline commands: - timeout 10m pytest -v -s -m 'core_model and cuda and L4 and not distributed_cuda' --ignore=tests/e2e --ignore=tests/engine/test_async_omni_engine_abort.py --cov=vllm_omni --cov-branch --cov-report=term-missing --cov-report=html --cov-report=xml agents: queue: "gpu_1_queue" plugins: - docker#v5.2.0: image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT always-pull: true propagate-environment: true environment: - "HF_HOME=/fsx/hf_cache" volumes: - "/fsx/hf_cache:/fsx/hf_cache" - label: "CUDA Unit Test with multi cards" depends_on: upload-ready-pipeline commands: - timeout 10m pytest -v -s -m 'core_model and cuda and L4 and distributed_cuda' --ignore=tests/e2e --cov=vllm_omni --cov-branch --cov-report=term-missing --cov-report=html --cov-report=xml agents: queue: "gpu_4_queue" plugins: - docker#v5.2.0: image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT always-pull: true propagate-environment: true environment: - "HF_HOME=/fsx/hf_cache" volumes: - "/fsx/hf_cache:/fsx/hf_cache" - label: "Diffusion Model Test" depends_on: upload-ready-pipeline commands: - timeout 30m pytest -s -v tests/e2e/offline_inference/test_t2i_model.py -m "core_model and diffusion" --run-level "core_model" agents: queue: "gpu_1_queue" plugins: - docker#v5.2.0: image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT always-pull: true propagate-environment: true environment: - "HF_HOME=/fsx/hf_cache" - "HF_TOKEN" volumes: - "/fsx/hf_cache:/fsx/hf_cache" - label: "Diffusion Batching Test" depends_on: upload-ready-pipeline commands: - timeout 20m pytest -s -v tests/e2e/offline_inference/test_qwen_image_diffusion_batching.py -m "core_model and diffusion" --run-level "core_model" agents: queue: "gpu_1_queue" # g6.4xlarge instance on AWS, has 1 L4 GPU plugins: - docker#v5.2.0: image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT always-pull: true propagate-environment: true environment: - "HF_HOME=/fsx/hf_cache" - "HF_TOKEN" volumes: - "/fsx/hf_cache:/fsx/hf_cache" - label: "Custom Pipeline Test" depends_on: upload-ready-pipeline commands: - timeout 20m pytest -s -v tests/e2e/offline_inference/custom_pipeline/ -m "core_model" agents: queue: "gpu_1_queue" plugins: - docker#v5.2.0: image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT always-pull: true propagate-environment: true environment: - "HF_HOME=/fsx/hf_cache" volumes: - "/fsx/hf_cache:/fsx/hf_cache" - label: "Diffusion Model CPU offloading Test" depends_on: upload-ready-pipeline commands: - timeout 10m pytest -s -v tests/e2e/offline_inference/test_diffusion_cpu_offload.py agents: queue: "gpu_1_queue" # g6.4xlarge instance on AWS, has 1 L4 GPU plugins: - docker#v5.2.0: image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT always-pull: true propagate-environment: true environment: - "HF_HOME=/fsx/hf_cache" - "HF_TOKEN" volumes: - "/fsx/hf_cache:/fsx/hf_cache" - label: "Diffusion Cache Backend Test" depends_on: upload-ready-pipeline commands: - timeout 15m pytest -s -v -m 'core_model and cache and diffusion and not distributed_cuda and L4' agents: queue: "gpu_1_queue" # g6.4xlarge instance on AWS, has 1 L4 GPU plugins: - docker#v5.2.0: image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT always-pull: true propagate-environment: true environment: - "HF_HOME=/fsx/hf_cache" - "HF_TOKEN" volumes: - "/fsx/hf_cache:/fsx/hf_cache" - label: "Diffusion Sequence Parallelism Test" depends_on: upload-ready-pipeline commands: - timeout 20m pytest -s -v tests/e2e/offline_inference/test_sequence_parallel.py -m core_model 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:$BUILDKITE_COMMIT always-pull: true propagate-environment: true shm-size: "8gb" environment: - "HF_HOME=/fsx/hf_cache" - "HF_TOKEN" volumes: - "/fsx/hf_cache:/fsx/hf_cache" - label: "Engine Test" depends_on: upload-ready-pipeline commands: - | timeout 15m bash -c ' pytest -s -v tests/engine/test_async_omni_engine_abort.py ' agents: queue: "gpu_1_queue" # g6.12xlarge instance on AWS, has 4 L4 GPU plugins: - docker#v5.2.0: image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT always-pull: true propagate-environment: true shm-size: "8gb" environment: - "HF_HOME=/fsx/hf_cache" - "HF_TOKEN" volumes: - "/fsx/hf_cache:/fsx/hf_cache" - label: "Omni Model Test with H100" depends_on: upload-ready-pipeline commands: - | timeout 20m bash -c ' 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:$BUILDKITE_COMMIT resources: limits: nvidia.com/gpu: 2 volumeMounts: - name: devshm mountPath: /dev/shm - name: hf-cache mountPath: /root/.cache/huggingface env: - name: HF_HOME value: /root/.cache/huggingface nodeSelector: node.kubernetes.io/instance-type: gpu-h100-sxm volumes: - name: devshm emptyDir: medium: Memory - name: hf-cache hostPath: path: /mnt/hf-cache type: DirectoryOrCreate - label: "MiMo-Audio E2E Test with H100" depends_on: upload-ready-pipeline commands: - | timeout 30m bash -c ' export VLLM_LOGGING_LEVEL=DEBUG pytest -s -v tests/e2e/online_serving/test_mimo_audio.py -m "core_model" --run-level "core_model" ' agents: queue: "mithril-h100-pool" plugins: - kubernetes: podSpec: containers: - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT resources: limits: nvidia.com/gpu: 1 volumeMounts: - name: devshm mountPath: /dev/shm - name: hf-cache mountPath: /root/.cache/huggingface env: - name: HF_HOME value: /root/.cache/huggingface - name: HF_TOKEN valueFrom: secretKeyRef: name: hf-token-secret key: token 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: "Qwen3-TTS E2E Test" depends_on: upload-ready-pipeline commands: - | timeout 20m bash -c ' export VLLM_LOGGING_LEVEL=DEBUG export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1" pytest -s -v tests/e2e/online_serving/test_qwen3_tts_customvoice.py -m "core_model" --run-level "core_model" ' agents: queue: "gpu_1_queue" plugins: - docker#v5.2.0: image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT always-pull: true propagate-environment: true shm-size: "8gb" environment: - "HF_HOME=/fsx/hf_cache" - "HF_TOKEN" volumes: - "/fsx/hf_cache:/fsx/hf_cache" - label: "VoxCPM E2E Test" timeout_in_minutes: 20 depends_on: upload-ready-pipeline commands: - | timeout 20m bash -c ' pip install voxcpm export VLLM_LOGGING_LEVEL=DEBUG export VLLM_WORKER_MULTIPROC_METHOD=spawn pytest -s -v tests/e2e/offline_inference/test_voxcpm.py -m "core_model" --run-level "core_model" ' agents: queue: "gpu_1_queue" plugins: - docker#v5.2.0: image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT always-pull: true propagate-environment: true shm-size: "8gb" environment: - "HF_HOME=/fsx/hf_cache" - "HF_TOKEN" volumes: - "/fsx/hf_cache:/fsx/hf_cache" - label: "VoxCPM2 Native AR E2E Test" timeout_in_minutes: 20 depends_on: upload-ready-pipeline commands: - | timeout 20m bash -c ' pip install voxcpm export VLLM_LOGGING_LEVEL=DEBUG export VLLM_WORKER_MULTIPROC_METHOD=spawn pytest -s -v tests/e2e/offline_inference/test_voxcpm2.py -m "core_model" --run-level "core_model" ' agents: queue: "gpu_1_queue" plugins: - docker#v5.2.0: image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT always-pull: true propagate-environment: true shm-size: "8gb" environment: - "HF_HOME=/fsx/hf_cache" - "HF_TOKEN" volumes: - "/fsx/hf_cache:/fsx/hf_cache" - label: "OmniVoice E2E Test" timeout_in_minutes: 20 depends_on: upload-ready-pipeline commands: - | timeout 20m bash -c ' export VLLM_LOGGING_LEVEL=DEBUG pytest -s -v tests/e2e/online_serving/test_omnivoice.py -m "core_model" --run-level "core_model" ' agents: queue: "gpu_1_queue" plugins: - docker#v5.2.0: image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT always-pull: true propagate-environment: true shm-size: "8gb" environment: - "HF_HOME=/fsx/hf_cache" volumes: - "/fsx/hf_cache:/fsx/hf_cache" - label: "Qwen3-TTS Base E2E Test (ModelRunner V2)" depends_on: upload-ready-pipeline soft_fail: - exit_status: 1 commands: - | timeout 20m bash -c ' export VLLM_LOGGING_LEVEL=DEBUG export VLLM_WORKER_MULTIPROC_METHOD=spawn export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1" export VLLM_OMNI_USE_V2_RUNNER="1" pytest -s -v tests/e2e/online_serving/test_qwen3_tts_base.py -m "core_model" --run-level "core_model" ' agents: queue: "gpu_1_queue" plugins: - docker#v5.2.0: image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT always-pull: true propagate-environment: true shm-size: "8gb" environment: - "HF_HOME=/fsx/hf_cache" - "HF_TOKEN" volumes: - "/fsx/hf_cache:/fsx/hf_cache" - label: "Voxtral-TTS E2E Test" timeout_in_minutes: 20 depends_on: upload-ready-pipeline commands: - | timeout 20m bash -c ' export VLLM_LOGGING_LEVEL=DEBUG pytest -s -v tests/e2e/online_serving/test_voxtral_tts.py -m "core_model" --run-level "core_model" ' agents: queue: "mithril-h100-pool" plugins: - kubernetes: podSpec: containers: - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT resources: limits: nvidia.com/gpu: 1 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: "Diffusion Image Edit Test with H100 (1 GPU)" # depends_on: upload-ready-pipeline # commands: # - | # timeout 20m bash -c ' # pytest -s -v tests/e2e/online_serving/test_image_gen_edit.py # ' # 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:$BUILDKITE_COMMIT # resources: # limits: # nvidia.com/gpu: 1 # volumeMounts: # - name: devshm # mountPath: /dev/shm # - name: hf-cache # mountPath: /root/.cache/huggingface # env: # - name: HF_HOME # value: /root/.cache/huggingface # nodeSelector: # node.kubernetes.io/instance-type: gpu-h100-sxm # volumes: # - name: devshm # emptyDir: # medium: Memory # - name: hf-cache # hostPath: # path: /mnt/hf-cache # type: DirectoryOrCreate - label: "Bagel Text2Img Model Test with H100" depends_on: upload-ready-pipeline commands: - | timeout 30m bash -c ' export VLLM_TEST_CLEAN_GPU_MEMORY=1 pytest -s -v tests/e2e/offline_inference/test_bagel_text2img.py -m "core_model" --run-level "core_model" ' agents: queue: "mithril-h100-pool" plugins: - kubernetes: podSpec: containers: - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT resources: limits: nvidia.com/gpu: 1 volumeMounts: - name: devshm mountPath: /dev/shm - name: hf-cache mountPath: /root/.cache/huggingface env: - name: HF_HOME value: /root/.cache/huggingface - name: HF_TOKEN valueFrom: secretKeyRef: name: hf-token-secret key: token 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: "Bagel Img2Img Model Test with H100" depends_on: upload-ready-pipeline commands: - | timeout 30m bash -c ' export VLLM_TEST_CLEAN_GPU_MEMORY=1 pytest -s -v tests/e2e/offline_inference/test_bagel_img2img.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:$BUILDKITE_COMMIT resources: limits: nvidia.com/gpu: 1 volumeMounts: - name: devshm mountPath: /dev/shm - name: hf-cache mountPath: /root/.cache/huggingface env: - name: HF_HOME value: /root/.cache/huggingface - name: HF_TOKEN valueFrom: secretKeyRef: name: hf-token-secret key: token nodeSelector: node.kubernetes.io/instance-type: gpu-h100-sxm volumes: - name: devshm emptyDir: medium: Memory - name: hf-cache hostPath: path: /mnt/hf-cache type: DirectoryOrCreate - label: "Bagel Online Serving Test with H100" depends_on: upload-ready-pipeline commands: - | timeout 40m bash -c ' export VLLM_TEST_CLEAN_GPU_MEMORY=1 export VLLM_IMAGE_FETCH_TIMEOUT=60 pytest -s -v tests/e2e/online_serving/test_bagel_online.py -m "core_model" --run-level "core_model" ' agents: queue: "mithril-h100-pool" plugins: - kubernetes: podSpec: containers: - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT resources: limits: nvidia.com/gpu: 1 volumeMounts: - name: devshm mountPath: /dev/shm - name: hf-cache mountPath: /root/.cache/huggingface env: - name: HF_HOME value: /root/.cache/huggingface - name: HF_TOKEN valueFrom: secretKeyRef: name: hf-token-secret key: token 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: "CosyVoice3-TTS E2E Test" timeout_in_minutes: 20 depends_on: upload-ready-pipeline commands: - | timeout 20m bash -c ' pytest -s -v tests/e2e/online_serving/test_cosyvoice3_tts.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: 1 volumeMounts: - name: devshm mountPath: /dev/shm - name: hf-cache mountPath: /root/.cache/huggingface env: - name: HF_HOME value: /root/.cache/huggingface - name: HF_TOKEN valueFrom: secretKeyRef: name: hf-token-secret key: token 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