vllm-omni/.buildkite/common/ci_mirror_hardwares.yml

# Uploader-only hardware presets for CUDA / NPU test YAML.
# Referenced as ``mirror_hardwares: l4_1`` on a step; ``upload_pipeline.py`` expands to
# ``agents`` (+ optional top-level ``image`` for NPU) + ``plugins``, then strips
# ``mirror_hardwares`` before Buildkite upload.
#
# CUDA naming: {chip}_{count}
#   l4_1, l4_4, h100_1 … h100_4
# NPU naming: {queue}_{resource_class}
#   a2b3_npu_1  — ascend-a2b3, resource_class npu-1 (A2/B3 CI image)
#   a2b3_npu_4  — ascend-a2b3, resource_class npu-4
#   a3_npu_2    — ascend-a3, resource_class npu-2
#
# The ``l4_*`` presets run under the ``docker`` plugin, which does not put
# ``buildkite-agent`` on PATH inside the container the way the ``kubernetes``
# presets do, so they set ``mount-buildkite-agent: true``; without it any step
# calling ``buildkite-agent`` (artifact upload, annotate, meta-data) fails there.

x-npu-k8s-plugins: &npu_k8s_plugins
  - kubernetes:
      podSpecPatch:
        imagePullSecrets:
          - name: swr-secret


mirror_hardwares:
  l4_1:
    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
          mount-buildkite-agent: true
          shm-size: "8gb"
          environment:
            - HF_HOME=/fsx/hf_cache
            - HF_TOKEN
          volumes:
            - /fsx/hf_cache:/fsx/hf_cache

  l4_4:
    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
          mount-buildkite-agent: true
          shm-size: "8gb"
          environment:
            - HF_HOME=/fsx/hf_cache
            - HF_TOKEN
          volumes:
            - /fsx/hf_cache:/fsx/hf_cache

  h100_1:
    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

  h100_2:
    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
                  - 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

  h100_3:
    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: 3
                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

  h100_4:
    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: 4
                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

  a2b3_npu_1:
    agents:
      queue: "ascend-a2b3"
      resource_class: "npu-1"
    image: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry/vllm-omni-ci-npu:${BUILDKITE_COMMIT}"
    plugins: *npu_k8s_plugins

  a2b3_npu_4:
    agents:
      queue: "ascend-a2b3"
      resource_class: "npu-4"
    image: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry/vllm-omni-ci-npu:${BUILDKITE_COMMIT}"
    plugins: *npu_k8s_plugins


  a2b3_npu_8:
    agents:
      queue: "ascend-a2b3"
      resource_class: "npu-8"
    image: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry/vllm-omni-ci-npu:${BUILDKITE_COMMIT}"
    plugins: *npu_k8s_plugins

  a3_npu_2:
    agents:
      queue: "ascend-a3"
      resource_class: "npu-2"
    image: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry/vllm-omni-ci-npu:${BUILDKITE_COMMIT}-a3"
    plugins: *npu_k8s_plugins

  a3_npu_4:
    agents:
      queue: "ascend-a3"
      resource_class: "npu-4"
    image: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry/vllm-omni-ci-npu:${BUILDKITE_COMMIT}-a3"
    plugins: *npu_k8s_plugins

  a3_npu_8:
    agents:
      queue: "ascend-a3"
      resource_class: "npu-8"
    image: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry/vllm-omni-ci-npu:${BUILDKITE_COMMIT}-a3"
    plugins: *npu_k8s_plugins

  a3_npu_16:
    agents:
      queue: "ascend-a3"
      resource_class: "npu-16"
    image: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry/vllm-omni-ci-npu:${BUILDKITE_COMMIT}-a3"
    plugins: *npu_k8s_plugins