anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity
Files
3e705fcdb115e205db31726ffc3a61f868f94136
vllm-omni/.buildkite/common/ci_mirror_hardwares.yml
T
Zhou TaichangandClaude Opus 5 aff7d64948 [Rebase] Rebase to vLLM 0.29.0 (#7230) 
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-09-10 12:08:28 +08:00

703 lines
23 KiB
YAML
Raw Blame History

# 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`` (+ ``retry``
# for ``l4_*``), then strips ``mirror_hardwares`` before Buildkite upload.
#
# Omit the key: compose {chip}_{n} from pytest -m SKU + cards_n (max of several
# positives; not cards_1 with no positive cards_* → that chip's highest existing preset).
# Unset MIRROR_HW matches H100 or L4 in -m (both → H100); no match skips the step.
# MIRROR_HW=b200 matches B200 in -m (else the step is skipped).
# MIRROR_HW must be empty or b200 (case-insensitive); unknown values fail the upload.
# CUDA preset strings (h100_4, l4_1) are omitted when MIRROR_HW=b200.
# Unset MIRROR_HW keeps string presets. NPU presets ignore MIRROR_HW.
#
# CUDA naming: {chip}_{count}
# l4_1, l4_2, l4_3, l4_4, h100_1 … h100_4, b200_1 … b200_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 (A3 CI image tag …:$BUILDKITE_COMMIT-a3)
# a5_npu_2 — ascend-a5, resource_class npu-2
# 310p_npu_1 — ascend-310p, resource_class npu-1
#
# B200 (b200-k8s): matches vLLM device ``b200-k8s`` from ci-infra
# (AgentQueue.B200_K8S + b200_plugin_template). Queue routes the K8s pool;
# podSpec uses hostNetwork + /raid|/mnt/shared (no H100-style nodeSelector).
#
# The ``l4_*`` presets run on the EKS ``l4-k8s`` queue (agent-stack-k8s),
# packed onto g6.12xlarge L4 nodes (``vllm.ci/gpu-pool=l4x4``). GPU / CPU /
# memory / shm requests scale with card count (1 GPU = 10 CPU / 40Gi / 24Gi shm).
# Retry covers lost agents / killed pods, not pytest or OOM (exit 1 / 137).
# The Kubernetes HF secret deliberately uses VLLM_CI_HF_TOKEN. Scheduled
# build-level HF_TOKEN values can override pod env entries with the same name;
# upload_pipeline.py restores the secret-backed value inside the job shell.
x-npu-k8s-plugins: &npu_k8s_plugins
- kubernetes:
podSpecPatch:
imagePullSecrets:
- name: swr-secret
# Infra-only retry. Omit exit 1 (pytest failed) and 137 (cgroup OOM / SIGKILL
# of the test process). ci-infra ``K8S_RETRY`` still retries exit 1.
x-l4-k8s-retry: &l4_k8s_retry
automatic:
- exit_status: -1
limit: 1
- exit_status: 128
limit: 1
- signal_reason: agent_stop
limit: 1
- signal_reason: agent_refused
limit: 1
mirror_hardwares:
l4_1:
agents:
queue: l4-k8s
retry: *l4_k8s_retry
plugins:
- kubernetes:
metadata:
annotations:
cluster-autoscaler.kubernetes.io/safe-to-evict: "false"
karpenter.sh/do-not-disrupt: "true"
podSpec:
priorityClassName: ci
serviceAccountName: buildkite-gpu-jobs
tolerations:
- key: nvidia.com/gpu
operator: Exists
effect: NoSchedule
nodeSelector:
vllm.ci/gpu-pool: l4x4
containers:
- image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
resources:
limits:
nvidia.com/gpu: 1
requests:
nvidia.com/gpu: 1
cpu: "10"
memory: 40Gi
volumeMounts:
- name: devshm
mountPath: /dev/shm
- name: hf-cache
mountPath: /fsx/hf_cache
env:
- name: HF_HOME
value: /fsx/hf_cache
- name: VLLM_CI_HF_TOKEN
valueFrom:
secretKeyRef:
name: hf-token-secret
key: token
volumes:
- name: devshm
emptyDir:
medium: Memory
sizeLimit: 24Gi
- name: hf-cache
hostPath:
path: /fsx/hf_cache
type: DirectoryOrCreate
l4_2:
agents:
queue: l4-k8s
retry: *l4_k8s_retry
plugins:
- kubernetes:
metadata:
annotations:
cluster-autoscaler.kubernetes.io/safe-to-evict: "false"
karpenter.sh/do-not-disrupt: "true"
podSpec:
priorityClassName: ci
serviceAccountName: buildkite-gpu-jobs
tolerations:
- key: nvidia.com/gpu
operator: Exists
effect: NoSchedule
nodeSelector:
vllm.ci/gpu-pool: l4x4
containers:
- image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
resources:
limits:
nvidia.com/gpu: 2
requests:
nvidia.com/gpu: 2
cpu: "20"
memory: 80Gi
volumeMounts:
- name: devshm
mountPath: /dev/shm
- name: hf-cache
mountPath: /fsx/hf_cache
env:
- name: HF_HOME
value: /fsx/hf_cache
- name: VLLM_CI_HF_TOKEN
valueFrom:
secretKeyRef:
name: hf-token-secret
key: token
volumes:
- name: devshm
emptyDir:
medium: Memory
sizeLimit: 48Gi
- name: hf-cache
hostPath:
path: /fsx/hf_cache
type: DirectoryOrCreate
l4_3:
agents:
queue: l4-k8s
retry: *l4_k8s_retry
plugins:
- kubernetes:
metadata:
annotations:
cluster-autoscaler.kubernetes.io/safe-to-evict: "false"
karpenter.sh/do-not-disrupt: "true"
podSpec:
priorityClassName: ci
serviceAccountName: buildkite-gpu-jobs
tolerations:
- key: nvidia.com/gpu
operator: Exists
effect: NoSchedule
nodeSelector:
vllm.ci/gpu-pool: l4x4
containers:
- image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
resources:
limits:
nvidia.com/gpu: 3
requests:
nvidia.com/gpu: 3
cpu: "30"
memory: 120Gi
volumeMounts:
- name: devshm
mountPath: /dev/shm
- name: hf-cache
mountPath: /fsx/hf_cache
env:
- name: HF_HOME
value: /fsx/hf_cache
- name: VLLM_CI_HF_TOKEN
valueFrom:
secretKeyRef:
name: hf-token-secret
key: token
volumes:
- name: devshm
emptyDir:
medium: Memory
sizeLimit: 72Gi
- name: hf-cache
hostPath:
path: /fsx/hf_cache
type: DirectoryOrCreate
l4_4:
agents:
queue: l4-k8s
retry: *l4_k8s_retry
plugins:
- kubernetes:
metadata:
annotations:
cluster-autoscaler.kubernetes.io/safe-to-evict: "false"
karpenter.sh/do-not-disrupt: "true"
podSpec:
priorityClassName: ci
serviceAccountName: buildkite-gpu-jobs
tolerations:
- key: nvidia.com/gpu
operator: Exists
effect: NoSchedule
nodeSelector:
vllm.ci/gpu-pool: l4x4
containers:
- image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
resources:
limits:
nvidia.com/gpu: 4
requests:
nvidia.com/gpu: 4
cpu: "40"
memory: 160Gi
volumeMounts:
- name: devshm
mountPath: /dev/shm
- name: hf-cache
mountPath: /fsx/hf_cache
env:
- name: HF_HOME
value: /fsx/hf_cache
- name: VLLM_CI_HF_TOKEN
valueFrom:
secretKeyRef:
name: hf-token-secret
key: token
volumes:
- name: devshm
emptyDir:
medium: Memory
sizeLimit: 96Gi
- name: hf-cache
hostPath:
path: /fsx/hf_cache
type: DirectoryOrCreate
h100_1:
agents:
queue: mithril-h100-pool
plugins:
- kubernetes:
podSpec:
containers:
- image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$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: VLLM_CI_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:$BUILDKITE_COMMIT
resources:
limits:
nvidia.com/gpu: 2
volumeMounts:
- name: devshm
mountPath: /dev/shm
- name: hf-cache
mountPath: /root/.cache/huggingface
env:
- name: HF_HOME
value: /root/.cache/huggingface
- name: VLLM_CI_HF_TOKEN
valueFrom:
secretKeyRef:
name: hf-token-secret
key: token
nodeSelector:
node.kubernetes.io/instance-type: gpu-h100-sxm
volumes:
- name: devshm
emptyDir:
medium: Memory
- name: hf-cache
hostPath:
path: /mnt/hf-cache
type: DirectoryOrCreate
h100_3:
agents:
queue: mithril-h100-pool
plugins:
- kubernetes:
podSpec:
containers:
- image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$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: VLLM_CI_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:$BUILDKITE_COMMIT
resources:
limits:
nvidia.com/gpu: 4
volumeMounts:
- name: devshm
mountPath: /dev/shm
- name: hf-cache
mountPath: /root/.cache/huggingface
env:
- name: HF_HOME
value: /root/.cache/huggingface
- name: VLLM_CI_HF_TOKEN
valueFrom:
secretKeyRef:
name: hf-token-secret
key: token
nodeSelector:
node.kubernetes.io/instance-type: gpu-h100-sxm
volumes:
- name: devshm
emptyDir:
medium: Memory
- name: hf-cache
hostPath:
path: /mnt/hf-cache
type: DirectoryOrCreate
# vLLM device: b200-k8s → agents.queue b200-k8s + Buildkite K8s agent-stack podSpec
b200_1:
agents:
queue: b200-k8s
plugins:
- kubernetes:
podSpec:
runtimeClassName: nvidia
hostNetwork: true
dnsPolicy: ClusterFirstWithHostNet
imagePullSecrets:
- name: k8s-ecr-login-renew-docker-secret
containers:
- image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
resources:
limits:
nvidia.com/gpu: 1
securityContext:
capabilities:
add:
- IPC_LOCK
- SYS_RESOURCE
volumeMounts:
- name: devshm
mountPath: /dev/shm
- name: raid
mountPath: /raid
- name: shared
mountPath: /mnt/shared
env:
- name: NCCL_CUMEM_HOST_ENABLE
value: "0"
- name: HF_HOME
value: /raid/hf_cache
- name: VLLM_CI_HF_TOKEN
valueFrom:
secretKeyRef:
name: hf-token-secret
key: token
volumes:
- name: devshm
emptyDir:
medium: Memory
- name: raid
hostPath:
path: /raid
type: DirectoryOrCreate
- name: shared
hostPath:
path: /mnt/shared
type: DirectoryOrCreate
b200_2:
agents:
queue: b200-k8s
plugins:
- kubernetes:
podSpec:
runtimeClassName: nvidia
hostNetwork: true
dnsPolicy: ClusterFirstWithHostNet
imagePullSecrets:
- name: k8s-ecr-login-renew-docker-secret
containers:
- image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
resources:
limits:
nvidia.com/gpu: 2
securityContext:
capabilities:
add:
- IPC_LOCK
- SYS_RESOURCE
volumeMounts:
- name: devshm
mountPath: /dev/shm
- name: raid
mountPath: /raid
- name: shared
mountPath: /mnt/shared
env:
- name: NCCL_CUMEM_HOST_ENABLE
value: "0"
- name: HF_HOME
value: /raid/hf_cache
- name: VLLM_CI_HF_TOKEN
valueFrom:
secretKeyRef:
name: hf-token-secret
key: token
volumes:
- name: devshm
emptyDir:
medium: Memory
- name: raid
hostPath:
path: /raid
type: DirectoryOrCreate
- name: shared
hostPath:
path: /mnt/shared
type: DirectoryOrCreate
b200_3:
agents:
queue: b200-k8s
plugins:
- kubernetes:
podSpec:
runtimeClassName: nvidia
hostNetwork: true
dnsPolicy: ClusterFirstWithHostNet
imagePullSecrets:
- name: k8s-ecr-login-renew-docker-secret
containers:
- image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
resources:
limits:
nvidia.com/gpu: 3
securityContext:
capabilities:
add:
- IPC_LOCK
- SYS_RESOURCE
volumeMounts:
- name: devshm
mountPath: /dev/shm
- name: raid
mountPath: /raid
- name: shared
mountPath: /mnt/shared
env:
- name: NCCL_CUMEM_HOST_ENABLE
value: "0"
- name: HF_HOME
value: /raid/hf_cache
- name: VLLM_CI_HF_TOKEN
valueFrom:
secretKeyRef:
name: hf-token-secret
key: token
volumes:
- name: devshm
emptyDir:
medium: Memory
- name: raid
hostPath:
path: /raid
type: DirectoryOrCreate
- name: shared
hostPath:
path: /mnt/shared
type: DirectoryOrCreate
b200_4:
agents:
queue: b200-k8s
plugins:
- kubernetes:
podSpec:
runtimeClassName: nvidia
hostNetwork: true
dnsPolicy: ClusterFirstWithHostNet
imagePullSecrets:
- name: k8s-ecr-login-renew-docker-secret
containers:
- image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
resources:
limits:
nvidia.com/gpu: 4
securityContext:
capabilities:
add:
- IPC_LOCK
- SYS_RESOURCE
volumeMounts:
- name: devshm
mountPath: /dev/shm
- name: raid
mountPath: /raid
- name: shared
mountPath: /mnt/shared
env:
- name: NCCL_CUMEM_HOST_ENABLE
value: "0"
- name: HF_HOME
value: /raid/hf_cache
- name: VLLM_CI_HF_TOKEN
valueFrom:
secretKeyRef:
name: hf-token-secret
key: token
volumes:
- name: devshm
emptyDir:
medium: Memory
- name: raid
hostPath:
path: /raid
type: DirectoryOrCreate
- name: shared
hostPath:
path: /mnt/shared
type: DirectoryOrCreate
a2b3_npu_1:
agents:
queue: "ascend-a2b3"
resource_class: "npu-1"
image: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry/vllm-omni-ci-npu:${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
a5_npu_2:
agents:
queue: "ascend-a5"
resource_class: "npu-2"
image: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry/vllm-omni-ci-npu:${BUILDKITE_COMMIT}-a5"
plugins: *npu_k8s_plugins
a5_npu_4:
agents:
queue: "ascend-a5"
resource_class: "npu-4"
image: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry/vllm-omni-ci-npu:${BUILDKITE_COMMIT}-a5"
plugins: *npu_k8s_plugins
a5_npu_8:
agents:
queue: "ascend-a5"
resource_class: "npu-8"
image: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry/vllm-omni-ci-npu:${BUILDKITE_COMMIT}-a5"
plugins: *npu_k8s_plugins
a5_npu_16:
agents:
queue: "ascend-a5"
resource_class: "npu-16"
image: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry/vllm-omni-ci-npu:${BUILDKITE_COMMIT}-a5"
plugins: *npu_k8s_plugins
310p_npu_1:
agents:
queue: "ascend-310p"
resource_class: "npu-1"
image: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry/vllm-omni-ci-npu:${BUILDKITE_COMMIT}-310p"
plugins: *npu_k8s_plugins
310p_npu_2:
agents:
queue: "ascend-310p"
resource_class: "npu-2"
image: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry/vllm-omni-ci-npu:${BUILDKITE_COMMIT}-310p"
plugins: *npu_k8s_plugins
310p_npu_4:
agents:
queue: "ascend-310p"
resource_class: "npu-4"
image: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry/vllm-omni-ci-npu:${BUILDKITE_COMMIT}-310p"
plugins: *npu_k8s_plugins
Reference in new issue View Git Blame Copy Permalink