Files
vllm-omni/.buildkite/pipeline-npu.yaml
T

196 lines
9.1 KiB
YAML

steps:
- label: ":buildkit: Build and Push NPU Test Image - A2"
key: image-build
agents:
queue: "ascend-a2b3"
resource_class: "npu-1"
plugins:
- kubernetes:
metadata:
annotations:
vault.hashicorp.com/agent-init-first: "true"
vault.hashicorp.com/agent-inject: "true"
vault.hashicorp.com/agent-inject-perms-ca.pem: "0400"
vault.hashicorp.com/agent-inject-perms-cert.pem: "0400"
vault.hashicorp.com/agent-inject-perms-config.json: "0400"
vault.hashicorp.com/agent-inject-perms-key.pem: "0400"
vault.hashicorp.com/agent-inject-secret-ca.pem: internal/data/ascend/buildkitd
vault.hashicorp.com/agent-inject-secret-cert.pem: internal/data/ascend/buildkitd
vault.hashicorp.com/agent-inject-secret-config.json: internal/data/ascend/buildkitd
vault.hashicorp.com/agent-inject-secret-key.pem: internal/data/ascend/buildkitd
vault.hashicorp.com/agent-inject-template-ca.pem: "{{- with secret \"internal/data/ascend/buildkitd\" -}}\n{{ .Data.data.RootCA }}\n{{- end }}"
vault.hashicorp.com/agent-inject-template-cert.pem: "{{- with secret \"internal/data/ascend/buildkitd\" -}}\n{{ .Data.data.ClientCaCert }}\n{{- end }}"
vault.hashicorp.com/agent-inject-template-config.json: "{{- with secret \"internal/data/ascend/buildkitd\" -}}\n{{ .Data.data.dockerConfig }}\n{{- end }}"
vault.hashicorp.com/agent-inject-template-key.pem: "{{- with secret \"internal/data/ascend/buildkitd\" -}}\n{{ .Data.data.ClientCaKey }}\n{{- end }}"
vault.hashicorp.com/agent-pre-populate-only: "true"
vault.hashicorp.com/agent-run-as-group: "1000"
vault.hashicorp.com/agent-run-as-user: "1000"
vault.hashicorp.com/agent-service-account-token-volume-name: token-vol
vault.hashicorp.com/role: ascend-gha-runners
vault.hashicorp.com/secret-volume-path: /home/user/.docker/
vault.hashicorp.com/tls-skip-verify: "true"
podSpecPatch:
volumes:
- name: token-vol
projected:
defaultMode: 420
sources:
- serviceAccountToken:
audience: api
expirationSeconds: 600
path: token
env:
VLLM_IMAGE_TAG: "${BUILDKITE_COMMIT}"
IMAGE_NAME: "vllm-omni-ci-npu"
IMAGE_REGISTRY: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry"
BUILDKITD_ADDR: "tcp://buildkitd-service.buildkitd:1234"
command: |
set -ex
echo "--- Building and pushing NPU Test Image"
echo "Image: $${IMAGE_REGISTRY}/$${IMAGE_NAME}:$${VLLM_IMAGE_TAG}"
echo "buildkitd address: $${BUILDKITD_ADDR}"
if ! command -v buildctl &> /dev/null; then
echo "Installing buildctl..."
mkdir -p /tmp/buildkit
BUILDKIT_VERSION="v0.29.0"
wget -q "https://github.com/moby/buildkit/releases/download/$${BUILDKIT_VERSION}/buildkit-$${BUILDKIT_VERSION}.linux-arm64.tar.gz" -O /tmp/buildkit.tar.gz
tar -xzf /tmp/buildkit.tar.gz -C /tmp/buildkit
cp /tmp/buildkit/bin/buildctl /usr/local/bin/
fi
export DOCKER_CONFIG=/home/user/.docker
buildctl \
--addr="$${BUILDKITD_ADDR}" \
--tlscacert=/home/user/.docker/ca.pem \
--tlscert=/home/user/.docker/cert.pem \
--tlskey=/home/user/.docker/key.pem \
build \
--frontend dockerfile.v0 \
--local context=. \
--local dockerfile=./docker \
--opt filename=Dockerfile.npu.ci \
--secret id=dockerconfig,src=/home/user/.docker/config.json \
--output type=image,name=$${IMAGE_REGISTRY}/$${IMAGE_NAME}:$${VLLM_IMAGE_TAG},push=true \
--progress=plain
echo "--- Image pushed successfully"
echo "$${IMAGE_REGISTRY}/$${IMAGE_NAME}:$${VLLM_IMAGE_TAG}"
- label: ":buildkit: Build and Push NPU Test Image - A3"
key: image-build-a3
agents:
queue: "ascend-a2b3"
resource_class: "npu-1"
plugins:
- kubernetes:
metadata:
annotations:
vault.hashicorp.com/agent-init-first: "true"
vault.hashicorp.com/agent-inject: "true"
vault.hashicorp.com/agent-inject-perms-ca.pem: "0400"
vault.hashicorp.com/agent-inject-perms-cert.pem: "0400"
vault.hashicorp.com/agent-inject-perms-config.json: "0400"
vault.hashicorp.com/agent-inject-perms-key.pem: "0400"
vault.hashicorp.com/agent-inject-secret-ca.pem: internal/data/ascend/buildkitd
vault.hashicorp.com/agent-inject-secret-cert.pem: internal/data/ascend/buildkitd
vault.hashicorp.com/agent-inject-secret-config.json: internal/data/ascend/buildkitd
vault.hashicorp.com/agent-inject-secret-key.pem: internal/data/ascend/buildkitd
vault.hashicorp.com/agent-inject-template-ca.pem: "{{- with secret \"internal/data/ascend/buildkitd\" -}}\n{{ .Data.data.RootCA }}\n{{- end }}"
vault.hashicorp.com/agent-inject-template-cert.pem: "{{- with secret \"internal/data/ascend/buildkitd\" -}}\n{{ .Data.data.ClientCaCert }}\n{{- end }}"
vault.hashicorp.com/agent-inject-template-config.json: "{{- with secret \"internal/data/ascend/buildkitd\" -}}\n{{ .Data.data.dockerConfig }}\n{{- end }}"
vault.hashicorp.com/agent-inject-template-key.pem: "{{- with secret \"internal/data/ascend/buildkitd\" -}}\n{{ .Data.data.ClientCaKey }}\n{{- end }}"
vault.hashicorp.com/agent-pre-populate-only: "true"
vault.hashicorp.com/agent-run-as-group: "1000"
vault.hashicorp.com/agent-run-as-user: "1000"
vault.hashicorp.com/agent-service-account-token-volume-name: token-vol
vault.hashicorp.com/role: ascend-gha-runners
vault.hashicorp.com/secret-volume-path: /home/user/.docker/
vault.hashicorp.com/tls-skip-verify: "true"
podSpecPatch:
volumes:
- name: token-vol
projected:
defaultMode: 420
sources:
- serviceAccountToken:
audience: api
expirationSeconds: 600
path: token
env:
VLLM_IMAGE_TAG: "${BUILDKITE_COMMIT}-a3"
IMAGE_NAME: "vllm-omni-ci-npu"
IMAGE_REGISTRY: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry"
BUILDKITD_ADDR: "tcp://buildkitd-service.buildkitd:1234"
command: |
set -ex
echo "--- Building and pushing NPU Test Image"
echo "Image: $${IMAGE_REGISTRY}/$${IMAGE_NAME}:$${VLLM_IMAGE_TAG}"
echo "buildkitd address: $${BUILDKITD_ADDR}"
if ! command -v buildctl &> /dev/null; then
echo "Installing buildctl..."
mkdir -p /tmp/buildkit
BUILDKIT_VERSION="v0.29.0"
wget -q "https://github.com/moby/buildkit/releases/download/$${BUILDKIT_VERSION}/buildkit-$${BUILDKIT_VERSION}.linux-arm64.tar.gz" -O /tmp/buildkit.tar.gz
tar -xzf /tmp/buildkit.tar.gz -C /tmp/buildkit
cp /tmp/buildkit/bin/buildctl /usr/local/bin/
fi
export DOCKER_CONFIG=/home/user/.docker
buildctl \
--addr="$${BUILDKITD_ADDR}" \
--tlscacert=/home/user/.docker/ca.pem \
--tlscert=/home/user/.docker/cert.pem \
--tlskey=/home/user/.docker/key.pem \
build \
--frontend dockerfile.v0 \
--local context=. \
--local dockerfile=./docker \
--opt filename=Dockerfile.npu.ci.a3 \
--secret id=dockerconfig,src=/home/user/.docker/config.json \
--output type=image,name=$${IMAGE_REGISTRY}/$${IMAGE_NAME}:$${VLLM_IMAGE_TAG},push=true \
--progress=plain
echo "--- Image pushed successfully"
echo "$${IMAGE_REGISTRY}/$${IMAGE_NAME}:$${VLLM_IMAGE_TAG}"
- label: "Upload Ready Pipeline"
depends_on:
- image-build
- image-build-a3
key: upload-ready-pipeline
if: >-
build.branch != "main" && (
build.pull_request.labels includes "npu-test" ||
build.pull_request.labels includes "ready"
)
agents:
queue: "ascend-a2b3"
resource_class: "npu-1"
command: |
buildkite-agent pipeline upload .buildkite/test-npu-ready.yaml
# L4 Test — main+NIGHTLY=1 (scheduled), or PR with specific label (e.g. add label then Rebuild)
- label: "Upload Nightly Pipeline"
depends_on:
- image-build
- image-build-a3
key: upload-nightly-pipeline
if: >-
(build.branch == "main" && build.env("NIGHTLY") == "1") ||
(build.branch != "main" && (
build.pull_request.labels includes "nightly-test" ||
build.pull_request.labels includes "omni-test" ||
build.pull_request.labels includes "tts-test" ||
build.pull_request.labels includes "diffusion-x2iat-test" ||
build.pull_request.labels includes "diffusion-x2v-test"
))
commands:
- buildkite-agent pipeline upload .buildkite/test-npu-nightly.yaml
agents:
queue: "ascend-a2b3"
resource_class: "npu-1"