[NPU][CI] Add A5 and 310P CI support (#6875)

Signed-off-by: Weiming Liao <liaowm5@gmail.com>
Co-authored-by: wangyu <53896905+yenuo26@users.noreply.github.com>
This commit is contained in:
Weiming Liaoandwangyu authored and GitHub committed 2026-09-10 02:16:14 +00:00
1 parent 3d71a2b3ad
commit 35a83a0885
14 files changed
+387 -308

No files matched your search

+51
View File
@@ -17,6 +17,8 @@
# 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 …:$BUILDKITE_COMMIT-a3)
# a5_npu_2 — ascend-a5, resource_class npu-2
# 310p_npu_1 — ascend-310p, resource_class npu-1
#
# B200 (b200-k8s): matches vLLM device ``b200-k8s`` from ci-infra
# (AgentQueue.B200_K8S + b200_plugin_template). Queue routes the K8s pool;
@@ -646,3 +648,52 @@ mirror_hardwares:
resource_class: "npu-16"
image: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry/vllm-omni-ci-npu:${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
+9 -1
View File
@@ -70,7 +70,15 @@ from tests.helpers.mark import ( # noqa: E402
LOG = "upload_pipeline"
BOOTSTRAP_STEPS_FILENAME = "bootstrap-upload-steps.yml"
BOOTSTRAP_IMAGE_BUILD_KEYS = frozenset({"image-build", "image-build-a2", "image-build-a3"})
BOOTSTRAP_IMAGE_BUILD_KEYS = frozenset(
{
"image-build",
"image-build-a2",
"image-build-a3",
"image-build-a5",
"image-build-310p",
}
)
BOOTSTRAP_UPLOAD_IF_KEYS = {
"upload-ready-pipeline": "ready",
"upload-merge-pipeline": "merge",
+30 -104
View File
@@ -3,10 +3,10 @@
steps:
- label: ":buildkit: Build and Push NPU Test Image - A2"
key: image-build-a2
agents:
agents: &npu-image-build-agents
queue: "ascend-a2b3"
resource_class: "npu-1"
plugins:
plugins: &npu-image-build-plugins
- kubernetes:
metadata:
annotations:
@@ -46,123 +46,47 @@ steps:
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}:$${VLLM_IMAGE_TAG}"
command: bash .buildkite/npu/scripts/build-npu-image.sh Dockerfile.npu.ci "$${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
agents: *npu-image-build-agents
plugins: *npu-image-build-plugins
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
command: bash .buildkite/npu/scripts/build-npu-image.sh Dockerfile.npu.ci "$${VLLM_IMAGE_TAG}" -a3
echo "--- Building and pushing NPU Test Image"
echo "Image: $${IMAGE_REGISTRY}/$${IMAGE_NAME}:$${VLLM_IMAGE_TAG}"
echo "buildkitd address: $${BUILDKITD_ADDR}"
- label: ":buildkit: Build and Push NPU Test Image - A5"
key: image-build-a5
agents: *npu-image-build-agents
plugins: *npu-image-build-plugins
env:
VLLM_IMAGE_TAG: "${BUILDKITE_COMMIT}-a5"
IMAGE_NAME: "vllm-omni-ci-npu"
IMAGE_REGISTRY: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry"
BUILDKITD_ADDR: "tcp://buildkitd-service.buildkitd:1234"
command: bash .buildkite/npu/scripts/build-npu-image.sh Dockerfile.npu.ci "$${VLLM_IMAGE_TAG}" -a5
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}:$${VLLM_IMAGE_TAG}"
- label: ":buildkit: Build and Push NPU Test Image - 310P"
key: image-build-310p
agents: *npu-image-build-agents
plugins: *npu-image-build-plugins
env:
VLLM_IMAGE_TAG: "${BUILDKITE_COMMIT}-310p"
IMAGE_NAME: "vllm-omni-ci-npu"
IMAGE_REGISTRY: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry"
BUILDKITD_ADDR: "tcp://buildkitd-service.buildkitd:1234"
command: bash .buildkite/npu/scripts/build-npu-image.sh Dockerfile.npu.ci "$${VLLM_IMAGE_TAG}" -310p
- label: "Upload Ready Pipeline"
depends_on:
- image-build-a2
- image-build-a3
- image-build-a5
- image-build-310p
key: upload-ready-pipeline
agents:
queue: "cpu_queue_premerge"
@@ -174,6 +98,8 @@ steps:
depends_on:
- image-build-a2
- image-build-a3
- image-build-a5
- image-build-310p
key: upload-nightly-pipeline
commands:
- python3 .buildkite/common/scripts/upload_pipeline.py --upload .buildkite/npu/test-npu-nightly.yml
+48
View File
@@ -0,0 +1,48 @@
#!/usr/bin/env bash
set -ex
dockerfile=${1:?Dockerfile is required}
image_tag=${2:?Image tag is required}
device_suffix=${3:-}
image_name=${IMAGE_NAME:-vllm-omni-ci-npu}
image_registry=${IMAGE_REGISTRY:-swr.cn-southwest-2.myhuaweicloud.com/modelfoundry}
buildkitd_addr=${BUILDKITD_ADDR:-tcp://buildkitd-service.buildkitd:1234}
echo "--- Building and pushing NPU Test Image"
echo "Image: ${image_registry}/${image_name}:${image_tag}"
echo "Dockerfile: ${dockerfile}"
if ! command -v buildctl &> /dev/null; then
mkdir -p /tmp/buildkit
buildkit_version=v0.29.0
wget -q \
"https://github.com/moby/buildkit/releases/download/${buildkit_version}/buildkit-${buildkit_version}.linux-arm64.tar.gz" \
-O /tmp/buildkit.tar.gz
tar -xzf /tmp/buildkit.tar.gz -C /tmp/buildkit
cp /tmp/buildkit/bin/buildctl /usr/local/bin/
fi
build_args=()
if [[ -n "${device_suffix}" ]]; then
build_args+=(--opt "build-arg:VLLM_ASCEND_DEVICE_SUFFIX=${device_suffix}")
fi
export DOCKER_CONFIG=/home/user/.docker
buildctl \
--addr="${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=${dockerfile}" \
"${build_args[@]}" \
--secret id=dockerconfig,src=/home/user/.docker/config.json \
--output "type=image,name=${image_registry}/${image_name}:${image_tag},push=true" \
--progress=plain
echo "--- Image pushed successfully"
echo "${image_registry}/${image_name}:${image_tag}"
+53 -22
View File
@@ -1,28 +1,59 @@
steps:
- label: "Platforms Test"
key: ready-platforms-test
- group: ":card_index_dividers: Simple Test"
depends_on: upload-ready-pipeline
mirror_hardwares: a3_npu_2
commands:
- >-
pytest -s -v
tests/platforms/npu/test_minicpmo_code2wav_npugraph.py
-m 'core_model and npu and A3 and omni'
--run-level 'core_model'
steps:
- label: "Platforms Test"
key: ready-platforms-test
mirror_hardwares: a3_npu_2
commands:
- >-
pytest -s -v
tests/platforms/npu/test_minicpmo_code2wav_npugraph.py
-m 'core_model and npu and A3 and omni'
--run-level 'core_model'
- label: "Diffusion NPU layer tests"
key: ready-diffusion-npu-layer-tests
depends_on: upload-ready-pipeline
mirror_hardwares: a3_npu_2
commands:
- >-
pytest -s -v
tests/diffusion/layers/test_activation.py
tests/diffusion/layers/test_fused_qk_norm_rope_npu.py
tests/diffusion/models/minimax_h3/test_minimax_h3_qwen3vl_swiglu.py
tests/diffusion/models/minimax_h3/test_minimax_h3_modulation.py
-m 'core_model and npu and A3'
--run-level 'core_model'
- label: "Diffusion NPU layer tests - A2"
key: ready-diffusion-npu-layer-tests-a2
mirror_hardwares: a2b3_npu_1
commands:
- >-
pytest -s -v
tests/diffusion/layers/test_activation.py
-m 'core_model and npu and A2'
--run-level 'core_model'
- label: "Diffusion NPU layer tests - A3"
key: ready-diffusion-npu-layer-tests
mirror_hardwares: a3_npu_2
commands:
- >-
pytest -s -v
tests/diffusion/layers/test_activation.py
tests/diffusion/layers/test_fused_qk_norm_rope_npu.py
tests/diffusion/models/minimax_h3/test_minimax_h3_qwen3vl_swiglu.py
tests/diffusion/models/minimax_h3/test_minimax_h3_modulation.py
-m 'core_model and npu and A3'
--run-level 'core_model'
- label: "Diffusion NPU layer tests - A5"
key: ready-diffusion-npu-layer-tests-a5
mirror_hardwares: a5_npu_2
commands:
- >-
pytest -s -v
tests/diffusion/layers/test_activation.py
-m 'core_model and npu and A5'
--run-level 'core_model'
- label: "Diffusion NPU layer tests - 310P"
key: ready-diffusion-npu-layer-tests-310p
mirror_hardwares: 310p_npu_1
commands:
- >-
pytest -s -v
tests/diffusion/layers/test_activation.py
-m 'core_model and npu and 310P'
--run-level 'core_model'
- group: ":card_index_dividers: Omni Model Test"
key: ready-omni-group
+4 -16
View File
@@ -1,20 +1,7 @@
ARG VLLM_ASCEND_IMAGE=quay.io/atlas-ci/vllm-ascend
ARG VLLM_ASCEND_TAG=v0.28.0
FROM ${VLLM_ASCEND_IMAGE}:${VLLM_ASCEND_TAG}
# WORKDIR /vllm-workspace/vllm
# RUN git fetch origin --tags && git checkout v0.18.0
# WORKDIR /vllm-workspace/vllm-ascend
# RUN git fetch origin releases/v0.18.0 && git checkout d781902ce9dbda8ab1e11bb0f2f0c1bc508fee7a
# # Install vllm-ascend
# # Append `libascend_hal.so` path (devlib) to LD_LIBRARY_PATH
# RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi && \
# source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
# source /usr/local/Ascend/nnal/atb/set_env.sh && \
# export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/`uname -i`-linux/devlib && \
# python3 -m pip install -v -e /vllm-workspace/vllm-ascend/ --extra-index https://download.pytorch.org/whl/cpu/ && \
# python3 -m pip cache purge
ARG VLLM_ASCEND_VERSION=v0.28.0
ARG VLLM_ASCEND_DEVICE_SUFFIX=
FROM ${VLLM_ASCEND_IMAGE}:${VLLM_ASCEND_VERSION}${VLLM_ASCEND_DEVICE_SUFFIX}
ARG APP_DIR=/vllm-workspace/vllm-omni
WORKDIR ${APP_DIR}
@@ -24,6 +11,7 @@ RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi
source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
source /usr/local/Ascend/nnal/atb/set_env.sh && \
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/`uname -i`-linux/devlib && \
python3 -m pip install -v "mindiesd==3.1.0" && \
python3 -m pip install -v -e /vllm-workspace/vllm-omni/ --no-build-isolation
RUN python3 -m pip install -v --no-deps \
-36
View File
@@ -1,36 +0,0 @@
ARG VLLM_ASCEND_IMAGE=quay.io/atlas-ci/vllm-ascend
ARG VLLM_ASCEND_TAG=v0.28.0-a3
FROM ${VLLM_ASCEND_IMAGE}:${VLLM_ASCEND_TAG}
# WORKDIR /vllm-workspace/vllm
# RUN git fetch origin --tags && git checkout v0.18.0
# WORKDIR /vllm-workspace/vllm-ascend
# RUN git fetch origin releases/v0.18.0 && git checkout d781902ce9dbda8ab1e11bb0f2f0c1bc508fee7a
# # Install vllm-ascend
# # Append `libascend_hal.so` path (devlib) to LD_LIBRARY_PATH
# RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi && \
# source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
# source /usr/local/Ascend/nnal/atb/set_env.sh && \
# export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/`uname -i`-linux/devlib && \
# python3 -m pip install -v -e /vllm-workspace/vllm-ascend/ --extra-index https://download.pytorch.org/whl/cpu/ && \
# python3 -m pip cache purge
ARG APP_DIR=/vllm-workspace/vllm-omni
WORKDIR ${APP_DIR}
COPY . .
RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi && \
source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
source /usr/local/Ascend/nnal/atb/set_env.sh && \
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/`uname -i`-linux/devlib && \
python3 -m pip install -v -e /vllm-workspace/vllm-omni/ --no-build-isolation
RUN python3 -m pip install -v --no-deps \
"stepaudio2-minicpmo>=0.1.1" \
"step-audio2>=1.0.0"
ENV VLLM_TARGET_DEVICE=npu
ENV VLLM_WORKER_MULTIPROC_METHOD=spawn
ENTRYPOINT []
+12 -8
View File
@@ -1,10 +1,10 @@
ARG VLLM_ASCEND_IMAGE=quay.io/atlas-ci/vllm-ascend
ARG VLLM_ASCEND_TAG=v0.28.0
FROM ${VLLM_ASCEND_IMAGE}:${VLLM_ASCEND_TAG}
ARG VLLM_ASCEND_VERSION=v0.28.0
ARG VLLM_ASCEND_DEVICE_SUFFIX=
FROM ${VLLM_ASCEND_IMAGE}:${VLLM_ASCEND_VERSION}${VLLM_ASCEND_DEVICE_SUFFIX}
ARG APP_DIR=/vllm-workspace/vllm-omni
WORKDIR ${APP_DIR}
COPY . .
RUN sed -i "s@^\(deb.*\)https\?://[a-z0-9.-]*\.ubuntu\.com@\1http://cache-service.nginx-pypi-cache.svc.cluster.local:8081@g" /etc/apt/sources.list
@@ -22,11 +22,9 @@ RUN apt-get update && \
rm -rf /var/cache/apt/* && \
rm -rf /var/lib/apt/lists/*
RUN source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
source /usr/local/Ascend/nnal/atb/set_env.sh && \
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/`uname -i`-linux/devlib && \
python3 -m pip install -U pip && \
RUN python3 -m pip install -U pip && \
python3 -m pip install -v \
"mindiesd==3.1.0" \
"pytest>=7.0.0" \
"pytest-asyncio>=0.21.0" \
"pytest-cov>=4.0.0" \
@@ -48,7 +46,13 @@ RUN source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
"datasets>=3.0.0" \
--index-url http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple \
--trusted-host cache-service.nginx-pypi-cache.svc.cluster.local \
--default-timeout=60 && \
--default-timeout=60
COPY . .
RUN source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
source /usr/local/Ascend/nnal/atb/set_env.sh && \
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/`uname -i`-linux/devlib && \
python3 -m pip install -v -e /vllm-workspace/vllm-omni/ --no-build-isolation \
--index-url http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple \
--trusted-host cache-service.nginx-pypi-cache.svc.cluster.local \
-72
View File
@@ -1,72 +0,0 @@
ARG VLLM_ASCEND_IMAGE=quay.io/atlas-ci/vllm-ascend
ARG VLLM_ASCEND_TAG=v0.28.0-a3
FROM ${VLLM_ASCEND_IMAGE}:${VLLM_ASCEND_TAG}
ARG APP_DIR=/vllm-workspace/vllm-omni
WORKDIR ${APP_DIR}
COPY . .
RUN sed -i "s@^\(deb.*\)https\?://[a-z0-9.-]*\.ubuntu\.com@\1http://cache-service.nginx-pypi-cache.svc.cluster.local:8081@g" /etc/apt/sources.list
RUN apt-get update && \
apt-get install -y --no-install-recommends \
ffmpeg \
libgl1 \
libglib2.0-0 \
libgomp1 \
libsm6 \
libxext6 \
libxrender1 \
libxcb1 \
espeak-ng && \
rm -rf /var/cache/apt/* && \
rm -rf /var/lib/apt/lists/*
RUN source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
source /usr/local/Ascend/nnal/atb/set_env.sh && \
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/`uname -i`-linux/devlib && \
python3 -m pip install -U pip && \
python3 -m pip install -v \
"pytest>=7.0.0" \
"pytest-asyncio>=0.21.0" \
"pytest-cov>=4.0.0" \
"pytest-mock>=3.10.0" \
"openpyxl>=3.0.0" \
"psutil>=7.2.0" \
"soundfile>=0.13.1" \
"pyttsx3>=2.99" \
"opencc==1.4.1" \
"opencv-python>=4.12.0.88" \
"imageio[ffmpeg]>=0.6.0" \
"jiwer>=3.0.0" \
"zhon>=2.0.0" \
"zhconv>=1.4.2" \
"funasr>=1.0.0" \
"hyperpyyaml>=1.2.0" \
"onnx>=1.16.0" \
"librosa>=0.10.0" \
"torchmetrics>=1.9.0" \
"datasets>=3.0.0" \
--index-url http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple \
--trusted-host cache-service.nginx-pypi-cache.svc.cluster.local \
--default-timeout=60 && \
python3 -m pip install -v -e /vllm-workspace/vllm-omni/ --no-build-isolation \
--index-url http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple \
--trusted-host cache-service.nginx-pypi-cache.svc.cluster.local \
--default-timeout=60
# MiniCPM-o 4.5 Stage-2 vocoder assets: s3tokenizer plus flashcosyvoice, which
# is shipped by step-audio2. --no-deps keeps pip from replacing the Ascend torch
# build and from shadowing onnxruntime-cann with the vanilla onnxruntime wheel;
# the deps these two actually need are installed above.
RUN python3 -m pip install -v --no-deps \
"s3tokenizer>=0.3.0" \
"step-audio2>=1.0.0" \
--index-url http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple \
--trusted-host cache-service.nginx-pypi-cache.svc.cluster.local \
--default-timeout=60
ENV VLLM_TARGET_DEVICE=npu
ENV VLLM_WORKER_MULTIPROC_METHOD=spawn
ENTRYPOINT []
+7 -2
View File
@@ -129,7 +129,7 @@ Canonical layout (prefer these paths for new changes):
=== "NPU"
**Bootstrap:** [`npu/pipeline-npu.yml`](https://github.com/vllm-project/vllm-omni/blob/main/.buildkite/npu/pipeline-npu.yml) + [`npu/bootstrap-upload-steps.yml`](https://github.com/vllm-project/vllm-omni/blob/main/.buildkite/npu/bootstrap-upload-steps.yml)—same split as CUDA; builds A2/B3 and A3 CI images, then uploads child test pipelines.
**Bootstrap:** [`npu/pipeline-npu.yml`](https://github.com/vllm-project/vllm-omni/blob/main/.buildkite/npu/pipeline-npu.yml) + [`npu/bootstrap-upload-steps.yml`](https://github.com/vllm-project/vllm-omni/blob/main/.buildkite/npu/bootstrap-upload-steps.yml)—same split as CUDA; builds A2/B3, A3, A5, and 310P CI images, then uploads child test pipelines.
**Test YAML:** `npu/test-npu-ready.yml` (L2), `test-npu-nightly.yml` (L4).
@@ -137,7 +137,12 @@ Canonical layout (prefer these paths for new changes):
**Upload:** same as CUDA—`upload_pipeline.py --upload`.
**Hardware in YAML:** `mirror_hardwares` preset (string), expanded to `agents`, top-level `image`, and `plugins`. Presets: `a2b3_npu_1`, `a2b3_npu_4`, `a3_npu_2` in `common/ci_mirror_hardwares.yml`.
**Hardware in YAML:** `mirror_hardwares` preset (string), expanded to `agents`, top-level `image`, and `plugins`. NPU presets in `common/ci_mirror_hardwares.yml` are:
- A2: `a2b3_npu_1`, `a2b3_npu_4`, `a2b3_npu_8`
- A3: `a3_npu_2`, `a3_npu_4`, `a3_npu_8`, `a3_npu_16`
- A5: `a5_npu_2`, `a5_npu_4`, `a5_npu_8`, `a5_npu_16`
- 310P: `310p_npu_1`, `310p_npu_2`, `310p_npu_4`
**Conventions**
+3 -1
View File
@@ -48,6 +48,8 @@ Defined in `pyproject.toml`:
| `MI325` | Tests that require MI325 GPU (AMD/ROCm) * |
| `A2` | Tests that require A2 NPU * |
| `A3` | Tests that require A3 NPU * |
| `A5` | Tests that require A5 NPU * |
| `310P` | Tests that require 310P NPU * |
| `cards_{n}` | Tests that require *n* accelerator cards (`cards_1` … `cards_8`); auto-added from `num_cards` * |
| `slow` | Slow tests (may skip in quick CI) |
| `benchmark` | Benchmark tests (decorator on runner test functions; perf JSON uses `full_model` + type marker instead) |
@@ -76,7 +78,7 @@ def test_video_to_audio()
This decorator is intended to make hardware-aware, cross-platform test authoring easier and more robust for CI/CD environments. The `hardware_test` decorator in `vllm-omni/tests/helpers/mark.py` performs the following actions:
1. **Applies platform and resource markers**
Adds the appropriate pytest markers for each specified hardware platform (e.g., `cuda`, `rocm`, `xpu`, `npu`) and resource type (e.g., `L4`, `H100`, `H200`, `B200`, `MI325`, `B60`, `A2`, `A3`).
Adds the appropriate pytest markers for each specified hardware platform (e.g., `cuda`, `rocm`, `xpu`, `npu`) and resource type (e.g., `L4`, `H100`, `H200`, `B200`, `MI325`, `B60`, `A2`, `A3`, `A5`, `310P`).
```python
@pytest.mark.cuda
@pytest.mark.L4
+156 -42
View File
@@ -7,13 +7,34 @@ For detailed hardware and software requirements, please refer to the [vLLM-Ascen
The recommended way to use vLLM-Omni on NPU is through the vLLM-Ascend pre-built Docker images:
=== "A2"
```bash
export IMAGE=quay.io/atlas-ci/vllm-ascend:v0.28.0
```
=== "A3"
```bash
export IMAGE=quay.io/atlas-ci/vllm-ascend:v0.28.0-a3
```
=== "A5"
```bash
export IMAGE=quay.io/atlas-ci/vllm-ascend:v0.28.0-a5
```
=== "310P (Experimental)"
```bash
export IMAGE=quay.io/atlas-ci/vllm-ascend:v0.28.0-310p
```
```bash
# vLLM-Ascend image
# Atlas A2: quay.io/atlas-ci/vllm-ascend:v0.28.0
# Atlas A3: quay.io/atlas-ci/vllm-ascend:v0.28.0-a3
docker run --rm \
--name vllm-omni-npu \
--shm-size=1g \
--shm-size=64g \
--device /dev/davinci0 \
--device /dev/davinci1 \
--device /dev/davinci2 \
@@ -27,8 +48,8 @@ docker run --rm \
-v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \
-v /etc/ascend_install.info:/etc/ascend_install.info \
-v /root/.cache:/root/.cache \
-p 8000:8000 \
-it quay.io/atlas-ci/vllm-ascend:v0.28.0-a3 bash
-p 8091:8091 \
-it "$IMAGE" bash
# Inside the container, install vLLM-Omni from source
cd /vllm-workspace
@@ -72,53 +93,146 @@ Supported images as following.
| image name | Hardware | OS |
|-|-|-|
| image-tag | Atlas A2 | Ubuntu |
| image-tag-a3 | Atlas A3 | Ubuntu |
| image-tag | A2 | Ubuntu |
| image-tag-a3 | A3 | Ubuntu |
| image-tag-a5 | A5 | Ubuntu |
| image-tag-310p | 310P (experimental) | Ubuntu |
Here's an example deployment command that has been verified on 4 x NPUs:
```bash
# Atlas A2: quay.io/ascend/vllm-omni:v0.28.0
# Atlas A3: quay.io/ascend/vllm-omni:v0.28.0-a3
docker run --rm \
--name vllm-omni-a3 \
--shm-size=4g \
--device /dev/davinci0 \
--device /dev/davinci1 \
--device /dev/davinci2 \
--device /dev/davinci3 \
--device /dev/davinci_manager \
--device /dev/devmm_svm \
--device /dev/hisi_hdc \
-v /usr/local/dcmi:/usr/local/dcmi \
-v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \
-v /usr/local/Ascend/driver/lib64/:/usr/local/Ascend/driver/lib64/ \
-v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \
--device /dev/davinci_manager \
--device /dev/devmm_svm \
--device /dev/hisi_hdc \
-v /usr/local/dcmi:/usr/local/dcmi \
-v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \
-v /usr/local/Ascend/driver/lib64/:/usr/local/Ascend/driver/lib64/ \
-v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \
-v /etc/ascend_install.info:/etc/ascend_install.info \
-v ~/.cache:/root/.cache \
-p 8091:8091 \
-it quay.io/ascend/vllm-omni:v0.28.0-a3 bash
```
=== "A2"
```bash
export IMAGE=quay.io/ascend/vllm-omni:v0.28.0
docker run --rm \
--name vllm-omni-a2 \
--shm-size=64g \
--device /dev/davinci0 \
--device /dev/davinci1 \
--device /dev/davinci2 \
--device /dev/davinci3 \
--device /dev/davinci_manager \
--device /dev/devmm_svm \
--device /dev/hisi_hdc \
-v /usr/local/dcmi:/usr/local/dcmi \
-v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \
-v /usr/local/Ascend/driver/lib64/:/usr/local/Ascend/driver/lib64/ \
-v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \
-v /etc/ascend_install.info:/etc/ascend_install.info \
-v ~/.cache:/root/.cache \
-p 8091:8091 \
-it "$IMAGE" bash
```
=== "A3"
```bash
export IMAGE=quay.io/ascend/vllm-omni:v0.28.0-a3
docker run --rm \
--name vllm-omni-a3 \
--shm-size=64g \
--device /dev/davinci0 \
--device /dev/davinci1 \
--device /dev/davinci2 \
--device /dev/davinci3 \
--device /dev/davinci_manager \
--device /dev/devmm_svm \
--device /dev/hisi_hdc \
-v /usr/local/dcmi:/usr/local/dcmi \
-v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \
-v /usr/local/Ascend/driver/lib64/:/usr/local/Ascend/driver/lib64/ \
-v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \
-v /etc/ascend_install.info:/etc/ascend_install.info \
-v ~/.cache:/root/.cache \
-p 8091:8091 \
-it "$IMAGE" bash
```
=== "A5"
```bash
export IMAGE=quay.io/ascend/vllm-omni:v0.28.0-a5
docker run --rm \
--name vllm-omni-a5 \
--shm-size=64g \
--device /dev/davinci0 \
--device /dev/davinci1 \
--device /dev/davinci2 \
--device /dev/davinci3 \
--device /dev/davinci_manager \
--device /dev/devmm_svm \
--device /dev/hisi_hdc \
-v /usr/local/dcmi:/usr/local/dcmi \
-v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \
-v /usr/local/Ascend/driver/lib64/:/usr/local/Ascend/driver/lib64/ \
-v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \
-v /etc/ascend_install.info:/etc/ascend_install.info \
-v ~/.cache:/root/.cache \
-p 8091:8091 \
-it "$IMAGE" bash
```
=== "310P (Experimental)"
```bash
export IMAGE=quay.io/ascend/vllm-omni:v0.28.0-310p
docker run --rm \
--name vllm-omni-310p \
--shm-size=64g \
--device /dev/davinci0 \
--device /dev/davinci1 \
--device /dev/davinci2 \
--device /dev/davinci3 \
--device /dev/davinci_manager \
--device /dev/devmm_svm \
--device /dev/hisi_hdc \
-v /usr/local/dcmi:/usr/local/dcmi \
-v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \
-v /usr/local/Ascend/driver/lib64/:/usr/local/Ascend/driver/lib64/ \
-v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \
-v /etc/ascend_install.info:/etc/ascend_install.info \
-v ~/.cache:/root/.cache \
-p 8091:8091 \
-it "$IMAGE" bash
```
!!! tip
You can use this docker image to serve models the same way you would with in vLLM! To do so, make sure you overwrite the default entrypoint (`vllm serve --omni`) which works only for models supported in the vLLM-Omni project.
Or build IMAGE from **source code**:
Or build the image from **source code**:
```bash
git clone https://github.com/vllm-project/vllm-omni.git
cd vllm-omni
# A2
# docker build -t vllm-omni-dev-image:latest -f ./docker/Dockerfile.npu .
# A3
docker build -t vllm-omni-dev-image:latest -f ./docker/Dockerfile.npu.a3 .
```
All hardware variants use `docker/Dockerfile.npu`. Choose the device suffix for your hardware:
=== "A2"
```bash
docker build -t vllm-omni-dev-image:latest -f docker/Dockerfile.npu .
```
=== "A3"
```bash
docker build -t vllm-omni-dev-image:latest -f docker/Dockerfile.npu \
--build-arg VLLM_ASCEND_DEVICE_SUFFIX=-a3 .
```
=== "A5"
```bash
docker build -t vllm-omni-dev-image:latest -f docker/Dockerfile.npu \
--build-arg VLLM_ASCEND_DEVICE_SUFFIX=-a5 .
```
=== "310P (Experimental)"
```bash
docker build -t vllm-omni-dev-image:latest -f docker/Dockerfile.npu \
--build-arg VLLM_ASCEND_DEVICE_SUFFIX=-310p .
```
# --8<-- [end:pre-built-images]
+2
View File
@@ -283,6 +283,8 @@ markers = [
"S5000: [hardware-resource] [musa] Tests that require S5000 GPU (Moore Threads/MUSA)",
"A2: [hardware-resource] [npu] Tests that require A2 NPU",
"A3: [hardware-resource] [npu] Tests that require A3 NPU",
"A5: [hardware-resource] [npu] Tests that require A5 NPU",
"310P: [hardware-resource] [npu] Tests that require 310P NPU",
# Tag with [hardware-cards] for tests.helpers.mark.get_supported_card_counts().
"cards_1: [hardware-cards] Tests that require 1 accelerator card",
"cards_2: [hardware-cards] Tests that require 2 accelerator cards",
+12 -4
View File
@@ -5,7 +5,7 @@ import pytest
import torch
import torch.nn.functional as F
from tests.helpers.mark import hardware_test
from tests.helpers.mark import hardware_marks
from vllm_omni.diffusion.layers.activation import SiluAndMul
pytestmark = [pytest.mark.core_model, pytest.mark.diffusion]
@@ -19,9 +19,17 @@ def test_silu_and_mul_native_matches_packed_reference() -> None:
torch.testing.assert_close(SiluAndMul().forward_native(packed), F.silu(gate) * up)
@hardware_test(res={"npu": "A3"}, num_cards=1)
def test_silu_and_mul_npu_matches_packed_reference() -> None:
packed = torch.randn(257, 256, device="npu", dtype=torch.bfloat16)
@pytest.mark.parametrize(
"dtype",
[
pytest.param(torch.bfloat16, marks=hardware_marks(res={"npu": "A2"}, num_cards=1), id="A2-bf16"),
pytest.param(torch.bfloat16, marks=hardware_marks(res={"npu": "A3"}, num_cards=1), id="A3-bf16"),
pytest.param(torch.bfloat16, marks=hardware_marks(res={"npu": "A5"}, num_cards=1), id="A5-bf16"),
pytest.param(torch.float16, marks=hardware_marks(res={"npu": "310P"}, num_cards=1), id="310P-fp16"),
],
)
def test_silu_and_mul_npu_matches_packed_reference(dtype: torch.dtype) -> None:
packed = torch.randn(257, 256, device="npu", dtype=dtype)
gate, up = packed.chunk(2, dim=-1)
torch.testing.assert_close(