Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion .github/workflows/_accuracy_test.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@ jobs:
runs-on: ${{ inputs.runner }}
name: ${{ inputs.model_name }} accuracy
container:
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-910b-ubuntu22.04-py3.11
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11
env:
VLLM_USE_MODELSCOPE: True
# 1. If version specified (work_dispatch), do specified branch accuracy test
Expand Down
2 changes: 1 addition & 1 deletion .github/workflows/accuracy_test.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -68,5 +68,5 @@ jobs:
with:
vllm: v0.11.0
runner: linux-aarch64-${{ matrix.runner }}
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-910b-ubuntu22.04-py3.11
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11
model_name: ${{ matrix.model_name }}
2 changes: 1 addition & 1 deletion .github/workflows/multi_node_test.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@ jobs:
# This is a runner with no NPU for k8s controller
runs-on: linux-aarch64-a3-0
container:
image: m.daocloud.io/quay.io/ascend/cann:8.3.rc1-a3-ubuntu22.04-py3.11
image: m.daocloud.io/quay.io/ascend/cann:8.3.rc2-a3-ubuntu22.04-py3.11
env:
KUBECONFIG: /tmp/kubeconfig
KUBECTL: /root/.cache/.kube/kubectl
Expand Down
2 changes: 1 addition & 1 deletion .github/workflows/nightly_benchmarks.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -56,7 +56,7 @@ jobs:
vllm_use_v1: 1
max-parallel: 1
container:
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-910b-ubuntu22.04-py3.11
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11
volumes:
- /usr/local/dcmi:/usr/local/dcmi
- /usr/local/bin/npu-smi:/usr/local/bin/npu-smi
Expand Down
4 changes: 2 additions & 2 deletions .github/workflows/vllm_ascend_dist.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -47,7 +47,7 @@ jobs:
name: vLLM Ascend test
runs-on: ${{ matrix.os }}
container:
image: m.daocloud.io/quay.io/ascend/cann:8.3.rc1-a3-ubuntu22.04-py3.11
image: m.daocloud.io/quay.io/ascend/cann:8.3.rc2-a3-ubuntu22.04-py3.11
env:
DEBIAN_FRONTEND: noninteractive
steps:
Expand Down Expand Up @@ -97,4 +97,4 @@ jobs:
VLLM_USE_MODELSCOPE: True
run: |
# TODO: enable more tests
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_multistream_moe
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_multistream_moe
2 changes: 1 addition & 1 deletion .github/workflows/vllm_ascend_test.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -145,5 +145,5 @@ jobs:
with:
vllm: ${{ matrix.vllm_version }}
runner: linux-aarch64-a2
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-910b-ubuntu22.04-py3.11
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11
type: light
2 changes: 1 addition & 1 deletion .github/workflows/vllm_ascend_test_310p.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -58,7 +58,7 @@ jobs:
runs-on: ${{ matrix.os }}
container:
# TODO(yikun): Remove m.daocloud.io prefix when infra proxy ready
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-310p-ubuntu22.04-py3.11
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-310p-ubuntu22.04-py3.11
env:
VLLM_LOGGING_LEVEL: ERROR
VLLM_USE_MODELSCOPE: True
Expand Down
2 changes: 1 addition & 1 deletion .github/workflows/vllm_ascend_test_full.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -76,5 +76,5 @@ jobs:
with:
vllm: ${{ matrix.vllm_version }}
runner: linux-aarch64-a2
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-910b-ubuntu22.04-py3.11
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11
type: full
2 changes: 1 addition & 1 deletion .github/workflows/vllm_ascend_test_full_vllm_main.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -41,5 +41,5 @@ jobs:
with:
vllm: main
runner: linux-aarch64-a2
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-910b-ubuntu22.04-py3.11
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11
type: full
2 changes: 1 addition & 1 deletion .github/workflows/vllm_ascend_test_models.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -79,7 +79,7 @@ jobs:
with:
vllm: v0.11.0
runner: linux-aarch64-${{ matrix.runner }}
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-910b-ubuntu22.04-py3.11
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11
model_name: ${{ matrix.model_name }}
upload: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.vllm-ascend-version == 'latest' }}

Expand Down
4 changes: 2 additions & 2 deletions .github/workflows/vllm_ascend_test_pd.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -49,7 +49,7 @@ jobs:
runs-on: linux-arm64-npu-static-8

container:
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-910b-ubuntu22.04-py3.11
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11
volumes:
- /usr/local/dcmi:/usr/local/dcmi
- /usr/local/bin/npu-smi:/usr/local/bin/npu-smi
Expand Down Expand Up @@ -109,4 +109,4 @@ jobs:
- name: Run vllm-project/vllm-ascend PD Disaggregation edge test
run: |
git config --global --add safe.directory/__w/vllm-ascend/vllm-ascend
bash tests/e2e/pd_disaggreate/run_edge_case_test.sh
bash tests/e2e/pd_disaggreate/run_edge_case_test.sh
2 changes: 1 addition & 1 deletion Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@
# This file is a part of the vllm-ascend project.
#

FROM quay.io/ascend/cann:8.3.rc1-910b-ubuntu22.04-py3.11
FROM quay.io/ascend/cann:8.3.rc2-910b-ubuntu22.04-py3.11

ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
ARG COMPILE_CUSTOM_KERNELS=1
Expand Down
2 changes: 1 addition & 1 deletion Dockerfile.310p
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@
# This file is a part of the vllm-ascend project.
#

FROM quay.io/ascend/cann:8.3.rc1-310p-ubuntu22.04-py3.11
FROM quay.io/ascend/cann:8.3.rc2-310p-ubuntu22.04-py3.11

ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
ARG COMPILE_CUSTOM_KERNELS=1
Expand Down
2 changes: 1 addition & 1 deletion Dockerfile.310p.openEuler
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@
# This file is a part of the vllm-ascend project.
#

FROM quay.io/ascend/cann:8.3.rc1-310p-openeuler24.03-py3.11
FROM quay.io/ascend/cann:8.3.rc2-310p-openeuler24.03-py3.11

ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
ARG COMPILE_CUSTOM_KERNELS=1
Expand Down
4 changes: 2 additions & 2 deletions Dockerfile.a3
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@
# This file is a part of the vllm-ascend project.
#

FROM quay.io/ascend/cann:8.3.rc1-a3-ubuntu22.04-py3.11
FROM quay.io/ascend/cann:8.3.rc2-a3-ubuntu22.04-py3.11

ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
ARG COMPILE_CUSTOM_KERNELS=1
Expand Down Expand Up @@ -57,4 +57,4 @@ RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi
RUN python3 -m pip install modelscope 'ray>=2.47.1' 'protobuf>3.20.0' && \
python3 -m pip cache purge

CMD ["/bin/bash"]
CMD ["/bin/bash"]
4 changes: 2 additions & 2 deletions Dockerfile.a3.openEuler
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@
# This file is a part of the vllm-ascend project.
#

FROM quay.io/ascend/cann:8.3.rc1-a3-openeuler24.03-py3.11
FROM quay.io/ascend/cann:8.3.rc2-a3-openeuler24.03-py3.11

ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
ARG COMPILE_CUSTOM_KERNELS=1
Expand Down Expand Up @@ -55,4 +55,4 @@ RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi
RUN python3 -m pip install modelscope 'ray>=2.47.1' 'protobuf>3.20.0' && \
python3 -m pip cache purge

CMD ["/bin/bash"]
CMD ["/bin/bash"]
2 changes: 1 addition & 1 deletion Dockerfile.openEuler
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@
# This file is a part of the vllm-ascend project.
#

FROM quay.io/ascend/cann:8.3.rc1-910b-openeuler24.03-py3.11
FROM quay.io/ascend/cann:8.3.rc2-910b-openeuler24.03-py3.11

ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
ARG COMPILE_CUSTOM_KERNELS=1
Expand Down
2 changes: 1 addition & 1 deletion docs/source/conf.py
Original file line number Diff line number Diff line change
Expand Up @@ -75,7 +75,7 @@
'pip_vllm_ascend_version': "0.11.0rc0",
'pip_vllm_version': "0.11.0",
# CANN image tag
'cann_image_tag': "8.3.rc1-910b-ubuntu22.04-py3.11",
'cann_image_tag': "8.3.rc2-910b-ubuntu22.04-py3.11",
# vllm version in ci
'ci_vllm_version': 'v0.11.0rc3',
}
Expand Down
20 changes: 10 additions & 10 deletions docs/source/installation.md
Original file line number Diff line number Diff line change
Expand Up @@ -79,19 +79,19 @@ source vllm-ascend-env/bin/activate
pip3 install -i https://pypi.tuna.tsinghua.edu.cn/simple attrs 'numpy<2.0.0' decorator sympy cffi pyyaml pathlib2 psutil protobuf scipy requests absl-py wheel typing_extensions

# Download and install the CANN package.
wget --header="Referer: https://www.hiascend.com/" https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/CANN/CANN%208.3.RC1/Ascend-cann-toolkit_8.3.RC1_linux-"$(uname -i)".run
chmod +x ./Ascend-cann-toolkit_8.3.RC1_linux-"$(uname -i)".run
./Ascend-cann-toolkit_8.3.RC1_linux-"$(uname -i)".run --full
# https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/Milan-ASL/Milan-ASL%20V100R001C22B800TP052/Ascend-cann-kernels-910b_8.3.rc1_linux-aarch64.run
wget --header="Referer: https://www.hiascend.com/" https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/CANN/CANN%208.3.RC2/Ascend-cann-toolkit_8.3.RC2_linux-"$(uname -i)".run
chmod +x ./Ascend-cann-toolkit_8.3.RC2_linux-"$(uname -i)".run
./Ascend-cann-toolkit_8.3.RC2_linux-"$(uname -i)".run --full
# https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/Milan-ASL/Milan-ASL%20V100R001C22B800TP052/Ascend-cann-kernels-910b_8.3.rc2_linux-aarch64.run

source /usr/local/Ascend/ascend-toolkit/set_env.sh
wget --header="Referer: https://www.hiascend.com/" https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/CANN/CANN%208.3.RC1/Ascend-cann-kernels-910b_8.3.RC1_linux-"$(uname -i)".run
chmod +x ./Ascend-cann-kernels-910b_8.3.RC1_linux-"$(uname -i)".run
./Ascend-cann-kernels-910b_8.3.RC1_linux-"$(uname -i)".run --install
wget --header="Referer: https://www.hiascend.com/" https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/CANN/CANN%208.3.RC2/Ascend-cann-kernels-910b_8.3.RC2_linux-"$(uname -i)".run
chmod +x ./Ascend-cann-kernels-910b_8.3.RC2_linux-"$(uname -i)".run
./Ascend-cann-kernels-910b_8.3.RC2_linux-"$(uname -i)".run --install

wget --header="Referer: https://www.hiascend.com/" https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/CANN/CANN%208.3.RC1/Ascend-cann-nnal_8.3.RC1_linux-"$(uname -i)".run
chmod +x ./Ascend-cann-nnal_8.3.RC1_linux-"$(uname -i)".run
./Ascend-cann-nnal_8.3.RC1_linux-"$(uname -i)".run --install
wget --header="Referer: https://www.hiascend.com/" https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/CANN/CANN%208.3.RC2/Ascend-cann-nnal_8.3.RC2_linux-"$(uname -i)".run
chmod +x ./Ascend-cann-nnal_8.3.RC2_linux-"$(uname -i)".run
./Ascend-cann-nnal_8.3.RC2_linux-"$(uname -i)".run --install
Comment on lines +82 to +94
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

high

The commands for downloading and installing the CANN packages are repeated multiple times, which makes the script hard to read and error-prone for future version updates. I suggest using variables for the version and package names to improve maintainability and readability.

Suggested change
wget --header="Referer: https://www.hiascend.com/" https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/CANN/CANN%208.3.RC2/Ascend-cann-toolkit_8.3.RC2_linux-"$(uname -i)".run
chmod +x ./Ascend-cann-toolkit_8.3.RC2_linux-"$(uname -i)".run
./Ascend-cann-toolkit_8.3.RC2_linux-"$(uname -i)".run --full
# https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/Milan-ASL/Milan-ASL%20V100R001C22B800TP052/Ascend-cann-kernels-910b_8.3.rc2_linux-aarch64.run
source /usr/local/Ascend/ascend-toolkit/set_env.sh
wget --header="Referer: https://www.hiascend.com/" https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/CANN/CANN%208.3.RC1/Ascend-cann-kernels-910b_8.3.RC1_linux-"$(uname -i)".run
chmod +x ./Ascend-cann-kernels-910b_8.3.RC1_linux-"$(uname -i)".run
./Ascend-cann-kernels-910b_8.3.RC1_linux-"$(uname -i)".run --install
wget --header="Referer: https://www.hiascend.com/" https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/CANN/CANN%208.3.RC2/Ascend-cann-kernels-910b_8.3.RC2_linux-"$(uname -i)".run
chmod +x ./Ascend-cann-kernels-910b_8.3.RC2_linux-"$(uname -i)".run
./Ascend-cann-kernels-910b_8.3.RC2_linux-"$(uname -i)".run --install
wget --header="Referer: https://www.hiascend.com/" https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/CANN/CANN%208.3.RC1/Ascend-cann-nnal_8.3.RC1_linux-"$(uname -i)".run
chmod +x ./Ascend-cann-nnal_8.3.RC1_linux-"$(uname -i)".run
./Ascend-cann-nnal_8.3.RC1_linux-"$(uname -i)".run --install
wget --header="Referer: https://www.hiascend.com/" https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/CANN/CANN%208.3.RC2/Ascend-cann-nnal_8.3.RC2_linux-"$(uname -i)".run
chmod +x ./Ascend-cann-nnal_8.3.RC2_linux-"$(uname -i)".run
./Ascend-cann-nnal_8.3.RC2_linux-"$(uname -i)".run --install
CANN_VERSION="8.3.RC2"
ARCH="$(uname -i)"
TOOLKIT_PKG="Ascend-cann-toolkit_${CANN_VERSION}_linux-${ARCH}.run"
KERNELS_PKG="Ascend-cann-kernels-910b_${CANN_VERSION}_linux-${ARCH}.run"
NNAL_PKG="Ascend-cann-nnal_${CANN_VERSION}_linux-${ARCH}.run"
wget --header="Referer: https://www.hiascend.com/" "https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/CANN/CANN%20${CANN_VERSION}/${TOOLKIT_PKG}"
chmod +x ./${TOOLKIT_PKG}
./${TOOLKIT_PKG} --full
# https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/Milan-ASL/Milan-ASL%20V100R001C22B800TP052/Ascend-cann-kernels-910b_8.3.rc2_linux-aarch64.run
source /usr/local/Ascend/ascend-toolkit/set_env.sh
wget --header="Referer: https://www.hiascend.com/" "https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/CANN/CANN%20${CANN_VERSION}/${KERNELS_PKG}"
chmod +x ./${KERNELS_PKG}
./${KERNELS_PKG} --install
wget --header="Referer: https://www.hiascend.com/" "https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/CANN/CANN%20${CANN_VERSION}/${NNAL_PKG}"
chmod +x ./${NNAL_PKG}
./${NNAL_PKG} --install


source /usr/local/Ascend/nnal/atb/set_env.sh
```
Expand Down
4 changes: 2 additions & 2 deletions docs/source/tutorials/multi_npu_qwen3_next.md
Original file line number Diff line number Diff line change
Expand Up @@ -51,7 +51,7 @@ Install the Ascend BiSheng toolkit:
wget https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/Ascend-BiSheng-toolkit_aarch64.run
chmod a+x Ascend-BiSheng-toolkit_aarch64.run
./Ascend-BiSheng-toolkit_aarch64.run --install
source /usr/local/Ascend/8.3.RC1/bisheng_toolkit/set_env.sh
source /usr/local/Ascend/8.3.RC2/bisheng_toolkit/set_env.sh
```

Install Triton Ascend:
Expand All @@ -75,7 +75,7 @@ Coming soon ...
Please make sure you have already executed the command:

```bash
source /usr/local/Ascend/8.3.RC1/bisheng_toolkit/set_env.sh
source /usr/local/Ascend/8.3.RC2/bisheng_toolkit/set_env.sh
```

:::::{tab-set}
Expand Down
4 changes: 2 additions & 2 deletions tests/e2e/nightly/multi_node/scripts/lws.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@ spec:
spec:
containers:
- name: vllm-leader
image: m.daocloud.io/quay.io/ascend/cann:8.3.rc1-a3-ubuntu22.04-py3.11
image: m.daocloud.io/quay.io/ascend/cann:8.3.rc2-a3-ubuntu22.04-py3.11
env:
- name: WORKSPACE
value: "/root/workspace"
Expand Down Expand Up @@ -70,7 +70,7 @@ spec:
spec:
containers:
- name: vllm-worker
image: m.daocloud.io/quay.io/ascend/cann:8.3.rc1-a3-ubuntu22.04-py3.11
image: m.daocloud.io/quay.io/ascend/cann:8.3.rc2-a3-ubuntu22.04-py3.11
env:
- name: WORKSPACE
value: "/root/workspace"
Expand Down
2 changes: 1 addition & 1 deletion tests/e2e/vllm_interface/vllm_test.cfg
Original file line number Diff line number Diff line change
@@ -1,2 +1,2 @@
# Base docker image used to build the vllm-ascend e2e test image, which is built in the vLLM repository
BASE_IMAGE_NAME="quay.io/ascend/cann:8.3.rc1-910b-ubuntu22.04-py3.11"
BASE_IMAGE_NAME="quay.io/ascend/cann:8.3.rc2-910b-ubuntu22.04-py3.11"
Loading