[Perf] Add new npu_fused_infer_attention_score op to improve perfomance in splitfuse cases and resolve long-seq mask problems #768
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # | |
| # Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved. | |
| # | |
| # Licensed under the Apache License, Version 2.0 (the "License"); | |
| # you may not use this file except in compliance with the License. | |
| # You may obtain a copy of the License at | |
| # | |
| # http://www.apache.org/licenses/LICENSE-2.0 | |
| # | |
| # Unless required by applicable law or agreed to in writing, software | |
| # distributed under the License is distributed on an "AS IS" BASIS, | |
| # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | |
| # See the License for the specific language governing permissions and | |
| # limitations under the License. | |
| # This file is a part of the vllm-ascend project. | |
| # | |
| name: 'e2e test / a3-test' | |
| on: | |
| workflow_call: | |
| pull_request: | |
| types: [ labeled ] | |
| # Bash shells do not use ~/.profile or ~/.bashrc so these shells need to be explicitly | |
| # declared as "shell: bash -el {0}" on steps that need to be properly activated. | |
| # It's used to activate ascend-toolkit environment variables. | |
| defaults: | |
| run: | |
| shell: bash -el {0} | |
| # only cancel in-progress runs of the same workflow | |
| # and ignore the lint / 8 cards test type | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.ref }} | |
| cancel-in-progress: true | |
| jobs: | |
| e2e: | |
| # only trigger e2e test after lint passed and the change is e2e related with pull request. | |
| if: ${{ contains(github.event.pull_request.labels.*.name, 'dist-test') && contains(github.event.pull_request.labels.*.name, 'ready-for-test') || github.event_name == 'workflow_dispatch' }} | |
| strategy: | |
| matrix: | |
| os: [linux-aarch64-a3-8] | |
| vllm_version: [v0.10.2] | |
| name: vLLM Ascend test | |
| runs-on: ${{ matrix.os }} | |
| container: | |
| image: m.daocloud.io/quay.io/ascend/cann:8.2.rc1-a3-ubuntu22.04-py3.11 | |
| env: | |
| DEBIAN_FRONTEND: noninteractive | |
| steps: | |
| - name: Check npu and CANN info | |
| run: | | |
| npu-smi info | |
| cat /usr/local/Ascend/ascend-toolkit/latest/"$(uname -i)"-linux/ascend_toolkit_install.info | |
| - name: Config mirrors | |
| run: | | |
| sed -i 's|ports.ubuntu.com|mirrors.tuna.tsinghua.edu.cn|g' /etc/apt/sources.list | |
| pip config set global.index-url https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple | |
| apt-get update -y | |
| apt install git -y | |
| git config --global url."https://gh-proxy.test.osinfra.cn/https://github.com/".insteadOf https://github.com/ | |
| - name: Checkout vllm-project/vllm-ascend repo | |
| uses: actions/checkout@v4 | |
| - name: Install system dependencies | |
| run: | | |
| apt-get -y install `cat packages.txt` | |
| apt-get -y install gcc g++ cmake libnuma-dev | |
| - name: Checkout vllm-project/vllm repo | |
| uses: actions/checkout@v4 | |
| with: | |
| repository: vllm-project/vllm | |
| ref: ${{ matrix.vllm_version }} | |
| path: ./vllm-empty | |
| - name: Install vllm-project/vllm from source | |
| working-directory: ./vllm-empty | |
| run: | | |
| VLLM_TARGET_DEVICE=empty pip install -e . | |
| - name: Install vllm-project/vllm-ascend | |
| run: | | |
| export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi | |
| export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/x86_64-linux/devlib | |
| pip install -r requirements-dev.txt | |
| pip install -v -e . | |
| - name: Run vllm-project/vllm-ascend test for V1 Engine | |
| env: | |
| VLLM_WORKER_MULTIPROC_METHOD: spawn | |
| 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 |