xc-llm-ascend/.github/workflows/_e2e_test.yaml

name: 'e2e test'

on:
  workflow_call:
    inputs:
      vllm:
        required: true
        type: string
      runner:
        required: true
        type: string
      image:
        required: true
        type: string
      type:
        required: true
        type: string

jobs:
  e2e:
    name: singlecard
    runs-on: ${{ inputs.runner }}-1
    container:
      image: ${{ inputs.image }}
      env:
        VLLM_LOGGING_LEVEL: ERROR
        VLLM_USE_MODELSCOPE: True
        TRANSFORMERS_OFFLINE: 1
    steps:
      - name: Check npu and CANN info
        run: |
          npu-smi info
          cat /usr/local/Ascend/ascend-toolkit/latest/"$(uname -i)"-linux/ascend_toolkit_install.info

      - name: Config mirrors
        run: |
          sed -Ei 's@(ports|archive).ubuntu.com@cache-service.nginx-pypi-cache.svc.cluster.local:8081@g' /etc/apt/sources.list
          pip config set global.index-url http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple
          pip config set global.trusted-host cache-service.nginx-pypi-cache.svc.cluster.local
          apt-get update -y
          apt install git -y

      - name: Checkout vllm-project/vllm-ascend repo
        uses: actions/checkout@v6

      - 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@v6
        with:
          repository: vllm-project/vllm
          ref: ${{ inputs.vllm }}
          path: ./vllm-empty
          fetch-depth: 1

      - 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
        env:
          PIP_EXTRA_INDEX_URL: https://mirrors.huaweicloud.com/ascend/repos/pypi
        run: |
          pip install -r requirements-dev.txt
          pip install -v -e .

      - name: Run vllm-project/vllm-ascend test (non triton)
        env:
          VLLM_WORKER_MULTIPROC_METHOD: spawn
          PYTORCH_NPU_ALLOC_CONF: max_split_size_mb:256
        if: ${{ inputs.type == 'full' }}
        run: |
          pytest -sv --durations=0 tests/e2e/singlecard/test_aclgraph_mem.py
          pytest -sv --durations=0 tests/e2e/singlecard/test_camem.py

      - name: Install Ascend toolkit & triton_ascend
        shell: bash -l {0}
        run: |
          . /usr/local/Ascend/ascend-toolkit/8.3.RC2/bisheng_toolkit/set_env.sh
          python3 -m pip install "https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/triton_ascend-3.2.0.dev2025110717-cp311-cp311-manylinux_2_27_aarch64.whl"

      - name: Run vllm-project/vllm-ascend test
        env:
          PYTORCH_NPU_ALLOC_CONF: max_split_size_mb:256
          VLLM_WORKER_MULTIPROC_METHOD: spawn
        if: ${{ inputs.type == 'light' }}
        run: |
          # pytest -sv --durations=0 tests/e2e/singlecard/test_aclgraph_accuracy.py
          # pytest -sv --durations=0 tests/e2e/singlecard/test_quantization.py
          pytest -sv --durations=0 tests/e2e/singlecard/test_vlm.py::test_multimodal_vl
          pytest -sv --durations=0 tests/e2e/singlecard/pooling/test_classification.py::test_qwen_pooling_classify_correctness

      - name: Run e2e test
        env:
          VLLM_WORKER_MULTIPROC_METHOD: spawn
          PYTORCH_NPU_ALLOC_CONF: max_split_size_mb:256
        if: ${{ inputs.type == 'full' }}
        run: |
          # We found that if running aclgraph tests in batch, it will cause AclmdlRICaptureBegin error. So we run
          # the test separately.

          pytest -sv --durations=0 tests/e2e/nightly/ops/triton/
          pytest -sv --durations=0 tests/e2e/singlecard/test_completion_with_prompt_embeds.py
          pytest -sv --durations=0 tests/e2e/singlecard/test_aclgraph_accuracy.py
          pytest -sv --durations=0 tests/e2e/singlecard/test_async_scheduling.py
          pytest -sv --durations=0 tests/e2e/singlecard/test_guided_decoding.py
          # torch 2.8 doesn't work with lora, fix me
          #pytest -sv --durations=0 tests/e2e/singlecard/test_ilama_lora.py
          pytest -sv --durations=0 tests/e2e/singlecard/test_profile_execute_duration.py
          pytest -sv --durations=0 tests/e2e/singlecard/test_quantization.py
          pytest -sv --durations=0 tests/e2e/singlecard/test_sampler.py
          pytest -sv --durations=0 tests/e2e/singlecard/test_vlm.py
          pytest -sv --durations=0 tests/e2e/singlecard/test_xlite.py
          pytest -sv --durations=0 tests/e2e/singlecard/test_models.py
          pytest -sv --durations=0 tests/e2e/singlecard/pooling/
          pytest -sv --durations=0 tests/e2e/singlecard/compile/test_norm_quant_fusion.py
          pytest -sv --durations=0 tests/e2e/singlecard/test_multistream_overlap_shared_expert.py

          # ------------------------------------ v1 spec decode test ------------------------------------ #
          pytest -sv --durations=0 tests/e2e/singlecard/spec_decode_v1/test_v1_mtp_correctness.py
          pytest -sv --durations=0 tests/e2e/singlecard/spec_decode_v1/test_v1_spec_decode.py

  e2e-2-cards:
    name: multicard-2
    runs-on: linux-aarch64-a3-2
    container:
      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-a3-ubuntu22.04-py3.11
      env:
        VLLM_LOGGING_LEVEL: ERROR
        VLLM_USE_MODELSCOPE: True
        HCCL_BUFFSIZE: 1024
        TRANSFORMERS_OFFLINE: 1
    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: |
          # Fix me: use nginx cache rather than the pypi
          # sed -Ei 's@(ports|archive).ubuntu.com@cache-service.nginx-pypi-cache.svc.cluster.local:8081@g' /etc/apt/sources.list
          # pip config set global.index-url http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple
          # pip config set global.trusted-host cache-service.nginx-pypi-cache.svc.cluster.local
          pip config set global.index-url https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple
          apt-get update -y
          apt install git -y

      - name: Checkout vllm-project/vllm-ascend repo
        uses: actions/checkout@v6

      - 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@v6
        with:
          repository: vllm-project/vllm
          ref: ${{ inputs.vllm }}
          path: ./vllm-empty
          fetch-depth: 1

      - 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
        env:
          PIP_EXTRA_INDEX_URL: https://mirrors.huaweicloud.com/ascend/repos/pypi
        run: |
          pip install -r requirements-dev.txt
          pip install -v -e .

      - name: Run vllm-project/vllm-ascend test (non triton)
        if: ${{ inputs.type == 'full' }}
        env:
          VLLM_WORKER_MULTIPROC_METHOD: spawn
        run: |
          pytest -sv --durations=0 tests/e2e/multicard/test_aclgraph_capture_replay.py

      - name: Install Ascend toolkit & triton_ascend
        shell: bash -l {0}
        run: |
          . /usr/local/Ascend/ascend-toolkit/8.3.RC2/bisheng_toolkit/set_env.sh
          python3 -m pip install "https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/triton_ascend-3.2.0.dev2025110717-cp311-cp311-manylinux_2_27_aarch64.whl"

      - name: Run vllm-project/vllm-ascend test (light)
        env:
          VLLM_WORKER_MULTIPROC_METHOD: spawn
        if: ${{ inputs.type == 'light' }}
        run: |
          pytest -sv --durations=0 tests/e2e/multicard/test_qwen3_moe.py::test_qwen3_moe_distributed_mp_tp2_ep

      - name: Run vllm-project/vllm-ascend test (full)
        env:
          VLLM_WORKER_MULTIPROC_METHOD: spawn
        if: ${{ inputs.type == 'full' }}
        run: |
          pytest -sv --durations=0 tests/e2e/multicard/test_quantization.py
          pytest -sv --durations=0 tests/e2e/multicard/test_full_graph_mode.py
          pytest -sv --durations=0 tests/e2e/multicard/test_data_parallel.py
          pytest -sv --durations=0 tests/e2e/multicard/test_expert_parallel.py
          pytest -sv --durations=0 tests/e2e/multicard/test_external_launcher.py
          pytest -sv --durations=0 tests/e2e/multicard/test_single_request_aclgraph.py
          # torch 2.8 doesn't work with lora, fix me
          #pytest -sv --durations=0 tests/e2e/multicard/test_ilama_lora_tp2.py

          # To avoid oom, we need to run the test in a single process.
          pytest -sv --durations=0 tests/e2e/multicard/test_offline_inference_distributed.py::test_deepseek_multistream_moe_tp2
          pytest -sv --durations=0 tests/e2e/multicard/test_offline_inference_distributed.py::test_qwen3_w4a8_dynamic_tp2
          pytest -sv --durations=0 tests/e2e/multicard/test_offline_inference_distributed.py::test_qwen3_moe_sp_tp2
          pytest -sv --durations=0 tests/e2e/multicard/test_offline_inference_distributed.py::test_qwen3_moe_fc2_tp2
          pytest -sv --durations=0 tests/e2e/multicard/test_offline_inference_distributed.py::test_qwen3_dense_fc1_tp2
          pytest -sv --durations=0 tests/e2e/multicard/test_offline_inference_distributed.py::test_qwen3_dense_prefetch_mlp_weight_tp2
          pytest -sv --durations=0 tests/e2e/multicard/test_offline_inference_distributed.py::test_deepseek_w4a8_accuracy_tp2
          pytest -sv --durations=0 tests/e2e/multicard/test_offline_inference_distributed.py::test_deepseek_v2_lite_fc1_tp2

          pytest -sv --durations=0 tests/e2e/multicard/test_prefix_caching.py
          pytest -sv --durations=0 tests/e2e/multicard/test_pipeline_parallel.py
          pytest -sv --durations=0 tests/e2e/multicard/test_qwen3_moe.py
          pytest -sv --durations=0 tests/e2e/multicard/test_offline_weight_load.py

  e2e-4-cards:
    name: multicard-4
    needs: [e2e, e2e-2-cards]
    if: ${{ needs.e2e.result == 'success' && needs.e2e-2-cards.result == 'success' && inputs.type == 'full' }}
    runs-on: linux-aarch64-a3-4
    container:
      image: m.daocloud.io/quay.io/ascend/cann:8.3.rc2-a3-ubuntu22.04-py3.11
      env:
        VLLM_LOGGING_LEVEL: ERROR
        VLLM_USE_MODELSCOPE: True
        TRANSFORMERS_OFFLINE: 1
    steps:
      - name: Check npu and CANN info
        run: |
          npu-smi info
          cat /usr/local/Ascend/ascend-toolkit/latest/"$(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 wget curl -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@v6
        with:
          path: ./vllm-ascend

      - 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@v6
        with:
          repository: vllm-project/vllm
          ref: ${{ inputs.vllm }}
          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
        working-directory: ./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: Install Ascend toolkit & triton_ascend
        shell: bash -l {0}
        run: |
          . /usr/local/Ascend/ascend-toolkit/8.3.RC2/bisheng_toolkit/set_env.sh
          python3 -m pip install "https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/triton_ascend-3.2.0.dev2025110717-cp311-cp311-manylinux_2_27_aarch64.whl"

      - name: Run vllm-project/vllm-ascend test for V1 Engine
        working-directory: ./vllm-ascend
        env:
          VLLM_WORKER_MULTIPROC_METHOD: spawn
        run: |
          pytest -sv --durations=0 tests/e2e/multicard/test_offline_inference_distributed.py::test_deepseek_multistream_moe_tp2
          pytest -sv --durations=0 tests/e2e/multicard/test_offline_inference_distributed.py::test_kimi_k2_thinking_w4a16_tp4
          pytest -sv --durations=0 tests/e2e/multicard/test_data_parallel_tp2.py
          pytest -sv --durations=0 tests/e2e/multicard/long_sequence/test_basic.py
          pytest -sv --durations=0 tests/e2e/multicard/long_sequence/test_accuracy.py
          pytest -sv --durations=0 tests/e2e/multicard/long_sequence/test_mtp.py
          pytest -sv --durations=0 tests/e2e/multicard/test_qwen3_next.py