[CI] Add 310p e2e test back (#5797)

This PR add 310 e2e test back to ensure the related PR will be tested on
310.
1. for light e2e, we'll run 310p test if the changed files are located
in `vllm_ascend/_310p`
2. for full e2e, we'll always run 310p test
3. for main2main test, we'll stop run 310p test

- vLLM version: v0.13.0
- vLLM main:
2f4e6548ef

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

.github/workflows/_e2e_test.yaml

@@ -15,6 +15,9 @@ on:
       type:
         required: true
         type: string
+      contains_310:
+        required: true
+        type: boolean
 
 jobs:
   e2e:
@@ -328,3 +331,119 @@ jobs:
 
           # spec_decode
           pytest -sv --durations=0 tests/e2e/multicard/4-cards/spec_decode/test_mtp_qwen3_next.py
+
+  e2e_310p:
+    name: 310p singlecard
+    runs-on: linux-aarch64-310p-1
+    if: ${{ inputs.contains_310 }}
+    container:
+      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-310p-ubuntu22.04-py3.11
+      env:
+        VLLM_LOGGING_LEVEL: ERROR
+        VLLM_USE_MODELSCOPE: True
+        TRANSFORMERS_OFFLINE: 1
+    steps:
+      - name: Check npu and CANN info
+        run: |
+          npu-smi info
+          cat /usr/local/Ascend/ascend-toolkit/latest/"$(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
+        env:
+          PYTORCH_NPU_ALLOC_CONF: max_split_size_mb:256
+          VLLM_WORKER_MULTIPROC_METHOD: spawn
+        run: |
+          pytest -sv --durations=0 tests/e2e/310p/test_offline_inference_310p.py
+
+  e2e_310p-4cards:
+    name: 310p multicards 4cards
+    runs-on: linux-aarch64-310p-4
+    if: ${{ inputs.contains_310 }}
+    container:
+      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-310p-ubuntu22.04-py3.11
+      env:
+        VLLM_LOGGING_LEVEL: ERROR
+        VLLM_USE_MODELSCOPE: True
+        TRANSFORMERS_OFFLINE: 1
+    steps:
+      - name: Check npu and CANN info
+        run: |
+          npu-smi info
+          cat /usr/local/Ascend/ascend-toolkit/latest/"$(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
+        env:
+          PYTORCH_NPU_ALLOC_CONF: max_split_size_mb:256
+          VLLM_WORKER_MULTIPROC_METHOD: spawn
+        run: |
+          pytest -sv --durations=0 tests/e2e/310p/test_offline_inference_parallel_310p.py