verl/.github/workflows/e2e_ascend.yml at main · ModelTC/verl · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
name: e2e_ascend

on:
  # Trigger the workflow on push or pull request,
  # but only for the main branch
  push:
    branches:
      - main
      - v0.2.x
    paths:
      - "**/*.py"
      - .github/workflows/e2e_ascend.yml
  pull_request:
    branches:
      - main
      - v0.2.x
    paths:
      - "**/*.py"
      - .github/workflows/e2e_ascend.yml

permissions:
  contents: read

jobs:
  test:
    name: verl Ascend test (self-host)
    runs-on: [self-hosted, npu-0]
    timeout-minutes: 5 # Increase this timeout value as needed
    env:
      HF_HUB_ENABLE_HF_TRANSFER: 1
    container:
      image: quay.io/ascend/cann:8.0.0-910b-ubuntu22.04-py3.10
      volumes:
        - /usr/local/dcmi:/usr/local/dcmi
        - /usr/local/bin/npu-smi:/usr/local/bin/npu-smi
        - /usr/local/Ascend/driver/lib64/:/usr/local/Ascend/driver/lib64/
        # Use self-host cache speed up pip and model download
        # - /home/action/actions-runner/_work/cache:/github/home/.cache/
      options: >-
        --device /dev/davinci0
        --device /dev/davinci_manager
        --device /dev/devmm_svm
        --device /dev/hisi_hdc
        --privileged
        --network "host"
    steps:
      - name: Check npu and CANN info
        run: |
          cat /usr/local/Ascend/ascend-toolkit/latest/"$(uname -i)"-linux/ascend_toolkit_install.info
          npu-smi info
      - name: Checkout volcengine/verl repo
        uses: actions/checkout@v4
      - name: Run test
        run: |
          lscpu