forked from huggingface/diffusers
-
Notifications
You must be signed in to change notification settings - Fork 0
52 lines (46 loc) · 1.42 KB
/
ssh-runner.yml
File metadata and controls
52 lines (46 loc) · 1.42 KB
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
name: SSH into GPU runners
on:
workflow_dispatch:
inputs:
runner_type:
description: 'Type of runner to test (aws-g6-4xlarge-plus: a10, aws-g4dn-2xlarge: t4, aws-g6e-xlarge-plus: L40)'
type: choice
required: true
options:
- aws-g6-4xlarge-plus
- aws-g4dn-2xlarge
- aws-g6e-xlarge-plus
docker_image:
description: 'Name of the Docker image'
required: true
env:
IS_GITHUB_CI: "1"
HF_HUB_READ_TOKEN: ${{ secrets.HF_HUB_READ_TOKEN }}
HF_HOME: /mnt/cache
DIFFUSERS_IS_CI: yes
OMP_NUM_THREADS: 8
MKL_NUM_THREADS: 8
RUN_SLOW: yes
jobs:
ssh_runner:
name: "SSH"
runs-on:
group: "${{ github.event.inputs.runner_type }}"
container:
image: ${{ github.event.inputs.docker_image }}
options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface/diffusers:/mnt/cache/ --gpus all --privileged
steps:
- name: Checkout diffusers
uses: actions/checkout@v6
with:
fetch-depth: 2
- name: NVIDIA-SMI
run: |
nvidia-smi
- name: Tailscale # In order to be able to SSH when a test fails
uses: huggingface/tailscale-action@main
with:
authkey: ${{ secrets.TAILSCALE_SSH_AUTHKEY }}
slackChannel: ${{ secrets.SLACK_CIFEEDBACK_CHANNEL }}
slackToken: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}
waitForSSH: true