-
Notifications
You must be signed in to change notification settings - Fork 48
79 lines (65 loc) · 2.27 KB
/
test_cli_cuda_tensorrt_llm.yaml
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
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
name: CLI CUDA TensorRT-LLM Tests
on:
workflow_dispatch:
push:
branches:
- main
pull_request:
branches:
- main
types:
- opened
- reopened
- synchronize
- labeled
- unlabeled
concurrency:
cancel-in-progress: true
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
jobs:
cli_cuda_tensorrt_llm_single_gpu_tests:
if: ${{
(github.event_name == 'push') ||
(github.event_name == 'workflow_dispatch') ||
contains( github.event.pull_request.labels.*.name, 'cli') ||
contains( github.event.pull_request.labels.*.name, 'cuda') ||
contains( github.event.pull_request.labels.*.name, 'tensorrt_llm') ||
contains( github.event.pull_request.labels.*.name, 'single_gpu') ||
contains( github.event.pull_request.labels.*.name, 'cli_cuda_tensorrt_llm')
}}
runs-on: [single-gpu, nvidia-gpu, a10, ci]
container:
image: huggingface/optimum-nvidia:latest
options: --ipc host --gpus all
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Install dependencies
run: |
pip install -e .[testing]
- name: Run tests
run: |
pytest tests/test_cli.py -x -s -k "cli and cuda and tensorrt_llm and not (tp or pp)"
cli_cuda_tensorrt_llm_multi_gpu_tests:
if: ${{
(github.event_name == 'push') ||
(github.event_name == 'workflow_dispatch') ||
contains( github.event.pull_request.labels.*.name, 'cli') ||
contains( github.event.pull_request.labels.*.name, 'cuda') ||
contains( github.event.pull_request.labels.*.name, 'tensorrt_llm') ||
contains( github.event.pull_request.labels.*.name, 'multi_gpu') ||
contains( github.event.pull_request.labels.*.name, 'cli_cuda_tensorrt_llm_multi_gpu')
}}
runs-on: [multi-gpu, nvidia-gpu, 4-a10, ci]
container:
image: huggingface/optimum-nvidia:latest
options: --ipc host --gpus all
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Install dependencies
run: |
pip install -e .[testing]
- name: Run tests (sequential)
run: |
FORCE_SEQUENTIAL=1 pytest tests/test_cli.py -x -s -k "cli and cuda and tensorrt_llm and (tp or pp)"