Files
transformers/.github/workflows/self-push.yml
T
Lysandre Debut 10f8c63620 Ci test tf super slow (#8007)
* Test TF GPU CI

* Change cache

* Fix missing torch requirement

* Fix some model tests


Style

* LXMERT

* MobileBERT

* Longformer skip test

* XLNet

* The rest of the tests

* RAG goes OOM in multi gpu setup

* YAML test files

* Last fixes

* Skip doctests

* Fill mask tests

* Yaml files

* Last test fix

* Style

* Update cache

* Change ONNX tests to slow + use tiny model
2020-10-30 10:25:48 -04:00

210 lines
6.2 KiB
YAML

name: Self-hosted runner (push)
on:
push:
branches:
- master
paths:
- "src/**"
- "tests/**"
- ".github/**"
# pull_request:
repository_dispatch:
jobs:
run_tests_torch_gpu:
runs-on: [self-hosted, single-gpu]
steps:
- uses: actions/checkout@v2
- name: Python version
run: |
which python
python --version
pip --version
- name: Current dir
run: pwd
- run: nvidia-smi
- name: Loading cache.
uses: actions/cache@v2
id: cache
with:
path: .env
key: v1.1-tests_torch_gpu-${{ hashFiles('setup.py') }}
- name: Create new python env (on self-hosted runners we have to handle isolation ourselves)
run: |
python -m venv .env
source .env/bin/activate
which python
python --version
pip --version
- name: Install dependencies
run: |
source .env/bin/activate
pip install --upgrade pip
pip install .[torch,sklearn,testing,onnxruntime]
pip install git+https://github.com/huggingface/datasets
- name: Are GPUs recognized by our DL frameworks
run: |
source .env/bin/activate
python -c "import torch; print('Cuda available:', torch.cuda.is_available())"
python -c "import torch; print('Number of GPUs available:', torch.cuda.device_count())"
- name: Run all non-slow tests on GPU
env:
OMP_NUM_THREADS: 1
CUDA_VISIBLE_DEVICES: 0
run: |
source .env/bin/activate
python -m pytest -n 2 --dist=loadfile -s ./tests/
run_tests_tf_gpu:
runs-on: [self-hosted, single-gpu]
steps:
- uses: actions/checkout@v2
- name: Python version
run: |
which python
python --version
pip --version
- name: Current dir
run: pwd
- run: nvidia-smi
- name: Loading cache.
uses: actions/cache@v2
id: cache
with:
path: .env
key: v1.1-tests_tf_gpu-${{ hashFiles('setup.py') }}
- name: Create new python env (on self-hosted runners we have to handle isolation ourselves)
run: |
python -m venv .env
source .env/bin/activate
which python
python --version
pip --version
- name: Install dependencies
run: |
source .env/bin/activate
pip install --upgrade pip
pip install .[tf,sklearn,testing,onnxruntime]
pip install git+https://github.com/huggingface/datasets
- name: Are GPUs recognized by our DL frameworks
run: |
source .env/bin/activate
TF_CPP_MIN_LOG_LEVEL=3 python -c "import tensorflow as tf; print('TF GPUs available:', bool(tf.config.list_physical_devices('GPU')))"
TF_CPP_MIN_LOG_LEVEL=3 python -c "import tensorflow as tf; print('Number of TF GPUs available:', len(tf.config.list_physical_devices('GPU')))"
- name: Run all non-slow tests on GPU
env:
OMP_NUM_THREADS: 1
CUDA_VISIBLE_DEVICES: 0
run: |
source .env/bin/activate
python -m pytest -n 2 --dist=loadfile -s ./tests/
run_tests_torch_multiple_gpu:
runs-on: [self-hosted, multi-gpu]
steps:
- uses: actions/checkout@v2
- name: Python version
run: |
which python
python --version
pip --version
- name: Current dir
run: pwd
- run: nvidia-smi
- name: Loading cache.
uses: actions/cache@v2
id: cache
with:
path: .env
key: v1.1-tests_torch_multiple_gpu-${{ hashFiles('setup.py') }}
- name: Create new python env (on self-hosted runners we have to handle isolation ourselves)
run: |
python -m venv .env
source .env/bin/activate
which python
python --version
pip --version
- name: Install dependencies
run: |
source .env/bin/activate
pip install --upgrade pip
pip install .[torch,sklearn,testing,onnxruntime]
pip install git+https://github.com/huggingface/datasets
- name: Are GPUs recognized by our DL frameworks
run: |
source .env/bin/activate
python -c "import torch; print('Cuda available:', torch.cuda.is_available())"
python -c "import torch; print('Number of GPUs available:', torch.cuda.device_count())"
- name: Run all non-slow tests on GPU
env:
OMP_NUM_THREADS: 1
run: |
source .env/bin/activate
python -m pytest -n 2 --dist=loadfile -s ./tests/
run_tests_tf_multiple_gpu:
runs-on: [self-hosted, multi-gpu]
steps:
- uses: actions/checkout@v2
- name: Python version
run: |
which python
python --version
pip --version
- name: Current dir
run: pwd
- run: nvidia-smi
- name: Loading cache.
uses: actions/cache@v2
id: cache
with:
path: .env
key: v1.1-tests_tf_multiple_gpu-${{ hashFiles('setup.py') }}
- name: Create new python env (on self-hosted runners we have to handle isolation ourselves)
run: |
python -m venv .env
source .env/bin/activate
which python
python --version
pip --version
- name: Install dependencies
run: |
source .env/bin/activate
pip install --upgrade pip
pip install .[tf,sklearn,testing,onnxruntime]
pip install git+https://github.com/huggingface/datasets
- name: Are GPUs recognized by our DL frameworks
run: |
source .env/bin/activate
TF_CPP_MIN_LOG_LEVEL=3 python -c "import tensorflow as tf; print('TF GPUs available:', bool(tf.config.list_physical_devices('GPU')))"
TF_CPP_MIN_LOG_LEVEL=3 python -c "import tensorflow as tf; print('Number of TF GPUs available:', len(tf.config.list_physical_devices('GPU')))"
- name: Run all non-slow tests on GPU
env:
OMP_NUM_THREADS: 1
run: |
source .env/bin/activate
python -m pytest -n 2 --dist=loadfile -s ./tests/