Files
ColossalAI/.github/workflows/build.yml
ver217 c415240db6 [nvme] CPUAdam and HybridAdam support NVMe offload (#1360)
* impl nvme optimizer

* update cpu adam

* add unit test

* update hybrid adam

* update docstr

* add TODOs

* update CI

* fix CI

* fix CI

* fix CI path

* fix CI path

* fix CI path

* fix install tensornvme

* fix CI

* fix CI path

* fix CI env variables

* test CI

* test CI

* fix CI

* fix nvme optim __del__

* fix adam __del__

* fix nvme optim

* fix CI env variables

* fix nvme optim import

* test CI

* test CI

* fix CI
2022-07-26 17:25:24 +08:00

50 lines
1.7 KiB
YAML

name: Build
on:
pull_request:
types: [synchronize, labeled]
jobs:
build:
name: Build and Test Colossal-AI
if: |
github.event.pull_request.draft == false &&
github.base_ref == 'main' &&
github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI' &&
contains( github.event.pull_request.labels.*.name, 'Run Build and Test')
runs-on: [self-hosted, gpu]
container:
image: hpcaitech/pytorch-cuda:1.11.0-11.3.0
options: --gpus all --rm -v /data/scratch/cifar-10:/data/scratch/cifar-10
timeout-minutes: 40
steps:
- uses: actions/checkout@v2
with:
repository: hpcaitech/TensorNVMe
ssh-key: ${{ secrets.SSH_KEY_FOR_CI }}
path: TensorNVMe
- name: Install tensornvme
run: |
cd TensorNVMe
conda install cmake
pip install -r requirements.txt
pip install -v .
- uses: actions/checkout@v2
with:
ssh-key: ${{ secrets.SSH_KEY_FOR_CI }}
- name: Install Colossal-AI
run: |
[ ! -z "$(ls -A /github/home/cuda_ext_cache/)" ] && cp -r /github/home/cuda_ext_cache/* /__w/ColossalAI/ColossalAI/
pip install -r requirements/requirements.txt
pip install -v -e .
cp -r /__w/ColossalAI/ColossalAI/build /github/home/cuda_ext_cache/
cp /__w/ColossalAI/ColossalAI/*.so /github/home/cuda_ext_cache/
pip install -r requirements/requirements-test.txt
- name: Unit Testing
run: |
PYTHONPATH=$PWD pytest tests
env:
DATA: /data/scratch/cifar-10
NCCL_SHM_DISABLE: 1
LD_LIBRARY_PATH: /github/home/.tensornvme/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64