* attempt to also run e2e tests that needs gpus * fix stray quote * checkout specific github ref * dockerfile for tests with proper checkout ensure wandb is dissabled for docker pytests clear wandb env after testing clear wandb env after testing make sure to provide a default val for pop tryin skipping wandb validation tests explicitly disable wandb in the e2e tests explicitly report_to None to see if that fixes the docker e2e tests split gpu from non-gpu unit tests skip bf16 check in test for now build docker w/o cache since it uses branch name ref revert some changes now that caching is fixed skip bf16 check if on gpu w support * pytest skip for auto-gptq requirements * skip mamba tests for now, split multipack and non packed lora llama tests * split tests that use monkeypatches * fix relative import for prev commit * move other tests using monkeypatches to the correct run
55 lines
1.9 KiB
YAML
55 lines
1.9 KiB
YAML
name: e2e-docker-tests
|
|
|
|
on:
|
|
pull_request:
|
|
paths:
|
|
- '**.py'
|
|
- 'requirements.txt'
|
|
- '.github/workflows/*.yml'
|
|
workflow_dispatch:
|
|
|
|
jobs:
|
|
build-axolotl:
|
|
if: github.repository_owner == 'OpenAccess-AI-Collective'
|
|
# this job needs to be run on self-hosted GPU runners...
|
|
strategy:
|
|
fail-fast: false
|
|
matrix:
|
|
include:
|
|
- cuda: 118
|
|
cuda_version: 11.8.0
|
|
python_version: "3.10"
|
|
pytorch: 2.0.1
|
|
- cuda: 121
|
|
cuda_version: 12.1.0
|
|
python_version: "3.10"
|
|
pytorch: 2.1.1
|
|
runs-on: [self-hosted, gpu, docker]
|
|
steps:
|
|
- name: Checkout
|
|
uses: actions/checkout@v4
|
|
- name: Build Docker image
|
|
run: |
|
|
# Set up build arguments
|
|
BASE_TAG="main-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}"
|
|
CUDA="${{ matrix.cuda }}"
|
|
PYTORCH_VERSION="${{ matrix.pytorch }}"
|
|
# Build the Docker image
|
|
docker build . \
|
|
--file ./docker/Dockerfile-tests \
|
|
--build-arg BASE_TAG=$BASE_TAG \
|
|
--build-arg CUDA=$CUDA \
|
|
--build-arg GITHUB_REF=$GITHUB_REF \
|
|
--build-arg PYTORCH_VERSION=$PYTORCH_VERSION \
|
|
--tag test-axolotl \
|
|
--no-cache
|
|
- name: Unit Tests w docker image
|
|
run: |
|
|
docker run --rm test-axolotl pytest --ignore=tests/e2e/ /workspace/axolotl/tests/
|
|
- name: GPU Unit Tests w docker image
|
|
run: |
|
|
docker run --privileged --gpus "all" --env WANDB_DISABLED=true --rm test-axolotl pytest --ignore=tests/e2e/patched/ /workspace/axolotl/tests/e2e/
|
|
- name: GPU Unit Tests monkeypatched w docker image
|
|
run: |
|
|
docker run --privileged --gpus "all" --env WANDB_DISABLED=true --rm test-axolotl pytest /workspace/axolotl/tests/e2e/patched/
|