Skip to content

add caching

add caching #32

Workflow file for this run

name: Test Turbine Models
on:
workflow_dispatch:
pull_request:
push:
branches:
- main
concurrency:
# A PR number if a pull request and otherwise the commit hash. This cancels
# queued and in-progress runs for the same PR (presubmit) or commit
# (postsubmit). The workflow name is prepended to avoid conflicts between
# different workflows.
group: ${{ github.workflow }}-${{ github.event.number || github.sha }}
cancel-in-progress: true
jobs:
test-turbine-models:
strategy:
matrix:
version: [3.11]
os: [nodai-amdgpu-mi250-x86-64]
runs-on: ${{matrix.os}}
env:
E2E_VENV_DIR: ${{ github.workspace }}/test-suite_venv
HF_TOKEN: ${{ secrets.HF_TOKEN }}
AZ_PRIVATE_CONNECTION: ${{ secrets.ONNXPRIVATESTORAGE_AZ_PRIVATE_CONNECTION }}
ROCR_VISIBLE_DEVICES: ${{ matrix.visible-device }}
TORCH_HOME: /groups/aig_sharks/test-suite-ci-cache
HF_HOME: /groups/aig_sharks/test-suite-ci-cache
TURBINE_TANK_CACHE_DIR: /groups/aig_sharks/test-suite-ci-cache
steps:
# We are using a persistent Gentoo runner here, and this python action is not supported for the arch
# - name: "Setting up Python"
# uses: actions/setup-python@75f3110429a8c05be0e1bf360334e4cced2b63fa # v2.3.3
# with:
# python-version: ${{matrix.version}}
- name: "Checkout This Repo"
uses: actions/checkout@v4
- name: "Checkout iree-turbine"
uses: actions/checkout@v4
with:
repository: iree-org/iree-turbine
# TODO: Let the ref be passed as a parameter to run integration tests.
path: iree-turbine
- name: Sync source deps
# build IREE from source with -DIREE_BUILD_TRACY=ON if getting tracy profile
run: |
python3.11 -m venv turbine_venv
source turbine_venv/bin/activate
python3.11 -m pip install --upgrade pip
# Note: We install in three steps in order to satisfy requirements
# from non default locations first. Installing the PyTorch CPU
# wheels saves multiple minutes and a lot of bandwidth on runner setup.
pip install --no-compile -r ${{ github.workspace }}/iree-turbine/pytorch-cpu-requirements.txt
pip install --pre --upgrade -r ${{ github.workspace }}/iree-turbine/requirements.txt
pip install --no-compile --pre -e ${{ github.workspace }}/iree-turbine[testing]
pip install --upgrade --pre --no-cache-dir iree-compiler iree-runtime -f https://iree.dev/pip-release-links.html
pip install --no-compile --pre --upgrade -e models -r models/requirements.txt
- name: Show current free memory
run: |
free -mh
- name: Run stateless_llama tests
run: |
source turbine_venv/bin/activate
pytest -v models/turbine_models/tests/stateless_llama_test.py
- name: Run sd tests
run: |
source turbine_venv/bin/activate
pytest -v models/turbine_models/tests/sd_test.py
pytest -v models/turbine_models/tests/sdxl_test.py --device cpu --rt_device local-task --iree_target_triple x86_64-linux-gnu --num_inference_steps 5
pytest -v models/turbine_models/tests/sdxl_test.py --device vulkan --rt_device vulkan --iree_target_triple rdna3-unknown-linux
pytest -v models/turbine_models/tests/sdxl_test.py --device rocm --rt_device hip --iree_target_triple gfx90a --precision fp16 --attn_spec default
pytest -v models/turbine_models/tests/sdxl_test.py --device rocm --rt_device hip --iree_target_triple gfx90a --precision fp16 --attn_spec default --batch_size 2
pytest -v models/turbine_models/tests/sd3_test.py --device cpu --rt_device local-task --iree_target_triple x86_64-linux-gnu --num_inference_steps 5