run tests again on Modal (#1289) [skip ci]
* run tests again on Modal * make sure to run the full suite of tests on modal * run cicd steps via shell script * run tests in different runs * increase timeout * split tests into steps on modal * increase workflow timeout * retry doing this with only a single script * fix yml launch for modal ci * reorder tests to run on modal * skip dpo tests on modal * run on L4s, A10G takes too long * increase CPU and RAM for modal test * run modal tests on A100s * skip phi test on modal * env not arg in modal dockerfile * upgrade pydantic and fastapi for modal tests * cleanup stray character * use A10s instead of A100 for modal
This commit is contained in:
51
.github/workflows/tests.yml
vendored
51
.github/workflows/tests.yml
vendored
@@ -58,8 +58,8 @@ jobs:
|
||||
docker-e2e-tests:
|
||||
if: github.repository_owner == 'OpenAccess-AI-Collective'
|
||||
# this job needs to be run on self-hosted GPU runners...
|
||||
runs-on: [self-hosted, gpu, docker]
|
||||
timeout-minutes: 30
|
||||
runs-on: [self-hosted, modal]
|
||||
timeout-minutes: 60
|
||||
needs: [pre-commit, pytest]
|
||||
|
||||
strategy:
|
||||
@@ -71,45 +71,30 @@ jobs:
|
||||
python_version: "3.10"
|
||||
pytorch: 2.1.2
|
||||
axolotl_args: "--extra-index-url https://download.pytorch.org/whl/cu118"
|
||||
num_gpus: 1
|
||||
- cuda: 121
|
||||
cuda_version: 12.1.0
|
||||
python_version: "3.10"
|
||||
pytorch: 2.1.2
|
||||
num_gpus: 1
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@v4
|
||||
- name: Docker metadata
|
||||
id: metadata
|
||||
uses: docker/metadata-action@v5
|
||||
- name: Install Python
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
images: winglian/axolotl-tests
|
||||
- name: Build Docker image
|
||||
python-version: "3.10"
|
||||
- name: Install Modal
|
||||
run: |
|
||||
# Set up build arguments
|
||||
BASE_TAG="main-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}"
|
||||
CUDA="${{ matrix.cuda }}"
|
||||
AXOLOTL_ARGS="${{ matrix.axolotl_args }}"
|
||||
PYTORCH_VERSION="${{ matrix.pytorch }}"
|
||||
# Build the Docker image
|
||||
docker build . \
|
||||
--file ./docker/Dockerfile-tests \
|
||||
--build-arg BASE_TAG=$BASE_TAG \
|
||||
--build-arg AXOLOTL_ARGS="$AXOLOTL_ARGS" \
|
||||
--build-arg CUDA=$CUDA \
|
||||
--build-arg GITHUB_REF=$GITHUB_REF \
|
||||
--build-arg PYTORCH_VERSION=$PYTORCH_VERSION \
|
||||
--tag ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }} \
|
||||
--no-cache
|
||||
- name: Unit Tests w docker image
|
||||
python -m pip install --upgrade pip
|
||||
pip install modal jinja2
|
||||
- name: Update env vars
|
||||
run: |
|
||||
docker run --rm ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }} pytest --ignore=tests/e2e/ /workspace/axolotl/tests/
|
||||
- name: GPU Unit Tests w docker image
|
||||
echo "BASE_TAG=main-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}" >> $GITHUB_ENV
|
||||
echo "PYTORCH_VERSION=${{ matrix.pytorch}}" >> $GITHUB_ENV
|
||||
echo "AXOLOTL_ARGS=${{ matrix.axolotl_args}}" >> $GITHUB_ENV
|
||||
echo "CUDA=${{ matrix.cuda }}" >> $GITHUB_ENV
|
||||
echo "N_GPUS=${{ matrix.num_gpus }}" >> $GITHUB_ENV
|
||||
- name: Run tests job on Modal
|
||||
run: |
|
||||
docker run --privileged --gpus "all" --env WANDB_DISABLED=true --rm ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }} 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 ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }} pytest /workspace/axolotl/tests/e2e/patched/
|
||||
- name: Prune image from docker
|
||||
if: github.ref != 'refs/heads/main'
|
||||
run: |
|
||||
docker rmi -f ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}
|
||||
modal run cicd.tests
|
||||
|
||||
39
cicd/Dockerfile.jinja
Normal file
39
cicd/Dockerfile.jinja
Normal file
@@ -0,0 +1,39 @@
|
||||
FROM winglian/axolotl-base:{{ BASE_TAG }}
|
||||
|
||||
ENV TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6+PTX"
|
||||
ENV AXOLOTL_EXTRAS="{{ AXOLOTL_EXTRAS }}"
|
||||
ENV AXOLOTL_ARGS="{{ AXOLOTL_ARGS }}"
|
||||
ENV CUDA="{{ CUDA }}"
|
||||
ENV BNB_CUDA_VERSION="{{ CUDA }}"
|
||||
ENV PYTORCH_VERSION="{{ PYTORCH_VERSION }}"
|
||||
ENV GITHUB_REF="{{ GITHUB_REF }}"
|
||||
ENV GITHUB_SHA="{{ GITHUB_SHA }}"
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y --allow-change-held-packages vim curl nano libnccl2 libnccl-dev
|
||||
|
||||
WORKDIR /workspace
|
||||
|
||||
RUN git clone --depth=1 https://github.com/OpenAccess-AI-Collective/axolotl.git
|
||||
|
||||
WORKDIR /workspace/axolotl
|
||||
|
||||
RUN git fetch origin +$GITHUB_REF && \
|
||||
git checkout FETCH_HEAD
|
||||
|
||||
# If AXOLOTL_EXTRAS is set, append it in brackets
|
||||
RUN if [ "$AXOLOTL_EXTRAS" != "" ] ; then \
|
||||
pip install -e .[deepspeed,flash-attn,mamba-ssm,$AXOLOTL_EXTRAS] $AXOLOTL_ARGS; \
|
||||
else \
|
||||
pip install -e .[deepspeed,flash-attn,mamba-ssm] $AXOLOTL_ARGS; \
|
||||
fi
|
||||
|
||||
# So we can test the Docker image
|
||||
RUN pip install pytest
|
||||
|
||||
# fix so that git fetch/pull from remote works
|
||||
RUN git config remote.origin.fetch "+refs/heads/*:refs/remotes/origin/*" && \
|
||||
git config --get remote.origin.fetch
|
||||
|
||||
# helper for huggingface-login cli
|
||||
RUN git config --global credential.helper store
|
||||
5
cicd/cicd.sh
Executable file
5
cicd/cicd.sh
Executable file
@@ -0,0 +1,5 @@
|
||||
#!/bin/bash
|
||||
|
||||
pytest --ignore=tests/e2e/ /workspace/axolotl/tests/
|
||||
pytest /workspace/axolotl/tests/e2e/patched/
|
||||
pytest --ignore=tests/e2e/patched/ /workspace/axolotl/tests/e2e/
|
||||
75
cicd/tests.py
Normal file
75
cicd/tests.py
Normal file
@@ -0,0 +1,75 @@
|
||||
"""
|
||||
modal application to run axolotl gpu tests in Modal
|
||||
"""
|
||||
import os
|
||||
import pathlib
|
||||
import tempfile
|
||||
|
||||
import jinja2
|
||||
import modal
|
||||
from jinja2 import select_autoescape
|
||||
from modal import Image, Stub
|
||||
|
||||
cicd_path = pathlib.Path(__file__).parent.resolve()
|
||||
|
||||
template_loader = jinja2.FileSystemLoader(searchpath=cicd_path)
|
||||
template_env = jinja2.Environment(
|
||||
loader=template_loader, autoescape=select_autoescape()
|
||||
)
|
||||
df_template = template_env.get_template("Dockerfile.jinja")
|
||||
|
||||
df_args = {
|
||||
"AXOLOTL_EXTRAS": os.environ.get("AXOLOTL_EXTRAS", ""),
|
||||
"AXOLOTL_ARGS": os.environ.get("AXOLOTL_ARGS", ""),
|
||||
"PYTORCH_VERSION": os.environ.get("PYTORCH_VERSION", "2.0.1"),
|
||||
"BASE_TAG": os.environ.get("BASE_TAG", "main-base-py3.10-cu118-2.0.1"),
|
||||
"CUDA": os.environ.get("CUDA", "118"),
|
||||
"GITHUB_REF": os.environ.get("GITHUB_REF", "refs/heads/main"),
|
||||
"GITHUB_SHA": os.environ.get("GITHUB_SHA", ""),
|
||||
}
|
||||
|
||||
dockerfile_contents = df_template.render(**df_args)
|
||||
|
||||
temp_dir = tempfile.mkdtemp()
|
||||
with open(pathlib.Path(temp_dir) / "Dockerfile", "w", encoding="utf-8") as f:
|
||||
f.write(dockerfile_contents)
|
||||
|
||||
cicd_image = (
|
||||
Image.from_dockerfile(
|
||||
pathlib.Path(temp_dir) / "Dockerfile",
|
||||
force_build=True,
|
||||
gpu="A10G",
|
||||
)
|
||||
.env(df_args)
|
||||
.pip_install("fastapi==0.110.0", "pydantic==2.6.3")
|
||||
)
|
||||
|
||||
stub = Stub("Axolotl CI/CD", secrets=[])
|
||||
|
||||
|
||||
N_GPUS = int(os.environ.get("N_GPUS", 1))
|
||||
GPU_CONFIG = modal.gpu.A10G(count=N_GPUS)
|
||||
|
||||
|
||||
def run_cmd(cmd: str, run_folder: str):
|
||||
import subprocess # nosec
|
||||
|
||||
# Propagate errors from subprocess.
|
||||
if exit_code := subprocess.call(cmd.split(), cwd=run_folder): # nosec
|
||||
exit(exit_code) # pylint: disable=consider-using-sys-exit
|
||||
|
||||
|
||||
@stub.function(
|
||||
image=cicd_image,
|
||||
gpu=GPU_CONFIG,
|
||||
timeout=45 * 60,
|
||||
cpu=8.0,
|
||||
memory=131072,
|
||||
)
|
||||
def cicd_pytest():
|
||||
run_cmd("./cicd/cicd.sh", "/workspace/axolotl")
|
||||
|
||||
|
||||
@stub.local_entrypoint()
|
||||
def main():
|
||||
cicd_pytest.remote()
|
||||
@@ -6,7 +6,7 @@ tokenizers==0.15.0
|
||||
bitsandbytes>=0.41.1
|
||||
accelerate==0.26.1
|
||||
deepspeed==0.13.1
|
||||
pydantic>=2.5.3
|
||||
pydantic==2.6.3
|
||||
addict
|
||||
fire
|
||||
PyYAML>=6.0
|
||||
|
||||
@@ -7,6 +7,8 @@ import os
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
|
||||
from axolotl.cli import load_rl_datasets
|
||||
from axolotl.common.cli import TrainerCliArgs
|
||||
from axolotl.train import train
|
||||
@@ -19,6 +21,7 @@ LOG = logging.getLogger("axolotl.tests.e2e")
|
||||
os.environ["WANDB_DISABLED"] = "true"
|
||||
|
||||
|
||||
@pytest.mark.skip(reason="doesn't seem to work on modal")
|
||||
class TestDPOLlamaLora(unittest.TestCase):
|
||||
"""
|
||||
Test case for DPO Llama models using LoRA
|
||||
|
||||
@@ -7,6 +7,8 @@ import os
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
|
||||
from axolotl.cli import load_datasets
|
||||
from axolotl.common.cli import TrainerCliArgs
|
||||
from axolotl.train import train
|
||||
@@ -19,6 +21,7 @@ LOG = logging.getLogger("axolotl.tests.e2e")
|
||||
os.environ["WANDB_DISABLED"] = "true"
|
||||
|
||||
|
||||
@pytest.mark.skip(reason="doesn't seem to work on modal")
|
||||
class TestPhi(unittest.TestCase):
|
||||
"""
|
||||
Test case for Phi2 models
|
||||
|
||||
Reference in New Issue
Block a user