Various fixes for CI, save_only_model for RL, prevent packing multiprocessing deadlocks (#2661)

* lean mistral ft tests, remove e2e torch 2.4.1 test

* make sure to pass save_only_model for RL

* more tests to make ci leaner, add cleanup to modal ci

* fix module for import in e2e tests

* use mp spawn to prevent deadlocks with packing

* make sure cleanup shell script is executable when cloned out
This commit is contained in:
Wing Lian
2025-05-12 10:51:18 -04:00
committed by GitHub
parent 47e0e71bc8
commit c7b6790614
13 changed files with 190 additions and 99 deletions

View File

@@ -335,12 +335,6 @@ jobs:
pytorch: 2.6.0
num_gpus: 1
axolotl_extras: llmcompressor
- cuda: 124
cuda_version: 12.4.1
python_version: "3.11"
pytorch: 2.4.1
num_gpus: 1
axolotl_extras:
- cuda: 124
cuda_version: 12.4.1
python_version: "3.11"
@@ -377,3 +371,43 @@ jobs:
- name: Run tests job on Modal
run: |
modal run cicd.e2e_tests
docker-e2e-cleanup:
runs-on: [self-hosted, modal]
timeout-minutes: 90
needs: [docker-e2e-tests]
strategy:
fail-fast: false
matrix:
include:
- cuda: 124
cuda_version: 12.4.1
python_version: "3.11"
pytorch: 2.6.0
num_gpus: 1
axolotl_extras: vllm
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Install Python
uses: actions/setup-python@v5
with:
python-version: "3.11"
- name: Install Modal
run: |
python -m pip install --upgrade pip
pip install modal==0.71.8 jinja2
- name: Update env vars
run: |
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}}" >> $GITHUB_ENV
echo "AXOLOTL_EXTRAS=${{ matrix.axolotl_extras}}" >> $GITHUB_ENV
echo "CUDA=${{ matrix.cuda }}" >> $GITHUB_ENV
echo "MODAL_IMAGE_BUILDER_VERSION=2024.10" >> $GITHUB_ENV
echo "N_GPUS=${{ matrix.num_gpus }}" >> $GITHUB_ENV
echo "CODECOV_TOKEN=${{ secrets.CODECOV_TOKEN }}" >> $GITHUB_ENV
- name: Run tests job on Modal
run: |
modal run cicd.cleanup