feat: move to uv first (#3545)
* feat: move to uv first * fix: update doc to uv first * fix: merge dev/tests into uv pyproject * fix: update docker docs to match current config * fix: migrate examples to readme * fix: add llmcompressor to conflict * feat: rec uv sync with lockfile for dev/ci * fix: update docker docs to clarify how to use uv images * chore: docs * fix: use system python, no venv * fix: set backend cpu * fix: only set for installing pytorch step * fix: remove unsloth kernel and installs * fix: remove U in tests * fix: set backend in deps too * chore: test * chore: comments * fix: attempt to lock torch * fix: workaround torch cuda and not upgraded * fix: forgot to push * fix: missed source * fix: nightly upstream loralinear config * fix: nightly phi3 long rope not work * fix: forgot commit * fix: test phi3 template change * fix: no more requirements * fix: carry over changes from new requirements to pyproject * chore: remove lockfile per discussion * fix: set match-runtime * fix: remove unneeded hf hub buildtime * fix: duplicate cache delete on nightly * fix: torchvision being overridden * fix: migrate to uv images * fix: leftover from merge * fix: simplify base readme * fix: update assertion message to be clearer * chore: docs * fix: change fallback for cicd script * fix: match against main exactly * fix: peft 0.19.1 change * fix: e2e test * fix: ci * fix: e2e test
This commit is contained in:
35
.github/workflows/multi-gpu-e2e.yml
vendored
35
.github/workflows/multi-gpu-e2e.yml
vendored
@@ -3,17 +3,15 @@ name: docker-multigpu-tests-biweekly
|
||||
on:
|
||||
pull_request:
|
||||
paths:
|
||||
- 'tests/e2e/multigpu/**.py'
|
||||
- 'requirements.txt'
|
||||
- 'setup.py'
|
||||
- 'pyproject.toml'
|
||||
- '.github/workflows/multi-gpu-e2e.yml'
|
||||
- 'scripts/cutcrossentropy_install.py'
|
||||
- 'src/axolotl/core/trainers/mixins/sequence_parallel.py'
|
||||
- 'src/axolotl/utils/distributed.py'
|
||||
- "tests/e2e/multigpu/**.py"
|
||||
- "pyproject.toml"
|
||||
- ".github/workflows/multi-gpu-e2e.yml"
|
||||
- "scripts/cutcrossentropy_install.py"
|
||||
- "src/axolotl/core/trainers/mixins/sequence_parallel.py"
|
||||
- "src/axolotl/utils/distributed.py"
|
||||
workflow_dispatch:
|
||||
schedule:
|
||||
- cron: '0 0 * * 1,4' # Runs at 00:00 UTC every monday & thursday
|
||||
- cron: "0 0 * * 1,4" # Runs at 00:00 UTC every monday & thursday
|
||||
|
||||
# Cancel jobs on the same ref if a new one is triggered
|
||||
concurrency:
|
||||
@@ -33,19 +31,19 @@ jobs:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
include:
|
||||
# - cuda: 129
|
||||
# cuda_version: 12.9.1
|
||||
# python_version: "3.12"
|
||||
# pytorch: 2.9.1
|
||||
# axolotl_extras: "fbgemm-gpu"
|
||||
# num_gpus: 2
|
||||
# dockerfile: "Dockerfile-uv.jinja"
|
||||
# - cuda: 129
|
||||
# cuda_version: 12.9.1
|
||||
# python_version: "3.12"
|
||||
# pytorch: 2.9.1
|
||||
# axolotl_extras: "fbgemm-gpu"
|
||||
# num_gpus: 2
|
||||
# dockerfile: "Dockerfile-uv.jinja"
|
||||
- cuda: 130
|
||||
cuda_version: 13.0.0
|
||||
python_version: "3.11"
|
||||
pytorch: 2.9.1
|
||||
axolotl_extras:
|
||||
# axolotl_extras: fbgemm-gpu
|
||||
# axolotl_extras: fbgemm-gpu
|
||||
num_gpus: 2
|
||||
- cuda: 128
|
||||
cuda_version: 12.8.1
|
||||
@@ -53,7 +51,6 @@ jobs:
|
||||
pytorch: 2.10.0
|
||||
axolotl_extras: "fbgemm-gpu"
|
||||
num_gpus: 2
|
||||
dockerfile: "Dockerfile-uv.jinja"
|
||||
runs-on: [self-hosted, modal]
|
||||
timeout-minutes: 120
|
||||
steps:
|
||||
@@ -75,7 +72,7 @@ jobs:
|
||||
echo "AXOLOTL_EXTRAS=${{ matrix.axolotl_extras}}" >> $GITHUB_ENV
|
||||
echo "CUDA=${{ matrix.cuda }}" >> $GITHUB_ENV
|
||||
echo "N_GPUS=${{ matrix.num_gpus }}" >> $GITHUB_ENV
|
||||
echo "E2E_DOCKERFILE=${{ matrix.dockerfile || 'Dockerfile.jinja'}}" >> $GITHUB_ENV
|
||||
echo "E2E_DOCKERFILE=${{ matrix.dockerfile || 'Dockerfile-uv.jinja'}}" >> $GITHUB_ENV
|
||||
- name: Run tests job on Modal
|
||||
env:
|
||||
CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
|
||||
|
||||
Reference in New Issue
Block a user