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:
NanoCode012
2026-04-21 21:16:03 +07:00
committed by GitHub
parent 323da791eb
commit 9de5b76336
58 changed files with 496 additions and 1520 deletions

View File

@@ -31,7 +31,10 @@ PRs are **greatly welcome**!
Please run below to setup env
```bash
pip3 install -r requirements-dev.txt -r requirements-tests.txt
# Install axolotl + dev and test dependencies from lockfile
export UV_TORCH_BACKEND=cu128 # or cu130
uv sync --extra flash-attn --extra deepspeed --group dev --group test
source .venv/bin/activate
pre-commit install
# test

View File

@@ -6,7 +6,7 @@ on:
types: [opened, synchronize, reopened, ready_for_review]
paths:
- '**.py'
- 'requirements.txt'
- 'pyproject.toml'
- '.github/workflows/*.yml'
- "*.[q]md"
- "examples/**/*.y[a]?ml"

View File

@@ -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 }}

View File

@@ -8,6 +8,9 @@ on:
permissions: {}
env:
UV_SYSTEM_PYTHON: "1"
jobs:
setup_release:
name: Create Release
@@ -41,11 +44,15 @@ jobs:
with:
python-version: "3.11"
- name: Install uv
uses: astral-sh/setup-uv@v7
- name: Install dependencies
run: |
pip3 install wheel packaging==26.0
pip3 install --no-build-isolation -e .
pip3 install -r requirements-dev.txt -r requirements-tests.txt
uv pip install wheel packaging
uv pip install --no-build-isolation -e .
uv pip install black mypy pre-commit types-requests quartodoc jupyter blobfile tiktoken \
codecov codecov-cli pytest pytest-cov pytest-retry pytest-sugar pytest-xdist tbparse
- name: Extract tag name
id: tag

View File

@@ -2,15 +2,18 @@ name: Tests Nightly against upstream main
on:
workflow_dispatch:
schedule:
- cron: '0 0 * * *' # Runs at 00:00 UTC every day
- cron: "0 0 * * *" # Runs at 00:00 UTC every day
pull_request:
types: [opened, synchronize, reopened, ready_for_review]
paths:
- '.github/workflows/tests-nightly.yml'
- ".github/workflows/tests-nightly.yml"
permissions:
contents: read
env:
UV_SYSTEM_PYTHON: "1"
jobs:
pre-commit:
name: pre-commit
@@ -20,7 +23,7 @@ jobs:
- uses: actions/setup-python@v5
with:
python-version: "3.11"
cache: 'pip' # caching pip dependencies
cache: "pip" # caching pip dependencies
- uses: pre-commit/action@v3.0.1
env:
SKIP: no-commit-to-branch
@@ -43,7 +46,7 @@ jobs:
strategy:
fail-fast: false
matrix:
python_version: ["3.12"] # TODO include py3.14 once https://github.com/mistralai/mistral-common/pull/194 is merged
python_version: ["3.12"] # TODO include py3.14 once https://github.com/mistralai/mistral-common/pull/194 is merged
pytorch_version: ["2.9.1", "2.10.0"]
timeout-minutes: 20
@@ -61,36 +64,34 @@ jobs:
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python_version }}
cache: 'pip' # caching pip dependencies
- name: upgrade pip
run: |
pip3 install --upgrade pip
pip3 install --upgrade packaging==26.0 setuptools==78.1.1 wheel
- name: Install uv
uses: astral-sh/setup-uv@v7
- name: Install PyTorch
run: |
pip3 install torch==${{ matrix.pytorch_version }} torchvision
- name: Update requirements.txt
run: |
sed -i 's#^transformers.*#transformers @ git+https://github.com/huggingface/transformers.git@main#' requirements.txt
sed -i 's#^peft.*#peft @ git+https://github.com/huggingface/peft.git@main#' requirements.txt
sed -i 's#^accelerate.*#accelerate @ git+https://github.com/huggingface/accelerate.git@main#' requirements.txt
sed -i 's#^trl.*#trl @ git+https://github.com/huggingface/trl.git@main#' requirements.txt
sed -i 's#^datasets.*#datasets @ git+https://github.com/huggingface/datasets.git@main#' requirements.txt
uv pip install torch==${{ matrix.pytorch_version }} torchvision
uv pip freeze | grep -E "^(torch|torchvision)==" > /tmp/torch-pin.txt
- name: Install dependencies
run: |
pip3 show torch
pip3 install --no-build-isolation -U -e .
python scripts/unsloth_install.py | sh
python scripts/cutcrossentropy_install.py | sh
pip3 install -r requirements-dev.txt -r requirements-tests.txt
uv pip install --no-build-isolation -e . --override /tmp/torch-pin.txt
python scripts/cutcrossentropy_install.py --uv | sh
uv pip install black mypy pre-commit types-requests quartodoc jupyter blobfile tiktoken \
codecov codecov-cli pytest pytest-cov pytest-retry pytest-sugar pytest-xdist tbparse
- name: Override with nightly HF packages
run: |
uv pip install --no-deps \
"transformers @ git+https://github.com/huggingface/transformers.git@main" \
"peft @ git+https://github.com/huggingface/peft.git@main" \
"accelerate @ git+https://github.com/huggingface/accelerate.git@main" \
"trl @ git+https://github.com/huggingface/trl.git@main" \
"datasets @ git+https://github.com/huggingface/datasets.git@main"
- name: Make sure PyTorch version wasn't clobbered
run: |
python -c "import torch; assert '${{ matrix.pytorch_version }}' in torch.__version__"
python -c "import torch; assert '${{ matrix.pytorch_version }}' in torch.__version__, f'Expected torch ${{ matrix.pytorch_version }} but got {torch.__version__}'"
- name: Ensure axolotl CLI was installed
run: |
@@ -102,9 +103,6 @@ jobs:
pytest -v --durations=10 tests/patched/
pytest -v --durations=10 tests/cli/
- name: cleanup pip cache
run: |
find "$(pip cache dir)/http-v2" -type f -mtime +14 -exec rm {} \;
docker-e2e-tests:
if: github.repository_owner == 'axolotl-ai-cloud'
@@ -136,7 +134,6 @@ jobs:
pytorch: 2.9.1
num_gpus: 1
axolotl_extras:
dockerfile: "Dockerfile-uv.jinja"
nightly_build: "true"
steps:
- name: Checkout
@@ -157,7 +154,7 @@ 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'}}" >> $GITHUB_ENV
echo "NIGHTLY_BUILD=${{ matrix.nightly_build }}" >> $GITHUB_ENV
- name: Run tests job on Modal
env:

View File

@@ -6,21 +6,19 @@ on:
branches:
- "main"
paths:
- '**.py'
- 'requirements.txt'
- '.github/workflows/*.yml'
- 'requirements-tests.txt'
- 'cicd/cicd.sh'
- 'cicd/Dockerfile.jinja'
- "**.py"
- "pyproject.toml"
- ".github/workflows/*.yml"
- "cicd/cicd.sh"
- "cicd/Dockerfile-uv.jinja"
pull_request:
types: [opened, synchronize, reopened, ready_for_review]
paths:
- '**.py'
- 'requirements.txt'
- '.github/workflows/*.yml'
- 'requirements-tests.txt'
- 'cicd/cicd.sh'
- 'cicd/Dockerfile.jinja'
types: [opened, synchronize, reopened, ready_for_review]
paths:
- "**.py"
- "pyproject.toml"
- ".github/workflows/*.yml"
- "cicd/cicd.sh"
- "cicd/Dockerfile-uv.jinja"
workflow_dispatch:
# Cancel jobs on the same ref if a new one is triggered
@@ -33,6 +31,7 @@ permissions:
env:
TRANSFORMERS_IS_CI: "yes"
UV_SYSTEM_PYTHON: "1"
jobs:
pre-commit:
@@ -44,7 +43,7 @@ jobs:
- uses: actions/setup-python@v5
with:
python-version: "3.11"
cache: 'pip' # caching pip dependencies
cache: "pip" # caching pip dependencies
- uses: pre-commit/action@v3.0.1
env:
SKIP: no-commit-to-branch
@@ -94,32 +93,25 @@ jobs:
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python_version }}
cache: 'pip' # caching pip dependencies
- name: upgrade pip
run: |
pip3 install --upgrade pip
pip3 install --upgrade packaging==26.0 setuptools==75.8.0 wheel
- name: Install uv
uses: astral-sh/setup-uv@v7
- name: Install PyTorch
run: |
pip3 install --no-cache-dir torch==${{ matrix.pytorch_version }} torchvision
uv pip install torch==${{ matrix.pytorch_version }} torchvision
uv pip freeze | grep -E "^(torch|torchvision)==" > /tmp/torch-pin.txt
- name: Install dependencies
run: |
pip3 show torch
pip3 install --no-cache-dir --no-build-isolation -U -e .
python scripts/unsloth_install.py | sh
python scripts/cutcrossentropy_install.py | sh
pip3 install -r requirements-dev.txt -r requirements-tests.txt
- name: cleanup pip cache
run: |
find "$(pip cache dir)/http-v2" -type f -mtime +14 -exec rm {} \;
uv pip install --no-build-isolation -e . --override /tmp/torch-pin.txt
python scripts/cutcrossentropy_install.py --uv | sh
uv pip install black mypy pre-commit types-requests quartodoc jupyter blobfile tiktoken \
codecov codecov-cli pytest pytest-cov pytest-retry pytest-sugar pytest-xdist tbparse
- name: Make sure PyTorch version wasn't clobbered
run: |
python -c "import torch; assert '${{ matrix.pytorch_version }}' in torch.__version__"
python -c "import torch; assert '${{ matrix.pytorch_version }}' in torch.__version__, f'Expected torch ${{ matrix.pytorch_version }} but got {torch.__version__}'"
- name: Ensure axolotl CLI was installed
run: |
@@ -188,33 +180,27 @@ jobs:
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python_version }}
cache: 'pip' # caching pip dependencies
- name: upgrade pip
run: |
pip3 install --upgrade pip
pip3 install --upgrade packaging==26.0 setuptools==75.8.0 setuptools_scm build wheel psutil
- name: Install uv
uses: astral-sh/setup-uv@v7
- name: Install PyTorch
run: |
pip3 install --no-cache-dir torch==${{ matrix.pytorch_version }} torchvision
uv pip install torch==${{ matrix.pytorch_version }} torchvision
uv pip freeze | grep -E "^(torch|torchvision)==" > /tmp/torch-pin.txt
- name: Install dependencies
run: |
pip3 show torch
uv pip install packaging setuptools_scm build wheel psutil
python -m build --no-isolation --sdist
pip3 install --no-cache-dir --no-build-isolation dist/axolotl*.tar.gz
python scripts/unsloth_install.py | sh
python scripts/cutcrossentropy_install.py | sh
pip3 install -r requirements-dev.txt -r requirements-tests.txt
- name: cleanup pip cache
run: |
find "$(pip cache dir)/http-v2" -type f -mtime +14 -exec rm {} \;
uv pip install --no-build-isolation dist/axolotl*.tar.gz --override /tmp/torch-pin.txt
python scripts/cutcrossentropy_install.py --uv | sh
uv pip install black mypy pre-commit types-requests quartodoc jupyter blobfile tiktoken \
codecov codecov-cli pytest pytest-cov pytest-retry pytest-sugar pytest-xdist tbparse
- name: Make sure PyTorch version wasn't clobbered
run: |
python -c "import torch; assert '${{ matrix.pytorch_version }}' in torch.__version__"
python -c "import torch; assert '${{ matrix.pytorch_version }}' in torch.__version__, f'Expected torch ${{ matrix.pytorch_version }} but got {torch.__version__}'"
- name: Ensure axolotl CLI was installed
run: |
@@ -291,7 +277,6 @@ jobs:
pytorch: 2.9.1
num_gpus: 1
axolotl_extras:
dockerfile: "Dockerfile-uv.jinja"
steps:
- name: Checkout
uses: actions/checkout@v4
@@ -312,7 +297,7 @@ jobs:
echo "CUDA=${{ matrix.cuda }}" >> $GITHUB_ENV
echo "MODAL_IMAGE_BUILDER_VERSION=2024.10" >> $GITHUB_ENV
echo "N_GPUS=${{ 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 }}
@@ -374,7 +359,7 @@ jobs:
echo "MODAL_IMAGE_BUILDER_VERSION=2024.10" >> $GITHUB_ENV
echo "N_GPUS=${{ matrix.num_gpus }}" >> $GITHUB_ENV
echo "GPU_TYPE=${{ matrix.gpu_type || 'L40S'}}" >> $GITHUB_ENV
echo "E2E_DOCKERFILE=${{ 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 }}