axolotl-ai-cloud · djsaunde · Aug 21, 2025 · Aug 29, 2025 · Aug 29, 2025 · Aug 29, 2025
diff --git a/.coveragerc b/.coveragerc
@@ -2,7 +2,6 @@
 source = axolotl
 omit =
     */tests/*
-    setup.py
 
 [report]
 exclude_lines =

diff --git a/.github/CONTRIBUTING.md b/.github/CONTRIBUTING.md
@@ -29,13 +29,18 @@ PRs are **greatly welcome**!
 2. Set up the development environment by following the instructions in the [README.md](https://github.com/axolotl-ai-cloud/axolotl/tree/main/README.md) file.
 3. Explore the codebase, run tests, and verify that everything works as expected.
 
-Please run below to setup env
+Please run the below to setup:
+
 ```bash
-pip3 install -r requirements-dev.txt -r requirements-tests.txt
-pre-commit install
+git clone https://github.com/axolotl-ai-cloud/axolotl.git
+cd axolotl
+
+uv sync --dev && uv pip install flash-attn --no-build-isolation
+source .venv/bin/activate
+
+pre-commit install  # install pre-commit hooks
 
-# test
-pytest tests/
+pytest tests/  # optional; run test suite
 ```
 
 ## How to Contribute

diff --git a/.github/workflows/base.yml b/.github/workflows/base.yml
@@ -39,13 +39,6 @@ jobs:
             pytorch: 2.6.0
             torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
             dockerfile: "Dockerfile-base"
-          - cuda: "126"
-            cuda_version: 12.6.3
-            cudnn_version: ""
-            python_version: "3.11"
-            pytorch: 2.7.0
-            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
-            dockerfile: "Dockerfile-base"
           - cuda: "126"
             cuda_version: 12.6.3
             cudnn_version: ""
@@ -105,7 +98,9 @@ jobs:
           context: .
           file: ./docker/${{ matrix.dockerfile }}
           push: ${{ github.event_name != 'pull_request' }}
-          tags: ${{ steps.metadata.outputs.tags }}-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
+          tags: |
+            ${{ steps.metadata.outputs.tags }}-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
+            ${{ steps.metadata.outputs.tags }}-base-uv-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
           labels: ${{ steps.metadata.outputs.labels }}
           build-args: |
             CUDA_VERSION=${{ matrix.cuda_version }}

diff --git a/.github/workflows/docs.yml b/.github/workflows/docs.yml
@@ -20,10 +20,14 @@ jobs:
           uses: actions/setup-python@v5
           with:
             python-version: '3.11'
+        - name: Install uv
+          uses: astral-sh/setup-uv@v4
+          with:
+            version: "latest"
         - name: Install dependencies
           run: |
-            python3 -m pip install jupyter quartodoc
-            python3 -m pip install -e .
+            uv pip install --system jupyter quartodoc
+            uv pip install --system -e .
         - name: Build autodoc
           run: quartodoc build
         - name: Publish to GitHub Pages (and render)

diff --git a/.github/workflows/lint.yml b/.github/workflows/lint.yml
@@ -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"
@@ -23,5 +23,4 @@ jobs:
       - uses: actions/setup-python@v5
         with:
           python-version: "3.11"
-          cache: 'pip' # caching pip dependencies
       - uses: pre-commit/[email protected]
diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
@@ -20,11 +20,6 @@ jobs:
             python_version: "3.11"
             pytorch: 2.6.0
             axolotl_extras:
-          - cuda: 126
-            cuda_version: 12.6.3
-            python_version: "3.11"
-            pytorch: 2.7.0
-            axolotl_extras:
           - cuda: 126
             cuda_version: 12.6.3
             python_version: "3.11"
@@ -73,6 +68,8 @@ jobs:
             PYTORCH_VERSION=${{ matrix.pytorch }}
             AXOLOTL_ARGS=${{ matrix.axolotl_args }}
             AXOLOTL_EXTRAS=${{ matrix.axolotl_extras}}
+            GIT_REF=${{ github.ref }}
+            GIT_SHA=${{ github.sha }}
           file: ./docker/Dockerfile
           push: ${{ github.event_name != 'pull_request' }}
           tags: |
@@ -93,11 +90,6 @@ jobs:
             python_version: "3.11"
             pytorch: 2.6.0
             axolotl_extras:
-          - cuda: 126
-            cuda_version: 12.6.3
-            python_version: "3.11"
-            pytorch: 2.7.0
-            axolotl_extras:
           - cuda: 126
             cuda_version: 12.6.3
             python_version: "3.11"
@@ -148,6 +140,8 @@ jobs:
           build-args: |
             BASE_TAG=${{ github.ref_type == 'tag' && 'main' || github.ref_name }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
             CUDA=${{ matrix.cuda }}
+            GIT_REF=${{ github.ref }}
+            GIT_SHA=${{ github.sha }}
           file: ./docker/Dockerfile-cloud
           push: ${{ github.event_name != 'pull_request' }}
           tags: |
@@ -213,6 +207,8 @@ jobs:
           build-args: |
             BASE_TAG=${{ github.ref_type == 'tag' && 'main' || github.ref_name }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
             CUDA=${{ matrix.cuda }}
+            GIT_REF=${{ github.ref }}
+            GIT_SHA=${{ github.sha }}
           file: ./docker/Dockerfile-cloud-no-tmux
           push: ${{ github.event_name != 'pull_request' }}
           tags: |

diff --git a/.github/workflows/multi-gpu-e2e.yml b/.github/workflows/multi-gpu-e2e.yml
@@ -4,8 +4,6 @@ on:
   pull_request:
     paths:
       - 'tests/e2e/multigpu/**.py'
-      - 'requirements.txt'
-      - 'setup.py'
       - 'pyproject.toml'
       - '.github/workflows/multi-gpu-e2e.yml'
       - 'src/axolotl/core/trainers/mixins/sequence_parallel.py'
@@ -56,13 +54,17 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: "3.11"
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "latest"
       - name: Install Modal
         run: |
           python -m pip install --upgrade pip
-          pip install modal==1.0.2 jinja2
+          pip install modal==1.0.2 jinja2 protobuf
       - name: Update env vars
         run: |
-          echo "BASE_TAG=main-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}" >> $GITHUB_ENV
+          echo "BASE_TAG=${{ github.ref_name }}-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}}" >> $GITHUB_ENV
@@ -72,4 +74,4 @@ jobs:
           echo "CODECOV_TOKEN=${{ secrets.CODECOV_TOKEN }}" >> $GITHUB_ENV
       - name: Run tests job on Modal
         run: |
-          modal run cicd.multigpu
+          modal run -m cicd.multigpu
diff --git a/.github/workflows/nightlies.yml b/.github/workflows/nightlies.yml
@@ -52,6 +52,8 @@ jobs:
             CUDA=${{ matrix.cuda }}
             PYTORCH_VERSION=${{ matrix.pytorch }}
             AXOLOTL_ARGS=${{ matrix.axolotl_args }}
+            GIT_REF=${{ github.ref }}
+            GIT_SHA=${{ github.sha }}
           file: ./docker/Dockerfile
           push: ${{ github.event_name != 'pull_request' }}
           tags: |
@@ -102,6 +104,8 @@ jobs:
           build-args: |
             BASE_TAG=${{ github.ref_name }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
             CUDA=${{ matrix.cuda }}
+            GIT_REF=${{ github.ref }}
+            GIT_SHA=${{ github.sha }}
           file: ./docker/Dockerfile-cloud
           push: ${{ github.event_name != 'pull_request' }}
           tags: |

diff --git a/.github/workflows/precommit-autoupdate.yml b/.github/workflows/precommit-autoupdate.yml
@@ -18,10 +18,15 @@ jobs:
         with:
           python-version: '3.11'
 
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "latest"
+
       - name: Update pre-commit hooks
         id: update
         run: |
-          pip install pre-commit
+          uv pip install --system pre-commit
           pre-commit autoupdate
           if [[ -n $(git status --porcelain) ]]; then
             echo "changes=true" >> $GITHUB_OUTPUT

diff --git a/.github/workflows/preview-docs.yml b/.github/workflows/preview-docs.yml
@@ -40,10 +40,15 @@ jobs:
         with:
           python-version: '3.11'
 
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "latest"
+
       - name: Install dependencies
         run: |
-          python3 -m pip install jupyter quartodoc
-          python3 -m pip install -e .
+          uv pip install --system jupyter quartodoc
+          uv pip install --system -e .
 
       - name: Build autodoc
         run: quartodoc build

diff --git a/.github/workflows/pypi.yml b/.github/workflows/pypi.yml
@@ -38,23 +38,24 @@ jobs:
         with:
           python-version: "3.11"
 
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "latest"
+
       - name: Install dependencies
         run: |
-          pip3 install wheel packaging==23.2
-          pip3 install --no-build-isolation -e .
-          pip3 install -r requirements-dev.txt -r requirements-tests.txt
+          uv pip install --system wheel packaging==23.2
+          uv pip install --system --no-build-isolation -e ".[dev]"
 
       - name: Extract tag name
         id: tag
-        run: echo ::set-output name=TAG_NAME::$(echo $GITHUB_REF | cut -d / -f 3)
-
-      - name: Update version in setup.py
-        run: |
-          sed -i -E 's/version="([0-9.]+)",/version="${{ steps.tag.outputs.TAG_NAME }}",/g' setup.py
+        run: echo "TAG_NAME=$(echo "$GITHUB_REF" | cut -d / -f 3)" >> "$GITHUB_OUTPUT"
 
-      - name: Build a source dist
+      - name: Build package
         run: |
-          python setup.py sdist
+          uv pip install --system build
+          python -m build
 
       - name: Publish package distributions to PyPI
         uses: pypa/gh-action-pypi-publish@release/v1
diff --git a/.github/workflows/tests-nightly.yml b/.github/workflows/tests-nightly.yml
@@ -13,7 +13,6 @@ jobs:
       - uses: actions/setup-python@v5
         with:
           python-version: "3.11"
-          cache: 'pip' # caching pip dependencies
       - uses: pre-commit/[email protected]
         env:
           SKIP: no-commit-to-branch
@@ -43,32 +42,30 @@ 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==23.2 setuptools==75.8.0 wheel
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "latest"
 
       - name: Install PyTorch
         run: |
-          pip3 install torch==${{ matrix.pytorch_version }} torchvision
+          uv pip install --system torch==${{ matrix.pytorch_version }} torchvision
 
-      - name: Update requirements.txt
+      - name: Update pyproject.toml for nightly builds
         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
+          sed -i 's#"transformers==.*"#"transformers @ git+https://github.com/huggingface/transformers.git@main"#' pyproject.toml
+          sed -i 's#"peft==.*"#"peft @ git+https://github.com/huggingface/peft.git@main"#' pyproject.toml
+          sed -i 's#"accelerate==.*"#"accelerate @ git+https://github.com/huggingface/accelerate.git@main"#' pyproject.toml
+          sed -i 's#"trl==.*"#"trl @ git+https://github.com/huggingface/trl.git@main"#' pyproject.toml
+          sed -i 's#"datasets==.*"#"datasets @ git+https://github.com/huggingface/datasets.git@main"#' pyproject.toml
 
       - name: Install dependencies
         run: |
-          pip3 show torch
-          pip3 install --no-build-isolation -U -e .
+          uv pip show --system torch
+          uv pip install --system --no-build-isolation -e ".[dev]"
           python scripts/unsloth_install.py | sh
           python scripts/cutcrossentropy_install.py | sh
-          pip3 install -r requirements-dev.txt -r requirements-tests.txt
 
       - name: Make sure PyTorch version wasn't clobbered
         run: |
@@ -84,9 +81,6 @@ 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'
@@ -120,13 +114,16 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: "3.11"
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "latest"
       - name: Install Modal
         run: |
-          python -m pip install --upgrade pip
-          pip install modal==1.0.2 jinja2
+          uv pip install --system modal==1.0.2 jinja2
       - name: Update env vars
         run: |
-          echo "BASE_TAG=main-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}" >> $GITHUB_ENV
+          echo "BASE_TAG=main-base-uv-py${{ 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}}" >> $GITHUB_ENV
@@ -136,7 +133,7 @@ jobs:
           echo "CODECOV_TOKEN=${{ secrets.CODECOV_TOKEN }}" >> $GITHUB_ENV
       - name: Run tests job on Modal
         run: |
-          modal run cicd.e2e_tests
+          modal run -m cicd.e2e_tests
   docker-e2e-multigpu-tests:
     if: github.repository_owner == 'axolotl-ai-cloud'
     # this job needs to be run on self-hosted GPU runners...
@@ -162,13 +159,16 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: "3.11"
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "latest"
       - name: Install Modal
         run: |
-          python -m pip install --upgrade pip
-          pip install modal==1.0.2 jinja2
+          uv pip install --system modal==1.0.2 jinja2
       - name: Update env vars
         run: |
-          echo "BASE_TAG=main-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}" >> $GITHUB_ENV
+          echo "BASE_TAG=main-base-uv-py${{ 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