add uv tooling for e2e gpu tests (#2750)

* add uv tooling for e2e gpu tests

* fixes from PR feedback

* simplify check

* fix env var

* make sure to use uv for other install

* use raw_dockerfile_image

* Fix import

* fix args to experimental dockerfile image call

* use updated modal versions

.github/workflows/tests.yml

@@ -44,98 +44,6 @@ jobs:
         env:
           SKIP: no-commit-to-branch
 
-#  preload-cache:
-#    name: Preload HF cache
-#    runs-on: ubuntu-latest
-#    strategy:
-#      fail-fast: false
-#      matrix:
-#        python_version: ["3.11"]
-#        pytorch_version: ["2.6.0"]
-#    timeout-minutes: 20
-#
-#    env:
-#      AXOLOTL_IS_CI_CACHE_PRELOAD: "1"
-#
-#    steps:
-#      - name: Check out repository code
-#        uses: actions/checkout@v4
-#
-#      - name: Restore HF cache
-#        id: hf-cache-restore
-#        uses: actions/cache/restore@v4
-#        with:
-#          path: |
-#            /home/runner/.cache/huggingface/hub/datasets--*
-#            /home/runner/.cache/huggingface/hub/models--*
-#          key: ${{ runner.os }}-hf-hub-cache-v2
-#
-#      - name: Restore Cache from S3
-#        id: hf-cache-restore-s3
-#        run: |
-#          mkdir -p /home/runner/.cache/huggingface/hub
-#          curl -L https://d1dttdx32dkk5p.cloudfront.net/hf-cache.tar.zst | tar -xf - -C /home/runner/.cache/huggingface/hub/  --use-compress-program unzstd
-#
-#      - name: Setup Python
-#        uses: actions/setup-python@v5
-#        with:
-#          python-version: ${{ matrix.python_version }}
-#          cache: 'pip' # caching pip dependencies
-#
-#      - name: upgrade pip
-#        run: |
-#          pip3 install --upgrade pip
-#          pip3 install --upgrade packaging==23.2 setuptools==75.8.0 wheel
-#
-#      - name: Install PyTorch
-#        run: |
-#          pip3 install torch==${{ matrix.pytorch_version }}
-#
-#      - 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
-#
-#      - name: Make sure PyTorch version wasn't clobbered
-#        run: |
-#          python -c "import torch; assert '${{ matrix.pytorch_version }}' in torch.__version__"
-#
-#      - name: Ensure axolotl CLI was installed
-#        run: |
-#          axolotl --help
-#
-#      - name: Pre-Download dataset fixture
-#        run: |
-#          huggingface-cli download --repo-type=dataset axolotl-ai-internal/axolotl-oss-dataset-fixtures
-#
-#      - name: Run tests
-#        run: |
-#          pytest -v tests/conftest.py
-#
-#      - name: Upload coverage to Codecov
-#        uses: codecov/codecov-action@v5
-#        with:
-#          token: ${{ secrets.CODECOV_TOKEN }}
-#          files: ./coverage.xml
-#          flags: unittests,pytorch-${{ matrix.pytorch_version }}
-#          fail_ci_if_error: false
-#
-#      - name: cleanup pip cache
-#        run: |
-#          find "$(pip cache dir)/http-v2" -type f -mtime +14 -exec rm {} \;
-#
-#      - name: Save HF cache
-#        id: hf-cache
-#        uses: actions/cache/save@v4
-#        with:
-#          path: |
-#            /home/runner/.cache/huggingface/hub/datasets--*
-#            /home/runner/.cache/huggingface/hub/models--*
-#          key: ${{ steps.hf-cache-restore.outputs.cache-primary-key }}
-
   pytest:
     name: PyTest
     runs-on: ubuntu-latest
@@ -151,15 +59,6 @@ jobs:
       - name: Check out repository code
         uses: actions/checkout@v4
 
-#      - name: Restore HF cache
-#        id: hf-cache-restore
-#        uses: actions/cache/restore@v4
-#        with:
-#          path: |
-#            /home/runner/.cache/huggingface/hub/datasets--*
-#            /home/runner/.cache/huggingface/hub/models--*
-#          key: ${{ runner.os }}-hf-hub-cache-v2
-
       - name: Restore Cache from S3
         id: hf-cache-restore-s3
         run: |
@@ -222,7 +121,6 @@ jobs:
   pytest-sdist:
     name: PyTest from Source Dist
     runs-on: ubuntu-latest
-#    needs: [preload-cache]
     strategy:
       fail-fast: false
       matrix:
@@ -234,15 +132,6 @@ jobs:
       - name: Check out repository code
         uses: actions/checkout@v4
 
-#      - name: Restore HF cache
-#        id: hf-cache-restore
-#        uses: actions/cache/restore@v4
-#        with:
-#          path: |
-#            /home/runner/.cache/huggingface/hub/datasets--*
-#            /home/runner/.cache/huggingface/hub/models--*
-#          key: ${{ runner.os }}-hf-hub-cache-v2
-
       - name: Restore Cache from S3
         id: hf-cache-restore-s3
         run: |
@@ -312,6 +201,13 @@ jobs:
             pytorch: 2.6.0
             num_gpus: 1
             axolotl_extras: vllm
+          - cuda: 126
+            cuda_version: 12.6.3
+            python_version: "3.11"
+            pytorch: 2.6.0
+            num_gpus: 1
+            axolotl_extras:
+            dockerfile: "Dockerfile-uv.jinja"
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -333,6 +229,7 @@ jobs:
           echo "MODAL_IMAGE_BUILDER_VERSION=2024.10" >> $GITHUB_ENV
           echo "N_GPUS=${{ matrix.num_gpus }}" >> $GITHUB_ENV
           echo "CODECOV_TOKEN=${{ secrets.CODECOV_TOKEN }}" >> $GITHUB_ENV
+          echo "E2E_DOCKERFILE=${{ matrix.dockerfile || 'Dockerfile.jinja'}}" >> $GITHUB_ENV
       - name: Run tests job on Modal
         run: |
           modal run cicd.e2e_tests
@@ -395,6 +292,7 @@ jobs:
           echo "MODAL_IMAGE_BUILDER_VERSION=2024.10" >> $GITHUB_ENV
           echo "N_GPUS=${{ matrix.num_gpus }}" >> $GITHUB_ENV
           echo "CODECOV_TOKEN=${{ secrets.CODECOV_TOKEN }}" >> $GITHUB_ENV
+          echo "E2E_DOCKERFILE=${{ matrix.dockerfile || 'Dockerfile.jinja'}}" >> $GITHUB_ENV
       - name: Run tests job on Modal
         run: |
           modal run cicd.e2e_tests

cicd/Dockerfile-uv.jinja

@@ -0,0 +1,52 @@
+FROM axolotlai/axolotl-base-uv:{{ BASE_TAG }}
+
+ENV TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6 9.0+PTX"
+ENV AXOLOTL_EXTRAS="{{ AXOLOTL_EXTRAS }}"
+ENV AXOLOTL_ARGS="{{ AXOLOTL_ARGS }}"
+ENV CUDA="{{ CUDA }}"
+ENV PYTORCH_VERSION="{{ PYTORCH_VERSION }}"
+ENV GITHUB_REF="{{ GITHUB_REF }}"
+ENV GITHUB_SHA="{{ GITHUB_SHA }}"
+ENV NIGHTLY_BUILD="{{ NIGHTLY_BUILD }}"
+ENV HF_HOME="{{ HF_HOME }}"
+
+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/axolotl-ai-cloud/axolotl.git
+
+WORKDIR /workspace/axolotl
+
+RUN git fetch origin +$GITHUB_REF && \
+    git checkout FETCH_HEAD
+
+# If AXOLOTL_EXTRAS is set, append it in brackets
+RUN if [ "$NIGHTLY_BUILD" = "true" ] ; then \
+        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; \
+    fi
+
+RUN uv pip install packaging==23.2 setuptools==75.8.0
+RUN if [ "$AXOLOTL_EXTRAS" != "" ] ; then \
+        uv pip install --no-build-isolation -e .[deepspeed,flash-attn,ring-flash-attn,optimizers,ray,$AXOLOTL_EXTRAS] $AXOLOTL_ARGS; \
+    else \
+        uv pip install --no-build-isolation -e .[deepspeed,flash-attn,ring-flash-attn,optimizers,ray] $AXOLOTL_ARGS; \
+    fi
+
+RUN python scripts/unsloth_install.py --uv | sh
+RUN python scripts/cutcrossentropy_install.py --uv | sh
+
+# So we can test the Docker image
+RUN uv pip install -r requirements-dev.txt -r requirements-tests.txt
+
+# 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

cicd/multigpu.py

@@ -55,7 +55,7 @@ VOLUME_CONFIG = {
 }
 
 N_GPUS = int(os.environ.get("N_GPUS", 2))
-GPU_CONFIG = modal.gpu.H100(count=N_GPUS)
+GPU_CONFIG = f"H100:{N_GPUS}"
 
 
 def run_cmd(cmd: str, run_folder: str):

cicd/single_gpu.py

@@ -8,8 +8,9 @@ import tempfile
 
 import jinja2
 import modal
+import modal.experimental
 from jinja2 import select_autoescape
-from modal import App, Image
+from modal import App
 
 cicd_path = pathlib.Path(__file__).parent.resolve()
 
@@ -17,7 +18,8 @@ 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")
+dockerfile = os.environ.get("E2E_DOCKERFILE", "Dockerfile.jinja")
+df_template = template_env.get_template(dockerfile)
 
 df_args = {
     "AXOLOTL_EXTRAS": os.environ.get("AXOLOTL_EXTRAS", ""),
@@ -38,11 +40,11 @@ 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(
+cicd_image = modal.experimental.raw_dockerfile_image(
     pathlib.Path(temp_dir) / "Dockerfile",
-    context_mount=None,
+    # context_mount=None,
     force_build=True,
-    gpu="A10G",
+    # gpu="A10G",
 ).env(df_args)
 
 app = App("Axolotl CI/CD", secrets=[])
@@ -55,7 +57,7 @@ VOLUME_CONFIG = {
 }
 
 N_GPUS = int(os.environ.get("N_GPUS", 1))
-GPU_CONFIG = modal.gpu.L40S(count=N_GPUS)
+GPU_CONFIG = f"L40S:{N_GPUS}"
 
 
 def run_cmd(cmd: str, run_folder: str):

scripts/cutcrossentropy_install.py

@@ -9,6 +9,8 @@ except ImportError as exc:
     raise ImportError("Install torch via `pip install torch`") from exc
 from packaging.version import Version as V
 
+USE_UV = "--uv" in sys.argv[1:]
+
 v = V(torch.__version__)
 
 # no cut-cross-entropy support for torch < 2.4.0
@@ -23,7 +25,9 @@ if cce_spec:
     if not importlib.util.find_spec("cut_cross_entropy.transformers"):
         UNINSTALL_PREFIX = "pip uninstall -y cut-cross-entropy && "
 
+UV_PREFIX = "uv " if USE_UV else ""
+
 print(
     UNINSTALL_PREFIX
-    + 'pip install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@a1174ca"'
+    + f'{UV_PREFIX}pip install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@a1174ca"'
 )

scripts/unsloth_install.py

@@ -1,11 +1,15 @@
 # noqa
 # pylint: skip-file
+import sys
+
 try:
     import torch
 except ImportError:
     raise ImportError("Install torch via `pip install torch`")
 from packaging.version import Version as V
 
+use_uv = "--uv" in sys.argv[1:]
+
 v = V(torch.__version__)
 cuda = str(torch.version.cuda)
 try:
@@ -31,6 +35,7 @@ elif v < V("2.6.0"):
 else:
     raise RuntimeError(f"Torch = {v} too new!")
 x = x.format(cuda.replace(".", ""), "-ampere" if is_ampere else "")
+uv_prefix = "uv " if use_uv else ""
 print(
-    f'pip install unsloth-zoo==2024.12.1 && pip install --no-deps "unsloth[{x}]==2024.12.4"'
+    f'{uv_prefix}pip install unsloth-zoo==2024.12.1 && {uv_prefix}pip install --no-deps "unsloth[{x}]==2024.12.4"'
 )