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
2026-04-21 21:16:03 +07:00
parent 323da791eb
commit 9de5b76336
58 changed files with 496 additions and 1520 deletions
--- a/.github/CONTRIBUTING.md
+++ b/.github/CONTRIBUTING.md
@@ -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
--- 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"
--- a/.github/workflows/multi-gpu-e2e.yml
+++ b/.github/workflows/multi-gpu-e2e.yml
@@ -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 }}
--- a/.github/workflows/pypi.yml
+++ b/.github/workflows/pypi.yml
@@ -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
--- a/.github/workflows/tests-nightly.yml
+++ b/.github/workflows/tests-nightly.yml
@@ -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:
--- a/.github/workflows/tests.yml
+++ b/.github/workflows/tests.yml
@@ -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 }}
--- a/MANIFEST.in
+++ b/MANIFEST.in
@@ -1,7 +1,6 @@
-include requirements.txt
 include README.md
 include LICENSE
-include src/setuptools_axolotl_dynamic_dependencies.py
+include VERSION
 include src/axolotl/utils/chat_templates/templates/*.jinja
 include AGENTS.md
 recursive-include docs/agents *.md
--- a/README.md
+++ b/README.md
@@ -95,14 +95,11 @@ Features:

 ### Installation

-#### Using uv (recommended)
-
 ```bash
-# install uv if you don't already have it installed
+# install uv if you don't already have it installed (restart shell after)
 curl -LsSf https://astral.sh/uv/install.sh | sh
-source $HOME/.local/bin/env

-# CUDA 12.8.1 tends to have better package compatibility
+# change depending on system
 export UV_TORCH_BACKEND=cu128

 # create a new virtual environment
@@ -112,23 +109,6 @@ source .venv/bin/activate
 uv pip install torch==2.10.0 torchvision
 uv pip install --no-build-isolation axolotl[deepspeed]

-# recommended - install cut-cross-entropy
-uv pip install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@main"
-
-# (optional) - prefetch flash-attn2 and causal-conv1d kernels
-uv run --python 3.12 python -c "from kernels import get_kernel; get_kernel('kernels-community/flash-attn2'); get_kernel('kernels-community/causal-conv1d')"
-
-# Download example axolotl configs, deepspeed configs
-axolotl fetch examples
-axolotl fetch deepspeed_configs  # OPTIONAL
-```
-
-#### Using pip
-
-```bash
-pip3 install -U packaging==26.0 setuptools==75.8.0 wheel ninja
-pip3 install --no-build-isolation axolotl[flash-attn,deepspeed]
-
 # Download example axolotl configs, deepspeed configs
 axolotl fetch examples
 axolotl fetch deepspeed_configs  # OPTIONAL
@@ -138,7 +118,7 @@ axolotl fetch deepspeed_configs  # OPTIONAL

 Installing with Docker can be less error prone than installing in your own environment.
 ```bash
-docker run --gpus '"all"' --rm -it axolotlai/axolotl:main-latest
+docker run --gpus '"all"' --ipc=host --rm -it axolotlai/axolotl:main-latest
 ```

 Other installation approaches are described [here](https://docs.axolotl.ai/docs/installation.html).
--- a/_quarto.yml
+++ b/_quarto.yml
@@ -134,7 +134,6 @@ quartodoc:
        - monkeypatch.stablelm_attn_hijack_flash
        - monkeypatch.trainer_fsdp_optim
        - monkeypatch.transformers_fa_utils
-        - monkeypatch.unsloth_
        - monkeypatch.data.batch_dataset_fetcher
        - monkeypatch.mixtral
        - monkeypatch.gradient_checkpointing.offload_cpu
@@ -327,7 +326,6 @@ website:
        - section: "Advanced Features"
          contents:
            - docs/fsdp_qlora.qmd
-            - docs/unsloth.qmd
            - docs/torchao.qmd
            - docs/custom_integrations.qmd
            - docs/sequence_parallelism.qmd
--- a/cicd/Dockerfile-uv.jinja
+++ b/cicd/Dockerfile-uv.jinja
@@ -22,15 +22,6 @@ WORKDIR /workspace/axolotl
 RUN git fetch origin +$GITHUB_REF && \
    git checkout FETCH_HEAD

-# If AXOLOTL_EXTRAS is set, append it in brackets
-RUN if [ "$NIGHTLY_BUILD" = "true" ] ; then \
-        sed -i 's#^transformers.*#transformers @ git+https://github.com/huggingface/transformers.git@main#' requirements.txt; \
-        sed -i 's#^peft.*#peft @ git+https://github.com/huggingface/peft.git@main#' requirements.txt; \
-        sed -i 's#^accelerate.*#accelerate @ git+https://github.com/huggingface/accelerate.git@main#' requirements.txt; \
-        sed -i 's#^trl.*#trl @ git+https://github.com/huggingface/trl.git@main#' requirements.txt; \
-        sed -i 's#^datasets.*#datasets @ git+https://github.com/huggingface/datasets.git@main#' requirements.txt; \
-    fi
-
 RUN uv pip install packaging==26.0 setuptools==78.1.1
 RUN uv pip install torchvision
 RUN uv pip uninstall causal_conv1d
@@ -40,11 +31,21 @@ RUN if [ "$AXOLOTL_EXTRAS" != "" ] ; then \
        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
+# Override with nightly HF packages for nightly builds
+RUN if [ "$NIGHTLY_BUILD" = "true" ] ; then \
+        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"; \
+    fi
+
 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
+RUN 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

 # fix so that git fetch/pull from remote works
 RUN git config remote.origin.fetch "+refs/heads/*:refs/remotes/origin/*" && \
--- a/cicd/Dockerfile.jinja
+++ b/cicd/Dockerfile.jinja
@@ -1,54 +0,0 @@
-FROM axolotlai/axolotl-base:{{ BASE_TAG }}
-
-ENV TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6 8.7 8.9 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 }}"
-ENV AXOLOTL_DATASET_NUM_PROC="8"
-
-RUN apt-get update && \
-    apt-get install -y --allow-change-held-packages vim curl nano zstd libnccl2 libnccl-dev ibverbs-providers ibverbs-utils infiniband-diags librdmacm-dev librdmacm1 rdmacm-utils slurm-wlm
-
-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 pip install packaging==26.0 setuptools==78.1.1 psutil
-RUN pip uninstall -y causal_conv1d
-RUN if [ "$AXOLOTL_EXTRAS" != "" ] ; then \
-        pip install --no-build-isolation -e .[deepspeed,flash-attn,ring-flash-attn,optimizers,ray,$AXOLOTL_EXTRAS] $AXOLOTL_ARGS; \
-    else \
-        pip install --no-build-isolation -e .[deepspeed,flash-attn,ring-flash-attn,optimizers,ray] $AXOLOTL_ARGS; \
-    fi
-
-RUN python scripts/unsloth_install.py | sh
-RUN python scripts/cutcrossentropy_install.py | sh
-
-# So we can test the Docker image
-RUN 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
--- a/cicd/cicd.sh
+++ b/cicd/cicd.sh
@@ -1,7 +1,7 @@
 #!/bin/bash
 set -e

-python -c "import torch; assert '$PYTORCH_VERSION' in torch.__version__"
+python -c "import torch; assert '$PYTORCH_VERSION' in torch.__version__, f'Expected torch $PYTORCH_VERSION but got {torch.__version__}'"

 set -o pipefail
 for i in 1 2 3; do
--- a/cicd/multigpu.py
+++ b/cicd/multigpu.py
@@ -17,7 +17,7 @@ template_loader = jinja2.FileSystemLoader(searchpath=cicd_path)
 template_env = jinja2.Environment(
    loader=template_loader, autoescape=select_autoescape()
 )
-dockerfile = os.environ.get("E2E_DOCKERFILE", "Dockerfile.jinja")
+dockerfile = os.environ.get("E2E_DOCKERFILE", "Dockerfile-uv.jinja")
 df_template = template_env.get_template(dockerfile)

 df_args = {
--- a/cicd/single_gpu.py
+++ b/cicd/single_gpu.py
@@ -16,7 +16,7 @@ template_loader = jinja2.FileSystemLoader(searchpath=cicd_path)
 template_env = jinja2.Environment(
    loader=template_loader, autoescape=select_autoescape()
 )
-dockerfile = os.environ.get("E2E_DOCKERFILE", "Dockerfile.jinja")
+dockerfile = os.environ.get("E2E_DOCKERFILE", "Dockerfile-uv.jinja")
 df_template = template_env.get_template(dockerfile)

 df_args = {
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@@ -32,7 +32,7 @@ RUN if [ "$TARGETARCH" = "arm64" ]; then \
        pip install --no-build-isolation -e .[$BASE_EXTRAS,$AXOLOTL_EXTRAS] $AXOLOTL_ARGS; \
    else \
        pip install --no-build-isolation -e .[$BASE_EXTRAS] $AXOLOTL_ARGS; \
-    fi && \    python scripts/unsloth_install.py | sh && \
+    fi && \
    python scripts/cutcrossentropy_install.py | sh && \
    pip install pytest && \
    pip cache purge
--- a/docker/Dockerfile-uv
+++ b/docker/Dockerfile-uv
@@ -33,7 +33,6 @@ RUN if [ "$TARGETARCH" = "arm64" ]; then \
    else \
        uv pip install --no-build-isolation -e .[$BASE_EXTRAS] $AXOLOTL_ARGS; \
    fi && \
-    python scripts/unsloth_install.py --uv | sh && \
    python scripts/cutcrossentropy_install.py --uv | sh && \
    uv pip install pytest && \
    uv cache clean
--- a/docs/debugging.qmd
+++ b/docs/debugging.qmd
@@ -76,8 +76,9 @@ datasets:
 Make sure you have an [editable install](https://setuptools.pypa.io/en/latest/userguide/development_mode.html) of Axolotl, which ensures that changes you make to the code are reflected at runtime.  Run the following commands from the root of this project:

 ```bash
-pip3 install packaging
-pip3 install --no-build-isolation -e '.[flash-attn,deepspeed]'
+export UV_TORCH_BACKEND=cu128  # or cu130
+uv sync --extra flash-attn --extra deepspeed --group dev --group test
+source .venv/bin/activate
 ```

 #### Remote Hosts
@@ -208,17 +209,17 @@ cd axolotl
 Next, run the desired docker image and mount the current directory. Below is a docker command you can run to do this:[^2]

 ```bash
-docker run --privileged --gpus '"all"' --shm-size 10g --rm -it --name axolotl --ipc=host --ulimit memlock=-1 --ulimit stack=67108864 --mount type=bind,src="${PWD}",target=/workspace/axolotl -v ${HOME}/.cache/huggingface:/root/.cache/huggingface axolotlai/axolotl:main-py3.10-cu118-2.0.1
+docker run --privileged --gpus '"all"' --shm-size 10g --rm -it --name axolotl --ipc=host --ulimit memlock=-1 --ulimit stack=67108864 --mount type=bind,src="${PWD}",target=/workspace/axolotl -v ${HOME}/.cache/huggingface:/root/.cache/huggingface axolotlai/axolotl-uv:main-latest
 ```

 >[!Tip]
 > To understand which containers are available, see the [Docker section of the README](../README.md#docker) and the [DockerHub repo](https://hub.docker.com/r/axolotlai/axolotl/tags).  For details of how the Docker containers are built, see axolotl's [Docker CI builds](../.github/workflows/main.yml).

-You will now be in the container.  Next, perform an editable install of Axolotl:
+You will now be in the container.  Next, install Axolotl with dev dependencies:

 ```bash
-pip3 install packaging
-pip3 install --no-build-isolation -e '.[flash-attn,deepspeed]'
+uv sync --extra flash-attn --extra deepspeed --group dev --group test
+source .venv/bin/activate
 ```

 ### Attach To Container
--- a/docs/docker.qmd
+++ b/docs/docker.qmd
@@ -6,23 +6,30 @@ format:
    toc-depth: 4
 ---

-This section describes the different Docker images that are released by AxolotlAI at [Docker Hub](https://hub.docker.com/u/axolotlai).
+This section describes the different Docker images that are released by AxolotlAI at
+[Docker Hub](https://hub.docker.com/u/axolotlai).

 ::: {.callout-important}
-For Blackwell GPUs, please use the tags with PyTorch 2.7.1 and CUDA 12.8.
+For Blackwell GPUs, please use the tags with PyTorch 2.9.1 and CUDA 12.8.
+:::
+
+::: {.callout-tip}
+Each image below is available in a **uv variant** that uses [uv](https://docs.astral.sh/uv/) with
+a relocatable venv (`/workspace/axolotl-venv`) instead of Miniconda + pip. Append `-uv` to the image name
+(e.g. `axolotlai/axolotl-base-uv`). Tags follow the same format. We recommend the uv images for new deployments.
 :::

 ## Base

-The base image is the most minimal image that can install Axolotl. It is based on the `nvidia/cuda` image. It includes python, torch, git, git-lfs, awscli, pydantic, and more.
+The base image is the most minimal image that can install Axolotl. It is based on the `nvidia/cuda` image.
+It includes python, torch, git, git-lfs, awscli, pydantic, and more.

 #### Image

-```
-axolotlai/axolotl-base
-```
-
-Link: [Docker Hub](https://hub.docker.com/r/axolotlai/axolotl-base)
+| Variant | Image | Docker Hub |
+|---------|-------|------------|
+| pip | `axolotlai/axolotl-base` | [Link](https://hub.docker.com/r/axolotlai/axolotl-base) |
+| uv | `axolotlai/axolotl-base-uv` | [Link](https://hub.docker.com/r/axolotlai/axolotl-base-uv) |

 #### Tags format

@@ -32,8 +39,10 @@ main-base-py{python_version}-cu{cuda_version}-{pytorch_version}

 Tags examples:

- `main-base-py3.11-cu128-2.8.0`
 - `main-base-py3.11-cu128-2.9.1`
+- `main-base-py3.12-cu128-2.10.0`
+- `main-base-py3.12-cu130-2.9.1`
+- `main-base-py3.12-cu130-2.10.0`

 ## Main

@@ -41,11 +50,10 @@ The main image is the image that is used to run Axolotl. It is based on the `axo

 #### Image

-```
-axolotlai/axolotl
-```
-
-Link: [Docker Hub](https://hub.docker.com/r/axolotlai/axolotl)
+| Variant | Image | Docker Hub |
+|---------|-------|------------|
+| pip | `axolotlai/axolotl` | [Link](https://hub.docker.com/r/axolotlai/axolotl) |
+| uv | `axolotlai/axolotl-uv` | [Link](https://hub.docker.com/r/axolotlai/axolotl-uv) |

 #### Tags format {#sec-main-tags}

@@ -53,7 +61,7 @@ Link: [Docker Hub](https://hub.docker.com/r/axolotlai/axolotl)
 # on push to main
 main-py{python_version}-cu{cuda_version}-{pytorch_version}

-# latest main (currently torch 2.6.0, python 3.11, cuda 12.4)
+# latest main (currently torch 2.9.1, python 3.11, cuda 12.8)
 main-latest

 # nightly build
@@ -71,11 +79,12 @@ There may be some extra tags appended to the image, like `-vllm` which installs

 Tags examples:

- `main-py3.11-cu128-2.8.0`
 - `main-py3.11-cu128-2.9.1`
+- `main-py3.12-cu128-2.10.0`
+- `main-py3.12-cu130-2.9.1`
+- `main-py3.12-cu130-2.10.0`
 - `main-latest`
- `main-20250303-py3.11-cu124-2.6.0`
- `main-20250303-py3.11-cu126-2.6.0`
+- `main-20260315-py3.11-cu128-2.9.1`
 - `0.12.0`

 ## Cloud
@@ -90,11 +99,10 @@ Jupyter lab is run by default. Set `JUPYTER_DISABLE=1` in the environment variab

 #### Image

-```
-axolotlai/axolotl-cloud
-```
-
-Link: [Docker Hub](https://hub.docker.com/r/axolotlai/axolotl-cloud)
+| Variant | Image | Docker Hub |
+|---------|-------|------------|
+| pip | `axolotlai/axolotl-cloud` | [Link](https://hub.docker.com/r/axolotlai/axolotl-cloud) |
+| uv | `axolotlai/axolotl-cloud-uv` | [Link](https://hub.docker.com/r/axolotlai/axolotl-cloud-uv) |

 #### Tags format

--- a/docs/installation.qmd
+++ b/docs/installation.qmd
@@ -15,64 +15,30 @@ This guide covers all the ways you can install and set up Axolotl for your envir

 - NVIDIA GPU (Ampere architecture or newer for `bf16` and Flash Attention) or AMD GPU
 - Python ≥3.11
- PyTorch ≥2.6.0
+- PyTorch ≥2.9.0

-## Installation Methods {#sec-installation-methods}
-
-::: {.callout-important}
-Please make sure to have Pytorch installed before installing Axolotl in your local environment.
-
-Follow the instructions at: [https://pytorch.org/get-started/locally/](https://pytorch.org/get-started/locally/)
-:::
+## Installation {#sec-installation}

 ::: {.callout-important}
 For Blackwell GPUs, please use Pytorch 2.9.1 and CUDA 12.8.
 :::

-### PyPI Installation (Recommended) {#sec-pypi}
+### Quick Install {#sec-uv}

-```{.bash}
-pip3 install -U packaging setuptools wheel ninja
-pip3 install --no-build-isolation axolotl[flash-attn,deepspeed]
-```
+Axolotl uses [uv](https://docs.astral.sh/uv/) as its package manager. uv is a fast, reliable Python package installer and resolver built in Rust.

-We use `--no-build-isolation` in order to detect the installed PyTorch version (if
-installed) in order not to clobber it, and so that we set the correct version of
-dependencies that are specific to the PyTorch version or other installed
-co-dependencies.
-
-### uv Installation {#sec-uv}
-
-uv is a fast, reliable Python package installer and resolver built in Rust. It offers significant performance improvements over pip and provides better dependency resolution, making it an excellent choice for complex environments.
-
-Install uv if not already installed
+Install uv if not already installed:
 ```{.bash}
 curl -LsSf https://astral.sh/uv/install.sh | sh
 source $HOME/.local/bin/env
 ```

-Choose your CUDA version to use with PyTorch; e.g. `cu124`, `cu126`, `cu128`,
-then create the venv and activate
+Choose your CUDA version (e.g. `cu128`, `cu130`), create a venv, and install:
 ```{.bash}
-export UV_TORCH_BACKEND=cu126
+export UV_TORCH_BACKEND=cu128  # or cu130
 uv venv --no-project --relocatable
 source .venv/bin/activate
-```
-
-Install PyTorch
- PyTorch 2.6.0 recommended
-```{.bash}
-uv pip install packaging setuptools wheel
-uv pip install torch==2.6.0
-uv pip install awscli pydantic
-```
-
-Install axolotl from PyPi
-```{.bash}
-uv pip install --no-build-isolation axolotl[deepspeed,flash-attn]
-
-# optionally install with vLLM if you're using torch==2.6.0 and want to train w/ GRPO
-uv pip install --no-build-isolation axolotl[deepspeed,flash-attn,vllm]
+uv pip install --no-build-isolation axolotl[flash-attn,deepspeed]
 ```

 ### Edge/Development Build {#sec-edge-build}
@@ -82,14 +48,17 @@ For the latest features between releases:
 ```{.bash}
 git clone https://github.com/axolotl-ai-cloud/axolotl.git
 cd axolotl
-pip3 install -U packaging setuptools wheel ninja
-pip3 install --no-build-isolation -e '.[flash-attn,deepspeed]'
+export UV_TORCH_BACKEND=cu128  # or cu130
+uv sync --extra flash-attn --extra deepspeed
+source .venv/bin/activate
 ```

+`uv sync` creates a `.venv`, installs exact pinned versions from `uv.lock`, and sets up an editable install automatically.
+
 ### Docker {#sec-docker}

 ```{.bash}
-docker run --gpus '"all"' --rm -it axolotlai/axolotl:main-latest
+docker run --gpus '"all"' --rm -it --ipc=host axolotlai/axolotl-uv:main-latest
 ```

 For development with Docker:
@@ -106,12 +75,12 @@ docker run --privileged --gpus '"all"' --shm-size 10g --rm -it \
  --ulimit memlock=-1 --ulimit stack=67108864 \
  --mount type=bind,src="${PWD}",target=/workspace/axolotl \
  -v ${HOME}/.cache/huggingface:/root/.cache/huggingface \
-  axolotlai/axolotl:main-latest
+  axolotlai/axolotl-uv:main-latest
 ```
 :::

 ::: {.callout-important}
-For Blackwell GPUs, please use `axolotlai/axolotl:main-py3.11-cu128-2.9.1` or the cloud variant `axolotlai/axolotl-cloud:main-py3.11-cu128-2.9.1`.
+For Blackwell GPUs, please use `axolotlai/axolotl-uv:main-py3.11-cu128-2.9.1` or the cloud variant `axolotlai/axolotl-cloud-uv:main-py3.11-cu128-2.9.1`.
 :::

 Please refer to the [Docker documentation](docker.qmd) for more information on the different Docker images that are available.
@@ -122,7 +91,7 @@ Please refer to the [Docker documentation](docker.qmd) for more information on t

 For providers supporting Docker:

- Use `axolotlai/axolotl-cloud:main-latest`
+- Use `axolotlai/axolotl-cloud-uv:main-latest`
 - Available on:
    - [RunPod](https://runpod.io/gsc?template=v2ickqhz9s&ref=6i7fkpdz)
    - [Vast.ai](https://cloud.vast.ai?ref_id=62897&template_id=bdd4a49fa8bce926defc99471864cace&utm_source=axolotl&utm_medium=partner&utm_campaign=template_launch_july2025&utm_content=docs_link)
@@ -141,7 +110,7 @@ For providers supporting Docker:
 ### macOS {#sec-macos}

 ```{.bash}
-pip3 install --no-build-isolation -e '.'
+uv pip install --no-build-isolation -e '.'
 ```

 See @sec-troubleshooting for Mac-specific issues.
@@ -152,21 +121,44 @@ See @sec-troubleshooting for Mac-specific issues.
 We recommend using WSL2 (Windows Subsystem for Linux) or Docker.
 :::

-## Environment Managers {#sec-env-managers}
+## Migrating from pip to uv {#sec-migrating}

-### Conda/Pip venv {#sec-conda}
+If you have an existing pip-based Axolotl installation, you can migrate to uv:

-1. Install Python ≥3.11
-2. Install PyTorch: https://pytorch.org/get-started/locally/
-3. Install Axolotl:
-   ```{.bash}
-   pip3 install -U packaging setuptools wheel ninja
-   pip3 install --no-build-isolation -e '.[flash-attn,deepspeed]'
-   ```
-4. (Optional) Login to Hugging Face:
-   ```{.bash}
-   hf auth login
-   ```
+```{.bash}
+# Install uv
+curl -LsSf https://astral.sh/uv/install.sh | sh
+source $HOME/.local/bin/env
+
+# Create a fresh venv (recommended for a clean start)
+export UV_TORCH_BACKEND=cu128  # or cu130
+uv venv --no-project --relocatable
+source .venv/bin/activate
+
+# Reinstall axolotl
+uv pip install --no-build-isolation axolotl[flash-attn,deepspeed]
+```
+
+## Using pip (Alternative) {#sec-pip}
+
+If you are unable to install uv, you can still use pip directly.
+
+::: {.callout-important}
+Please make sure to have PyTorch installed before installing Axolotl with pip.
+
+Follow the instructions at: [https://pytorch.org/get-started/locally/](https://pytorch.org/get-started/locally/)
+:::
+
+```{.bash}
+pip3 install -U packaging setuptools wheel ninja
+pip3 install --no-build-isolation axolotl[flash-attn,deepspeed]
+```
+
+For editable/development installs:
+```{.bash}
+pip3 install -U packaging setuptools wheel ninja
+pip3 install --no-build-isolation -e '.[flash-attn,deepspeed]'
+```

 ## Troubleshooting {#sec-troubleshooting}

--- a/docs/unsloth.qmd
+++ b/docs/unsloth.qmd
@@ -1,53 +0,0 @@
---
-title: "Unsloth"
-description: "Hyper-optimized QLoRA finetuning for single GPUs"
---
-
-### Overview
-
-Unsloth provides hand-written optimized kernels for LLM finetuning that slightly improve speed and VRAM over
-standard industry baselines.
-
-::: {.callout-important}
-Due to breaking changes in transformers `v4.48.0`, users will need to downgrade to `<=v4.47.1` to use this patch.
-
-This will later be deprecated in favor of [LoRA Optimizations](lora_optims.qmd).
-:::
-
-
-### Installation
-
-The following will install the correct unsloth and extras from source.
-
-```bash
-python scripts/unsloth_install.py | sh
-```
-
-### Usage
-
-Axolotl exposes a few configuration options to try out unsloth and get most of the performance gains.
-
-Our unsloth integration is currently limited to the following model architectures:
- - llama
-
-These options are specific to LoRA finetuning and cannot be used for multi-GPU finetuning
-```yaml
-unsloth_lora_mlp: true
-unsloth_lora_qkv: true
-unsloth_lora_o: true
-```
-
-These options are composable and can be used with multi-gpu finetuning
-```yaml
-unsloth_cross_entropy_loss: true
-unsloth_rms_norm: true
-unsloth_rope: true
-```
-
-### Limitations
-
- Single GPU only; e.g. no multi-gpu support
- No deepspeed or FSDP support (requires multi-gpu)
- LoRA + QLoRA support only. No full fine tunes or fp8 support.
- Limited model architecture support. Llama, Phi, Gemma, Mistral only
- No MoE support.
--- a/examples/LiquidAI/README.md
+++ b/examples/LiquidAI/README.md
@@ -15,8 +15,7 @@ Thanks to the team at LiquidAI for giving us early access to prepare for these r
    Here is an example of how to install from pip:
    ```bash
    # Ensure you have a compatible version of Pytorch installed
-    pip3 install packaging setuptools wheel ninja
-    pip3 install --no-build-isolation 'axolotl[flash-attn]>=0.12.0'
+    uv pip install --no-build-isolation 'axolotl[flash-attn]>=0.12.0'
    ```

 2.  Run one of the finetuning examples below.
@@ -35,7 +34,7 @@ Thanks to the team at LiquidAI for giving us early access to prepare for these r

    **LFM2-MoE**
    ```bash
-    pip install git+https://github.com/huggingface/transformers.git@0c9a72e4576fe4c84077f066e585129c97bfd4e6
+    uv pip install git+https://github.com/huggingface/transformers.git@0c9a72e4576fe4c84077f066e585129c97bfd4e6

    # LoRA SFT (1x48GB @ 16.2GiB)
    axolotl train examples/LiquidAI/lfm2-8b-a1b-lora.yaml
@@ -45,7 +44,7 @@ Thanks to the team at LiquidAI for giving us early access to prepare for these r

 - **Installation Error**: If you encounter `ImportError: ... undefined symbol ...` or `ModuleNotFoundError: No module named 'causal_conv1d_cuda'`, the `causal-conv1d` package may have been installed incorrectly. Try uninstalling it:
  ```bash
-  pip uninstall -y causal-conv1d
+  uv pip uninstall causal-conv1d
  ```

 - **Dataset Loading**: Read more on how to load your own dataset in our [documentation](https://docs.axolotl.ai/docs/dataset_loading.html).
--- a/examples/apertus/README.md
+++ b/examples/apertus/README.md
@@ -15,8 +15,7 @@ This guide shows how to fine-tune it with Axolotl with multi-turn conversations
 git clone https://github.com/axolotl-ai-cloud/axolotl.git
 cd axolotl

-pip3 install packaging==26.0 setuptools==75.8.0 wheel ninja
-pip3 install --no-build-isolation -e '.[flash-attn]'
+uv pip install --no-build-isolation -e '.[flash-attn]'

 # Install CCE https://docs.axolotl.ai/docs/custom_integrations.html#cut-cross-entropy
 python scripts/cutcrossentropy_install.py | sh
@@ -31,7 +30,7 @@ python scripts/cutcrossentropy_install.py | sh
 # For those using our Docker image, use the below path.
 export CUDA_HOME=/usr/local/cuda

-pip3 install git+https://github.com/nickjbrowning/XIELU@59d6031 --no-build-isolation --no-deps
+uv pip install git+https://github.com/nickjbrowning/XIELU@59d6031 --no-build-isolation --no-deps
 ```

 For any installation errors, see [XIELU Installation Issues](#xielu-installation-issues)
@@ -67,7 +66,7 @@ If those didn't help, please try the below solutions:
 1. Pass env for CMAKE and try install again:

    ```bash
-    Python_EXECUTABLE=$(which python) pip3 install git+https://github.com/nickjbrowning/XIELU@59d6031 --no-build-isolation --no-deps
+    Python_EXECUTABLE=$(which python) uv pip install git+https://github.com/nickjbrowning/XIELU@59d6031 --no-build-isolation --no-deps
    ```

 2. Git clone the repo and manually hardcode python path:
@@ -92,7 +91,7 @@ If those didn't help, please try the below solutions:
    ```

    ```bash
-    pip3 install . --no-build-isolation --no-deps
+    uv pip install . --no-build-isolation --no-deps
    ```

 ## Optimization Guides
--- a/examples/arcee/README.md
+++ b/examples/arcee/README.md
@@ -17,8 +17,7 @@ Thanks to the team at Arcee.ai for using Axolotl in supervised fine-tuning the A
 git clone https://github.com/axolotl-ai-cloud/axolotl.git
 cd axolotl

-pip3 install packaging==26.0 setuptools==75.8.0 wheel ninja
-pip3 install --no-build-isolation -e '.[flash-attn]'
+uv pip install --no-build-isolation -e '.[flash-attn]'

 # Install CCE https://docs.axolotl.ai/docs/custom_integrations.html#cut-cross-entropy
 python scripts/cutcrossentropy_install.py | sh
--- a/examples/devstral/README.md
+++ b/examples/devstral/README.md
@@ -16,8 +16,7 @@ Thanks to the team at MistralAI for giving us early access to prepare for this r

 ```bash
 # Ensure you have Pytorch installed (Pytorch 2.6.0 min)
-pip3 install packaging==26.0 setuptools==75.8.0 wheel ninja
-pip3 install --no-build-isolation 'axolotl[flash-attn]>=0.12.0'
+uv pip install --no-build-isolation 'axolotl[flash-attn]>=0.12.0'
 ```

 2. Install [Cut Cross Entropy](https://docs.axolotl.ai/docs/custom_integrations.html#cut-cross-entropy) to reduce training VRAM usage
--- a/examples/gemma3n/README.md
+++ b/examples/gemma3n/README.md
@@ -10,17 +10,16 @@ Gemma-3n is a family of multimodal models from Google found on [HuggingFace](htt

 ```bash
 # Ensure you have Pytorch installed (Pytorch 2.6.0 min)
-pip3 install packaging==26.0 setuptools==75.8.0 wheel ninja
-pip3 install --no-build-isolation 'axolotl[flash-attn]>=0.12.0'
+uv pip install --no-build-isolation 'axolotl[flash-attn]>=0.12.0'
 ```

 2. In addition to Axolotl's requirements, Gemma-3n requires:

 ```bash
-pip3 install timm==1.0.17
+uv pip install timm==1.0.17

 # for loading audio data
-pip3 install librosa==0.11.0
+uv pip install librosa==0.11.0
 ```

 3. Download sample dataset files
--- a/examples/gpt-oss/README.md
+++ b/examples/gpt-oss/README.md
@@ -14,8 +14,7 @@ This guide shows how to fine-tune it with Axolotl with multi-turn conversations

 ```bash
 # Ensure you have Pytorch installed (Pytorch 2.6.0 min)
-pip3 install packaging==26.0 setuptools==75.8.0 wheel ninja
-pip3 install --no-build-isolation 'axolotl[flash-attn]>=0.12.0'
+uv pip install --no-build-isolation 'axolotl[flash-attn]>=0.12.0'
 ```

 2. Choose one of the following configs below for training the 20B model. (for 120B, see [below](#training-120b))
@@ -87,7 +86,7 @@ for more information about using a special vllm-openai docker image for inferenc
 Optionally, vLLM can be installed from nightly:

 ```bash
-pip install --no-build-isolation --pre -U vllm --extra-index-url https://wheels.vllm.ai/nightly
+uv pip install --no-build-isolation --pre -U vllm --extra-index-url https://wheels.vllm.ai/nightly
 ```
 and the vLLM server can be started with the following command (modify `--tensor-parallel-size 8` to match your environment):
 ```bash
--- a/examples/granite4/README.md
+++ b/examples/granite4/README.md
@@ -15,8 +15,7 @@ This guide shows how to fine-tune it with Axolotl with multi-turn conversations
 git clone https://github.com/axolotl-ai-cloud/axolotl.git
 cd axolotl

-pip3 install packaging==26.0 setuptools==75.8.0 wheel ninja
-pip3 install --no-build-isolation -e '.[flash-attn]'
+uv pip install --no-build-isolation -e '.[flash-attn]'

 # Install CCE https://docs.axolotl.ai/docs/custom_integrations.html#cut-cross-entropy
 python scripts/cutcrossentropy_install.py | sh
--- a/examples/hunyuan/README.md
+++ b/examples/hunyuan/README.md
@@ -13,8 +13,7 @@ Tencent released a family of opensource models called HunYuan with varying param
 git clone https://github.com/axolotl-ai-cloud/axolotl.git
 cd axolotl

-pip3 install packaging==26.0 setuptools==75.8.0 wheel ninja
-pip3 install --no-build-isolation -e '.[flash-attn]'
+uv pip install --no-build-isolation -e '.[flash-attn]'

 # Install CCE https://docs.axolotl.ai/docs/custom_integrations.html#cut-cross-entropy
 python scripts/cutcrossentropy_install.py | sh
--- a/examples/internvl3_5/README.md
+++ b/examples/internvl3_5/README.md
@@ -11,7 +11,7 @@ This guide shows how to fine-tune it with Axolotl.
 2. Install `timm` for vision model support:

    ```bash
-    pip install timm==1.0.19
+    uv pip install timm==1.0.19
    ```

 3. Install [Cut Cross Entropy](https://docs.axolotl.ai/docs/custom_integrations.html#cut-cross-entropy) to reduce training VRAM usage.
--- a/examples/magistral/README.md
+++ b/examples/magistral/README.md
@@ -14,8 +14,7 @@ Thanks to the team at MistralAI for giving us early access to prepare for these

 ```bash
 # Ensure you have Pytorch installed (Pytorch 2.7.0 min)
-pip3 install packaging==26.0 setuptools==75.8.0 wheel ninja
-pip3 install --no-build-isolation 'axolotl[flash-attn]>=0.12.0'
+uv pip install --no-build-isolation 'axolotl[flash-attn]>=0.12.0'
 ```

 2. Install [Cut Cross Entropy](https://docs.axolotl.ai/docs/custom_integrations.html#cut-cross-entropy) to reduce training VRAM usage
--- a/examples/magistral/vision/README.md
+++ b/examples/magistral/vision/README.md
@@ -12,7 +12,7 @@ Before starting, ensure you have:

 1. Install the required vision lib:
    ```bash
-    pip install 'mistral-common[opencv]==1.8.5'
+    uv pip install 'mistral-common[opencv]==1.8.5'
    ```

 2. Download the example dataset image:
--- a/examples/ministral3/README.md
+++ b/examples/ministral3/README.md
@@ -23,7 +23,7 @@ Note: This is still experimental given it is based on transformers v5 RC.
    git checkout transformers-v5

    # Install packages for transformers v5
-    pip install -e .
+    uv pip install -e .
    ```

 4. Run the fine-tuning:
--- a/examples/ministral3/vision/README.md
+++ b/examples/ministral3/vision/README.md
@@ -12,7 +12,7 @@ Before starting, ensure you have:

 1. Install the required vision lib:
    ```bash
-    pip install 'mistral-common[opencv]==1.8.6'
+    uv pip install 'mistral-common[opencv]==1.8.6'
    ```

 2. Download the example dataset image:
--- a/examples/mistral-small/README.md
+++ b/examples/mistral-small/README.md
@@ -12,7 +12,7 @@ Before starting, ensure you have:

 1. Install the required vision lib:
    ```bash
-    pip install 'mistral-common[opencv]==1.8.5'
+    uv pip install 'mistral-common[opencv]==1.8.5'
    ```

 2. Download the example dataset image:
--- a/examples/mistral4/README.md
+++ b/examples/mistral4/README.md
@@ -13,7 +13,7 @@ Thanks to the team at MistralAI for giving us early access to prepare for this r
 3. Install transformers from main

  ```bash
-  pip install git+https://github.com/huggingface/transformers.git
+  uv pip install git+https://github.com/huggingface/transformers.git
  ```

 4. Run one of the example configs:
--- a/examples/qwen3-next/README.md
+++ b/examples/qwen3-next/README.md
@@ -12,7 +12,7 @@ This guide shows how to fine-tune it with Axolotl with multi-turn conversations

 3. Install FLA for improved performance
 ```bash
-pip3 uninstall -y causal-conv1d && pip3 install flash-linear-attention==0.4.1
+uv pip uninstall causal-conv1d && uv pip install flash-linear-attention==0.4.1
 ```

 4. Run the finetuning example:
--- a/examples/qwen3.5/README.md
+++ b/examples/qwen3.5/README.md
@@ -10,7 +10,7 @@

 3. Install FLA for sample packing support with the Gated DeltaNet linear attention layers:
  ```bash
-  pip3 uninstall -y causal-conv1d && pip3 install flash-linear-attention==0.4.1
+  uv pip uninstall causal-conv1d && uv pip install flash-linear-attention==0.4.1
  ```
  > FLA is required when `sample_packing: true`. Without it, training raises a `RuntimeError` on packed sequences. Vision configs use `sample_packing: false` so FLA is optional there.

--- a/examples/seed-oss/README.md
+++ b/examples/seed-oss/README.md
@@ -11,8 +11,7 @@ This guide shows how to fine-tune it with Axolotl with multi-turn conversations
    Here is an example of how to install from pip:
    ```bash
    # Ensure you have a compatible version of Pytorch installed
-    pip3 install packaging setuptools wheel ninja
-    pip3 install --no-build-isolation 'axolotl[flash-attn]>=0.12.0'
+    uv pip install --no-build-isolation 'axolotl[flash-attn]>=0.12.0'

    # Install Cut Cross Entropy
    python scripts/cutcrossentropy_install.py | sh
--- a/examples/smolvlm2/README.md
+++ b/examples/smolvlm2/README.md
@@ -13,14 +13,13 @@ This guide shows how to fine-tune SmolVLM2 models with Axolotl.
    Here is an example of how to install from pip:
    ```bash
    # Ensure you have a compatible version of Pytorch installed
-    pip3 install packaging setuptools wheel ninja
-    pip3 install --no-build-isolation 'axolotl[flash-attn]>=0.12.0'
+    uv pip install --no-build-isolation 'axolotl[flash-attn]>=0.12.0'
    ```

 2. Install an extra dependency:

    ```bash
-    pip3 install num2words==0.5.14
+    uv pip install num2words==0.5.14
    ```

 3.  Run the finetuning example:
--- a/examples/voxtral/README.md
+++ b/examples/voxtral/README.md
@@ -12,16 +12,15 @@ Thanks to the team at MistralAI for giving us early access to prepare for this r

 ```bash
 # Ensure you have Pytorch installed (Pytorch 2.6.0 min)
-pip3 install packaging==26.0 setuptools==75.8.0 wheel ninja
-pip3 install --no-build-isolation 'axolotl[flash-attn]>=0.12.0'
+uv pip install --no-build-isolation 'axolotl[flash-attn]>=0.12.0'
 ```

 2. Please install the below.

 ```bash
 # audio
-pip3 install librosa==0.11.0
-pip3 install 'mistral_common[audio]==1.8.3'
+uv pip install librosa==0.11.0
+uv pip install 'mistral_common[audio]==1.8.3'

 # Install CCE https://docs.axolotl.ai/docs/custom_integrations.html#cut-cross-entropy
 python scripts/cutcrossentropy_install.py | sh
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,15 +1,165 @@
 [build-system]
-requires = ["setuptools>=64", "wheel", "setuptools_scm>=8", "packaging==26.0"]
+requires = ["setuptools>=64", "wheel", "setuptools_scm>=8"]
 build-backend = "setuptools.build_meta"

 [project]
 name = "axolotl"
-dynamic = ["version", "dependencies", "optional-dependencies"]
+dynamic = ["version"]
 description = "LLM Trainer"
 readme = "README.md"
 requires-python = ">=3.10"
 # license = "Apache-2.0"

+dependencies = [
+    # Core ML stack
+    "torch>=2.6.0",
+    "packaging==26.0",
+    "huggingface_hub>=1.1.7",
+    "peft>=0.19.1,<0.20.0",
+    "tokenizers>=0.22.1",
+    "transformers==5.5.4",
+    "accelerate==1.13.0",
+    "datasets>=4.8.4,<4.9.0",
+    "trl==1.1.0",
+    "hf_xet==1.4.3",
+    "kernels==0.13.0",
+    "trackio>=0.16.1",
+    "typing-extensions>=4.15.0",
+    "optimum==1.16.2",
+    "hf_transfer",
+    "sentencepiece",
+    "gradio>=6.2.0,<7.0",
+    "modal==1.3.0.post1",
+    "pydantic>=2.10.6",
+    "addict",
+    "fire",
+    "PyYAML>=6.0",
+    "requests",
+    "wandb",
+    "einops",
+    "colorama",
+    "numba>=0.61.2",
+    "numpy>=2.2.6",
+
+    # Evaluation & metrics
+    "evaluate==0.4.1",
+    "scipy",
+    "nvidia-ml-py==12.560.30",
+    "art",
+    "tensorboard",
+    "python-dotenv==1.0.1",
+
+    # Remote filesystems
+    "s3fs>=2024.5.0",
+    "gcsfs>=2025.3.0",
+    "adlfs>=2024.5.0",
+    "ocifs==1.3.2",
+
+    "zstandard==0.22.0",
+    "fastcore",
+
+    # lm eval harness
+    "lm_eval==0.4.11",
+    "langdetect==1.0.9",
+    "immutabledict==4.2.0",
+    "antlr4-python3-runtime==4.13.2",
+
+    "schedulefree==1.4.1",
+    "openenv-core==0.1.0",
+
+    # Axolotl contribs
+    "axolotl-contribs-lgpl==0.0.7",
+    "axolotl-contribs-mit==0.0.6",
+
+    # Telemetry
+    "posthog==6.7.11",
+
+    "mistral-common==1.11.0",
+
+    # Platform-specific (Linux only)
+    "bitsandbytes==0.49.1 ; sys_platform != 'darwin'",
+    "triton>=3.4.0 ; sys_platform != 'darwin'",
+    "xformers>=0.0.23.post1 ; sys_platform != 'darwin'",
+    "liger-kernel==0.7.0 ; sys_platform != 'darwin'",
+    "torchao==0.17.0 ; sys_platform != 'darwin' and platform_machine != 'aarch64'",
+
+    # Architecture-specific
+    "fla-core==0.4.1 ; platform_machine != 'aarch64'",
+    "flash-linear-attention==0.4.1 ; platform_machine != 'aarch64'",
+]
+
+[project.optional-dependencies]
+flash-attn = ["flash-attn==2.8.3"]
+ring-flash-attn = [
+    "flash-attn==2.8.3",
+    "ring-flash-attn>=0.1.7",
+]
+deepspeed = [
+    "deepspeed>=0.18.6,<0.19.0",
+    "deepspeed-kernels",
+]
+mamba-ssm = [
+    "mamba-ssm==1.2.0.post1",
+    "causal_conv1d",
+]
+auto-gptq = [
+    "auto-gptq==0.5.1",
+]
+mlflow = [
+    "mlflow",
+]
+galore = [
+    "galore_torch",
+]
+apollo = [
+    "apollo-torch",
+]
+optimizers = [
+    "galore_torch",
+    "apollo-torch",
+    "lomo-optim==0.1.1",
+    "torch-optimi==0.2.1",
+    "came_pytorch==0.1.3",
+]
+ray = [
+    "ray[train]>=2.52.1",
+]
+vllm = [
+    "vllm>=0.15.0",
+]
+llmcompressor = [
+    "llmcompressor>=0.10.0",
+]
+fbgemm-gpu = ["fbgemm-gpu-genai>=1.3.0"]
+opentelemetry = [
+    "opentelemetry-api",
+    "opentelemetry-sdk",
+    "opentelemetry-exporter-prometheus",
+    "prometheus-client",
+]
+
+[dependency-groups]
+dev = [
+    "black",
+    "mypy",
+    "pre-commit",
+    "types-requests",
+    "quartodoc",
+    "jupyter",
+    "blobfile",
+    "tiktoken",
+]
+test = [
+    "codecov",
+    "codecov-cli",
+    "pytest",
+    "pytest-cov",
+    "pytest-retry",
+    "pytest-sugar",
+    "pytest-xdist",
+    "tbparse",
+]
+
 [project.scripts]
 axolotl = "axolotl.cli.main:main"

@@ -18,18 +168,15 @@ Homepage = "https://axolotl.ai/"
 Documentation = "https://docs.axolotl.ai/"
 Repository = "https://github.com/axolotl-ai-cloud/axolotl.git"

-[tool.setuptools_scm]
-
 [tool.setuptools]
-py-modules = ["setuptools_axolotl_dynamic_dependencies"]
 include-package-data = true

+[tool.setuptools.packages.find]
+where = ["src"]
+
 [tool.setuptools.dynamic]
 version = { file = "VERSION" }

-[tool.setuptools.cmdclass]
-build_py = "setuptools_axolotl_dynamic_dependencies.BuildPyCommand"
-
 [tool.ruff]
 line-length = 88
 target-version = "py310"
@@ -67,5 +214,43 @@ markers = [
    "slow: marks tests as slow",
 ]

+# UV specific configuration
+[tool.uv]
+prerelease = "allow"
+conflicts = [
+    [
+        { package = "axolotl" },
+        { extra = "vllm" },
+    ],
+    [
+        { package = "axolotl" },
+        { extra = "flash-attn" },
+    ],
+    [
+        { package = "axolotl" },
+        { extra = "ring-flash-attn" },
+    ],
+    [
+        { package = "axolotl" },
+        { extra = "mamba-ssm" },
+    ],
+    [
+        { package = "axolotl" },
+        { extra = "auto-gptq" },
+    ],
+    [
+        { package = "axolotl" },
+        { extra = "fbgemm-gpu" },
+    ],
+    [
+        { package = "axolotl" },
+        { extra = "llmcompressor" },
+    ],
+]
+
 [tool.uv.extra-build-dependencies]
-axolotl = ["huggingface_hub"]
+mamba-ssm = [{ requirement = "torch", match-runtime = true }]
+causal-conv1d = [{ requirement = "torch", match-runtime = true }]
+flash-attn = [{ requirement = "torch", match-runtime = true }]
+deepspeed = [{ requirement = "torch", match-runtime = true }]
+auto-gptq = [{ requirement = "torch", match-runtime = true }]
--- a/requirements-dev.txt
+++ b/requirements-dev.txt
@@ -1,8 +0,0 @@
-black
-mypy
-pre-commit
-types-requests
-quartodoc
-jupyter
-blobfile
-tiktoken
--- a/requirements-tests.txt
+++ b/requirements-tests.txt
@@ -1,8 +0,0 @@
-codecov
-codecov-cli
-pytest
-pytest-cov
-pytest-retry
-pytest-sugar
-pytest-xdist
-tbparse
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,78 +0,0 @@
--extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/
-
-# START section of dependencies that don't install on Darwin/MacOS
-bitsandbytes==0.49.1
-triton>=3.4.0
-mamba-ssm==1.2.0.post1
-xformers>=0.0.23.post1
-liger-kernel==0.7.0
-# END section
-
-packaging==26.0
-huggingface_hub>=1.1.7
-peft>=0.19.0,<0.20.0
-tokenizers>=0.22.1
-transformers==5.5.4
-accelerate==1.13.0
-datasets>=4.8.4,<4.9.0
-deepspeed>=0.18.6,<0.19.0
-trl==1.1.0
-hf_xet==1.4.3
-kernels==0.13.0
-
-fla-core==0.4.1
-flash-linear-attention==0.4.1
-
-trackio>=0.16.1
-typing-extensions>=4.15.0
-
-optimum==1.16.2
-hf_transfer
-sentencepiece
-gradio>=6.2.0,<7.0
-
-modal==1.3.0.post1
-pydantic>=2.10.6
-addict
-fire
-PyYAML>=6.0
-requests
-wandb
-einops
-colorama
-numba>=0.61.2
-numpy>=2.2.6
-
-# qlora things
-evaluate==0.4.1
-scipy
-nvidia-ml-py==12.560.30
-art
-tensorboard
-python-dotenv==1.0.1
-
-# remote filesystems
-s3fs>=2024.5.0
-gcsfs>=2025.3.0
-adlfs>=2024.5.0
-ocifs==1.3.2
-
-zstandard==0.22.0
-fastcore
-
-# lm eval harness
-lm_eval==0.4.11
-langdetect==1.0.9
-immutabledict==4.2.0
-antlr4-python3-runtime==4.13.2
-
-torchao==0.17.0
-openenv-core==0.1.0
-schedulefree==1.4.1
-
-axolotl-contribs-lgpl==0.0.7
-axolotl-contribs-mit==0.0.6
-# telemetry
-posthog==6.7.11
-
-mistral-common==1.11.0
--- a/scripts/unsloth_install.py
+++ b/scripts/unsloth_install.py
@@ -1,40 +0,0 @@
-# noqa
-import sys
-
-try:
-    import torch
-except ImportError as error:
-    raise ImportError("Install torch via `pip install torch`") from error
-from packaging.version import Version as V
-
-use_uv = "--uv" in sys.argv[1:]
-
-v = V(torch.__version__)
-cuda = str(torch.version.cuda)
-try:
-    is_ampere = torch.cuda.get_device_capability()[0] >= 8
-except RuntimeError:
-    is_ampere = False
-if cuda != "12.1" and cuda != "11.8" and cuda != "12.4":
-    raise RuntimeError(f"CUDA = {cuda} not supported!")
-if v <= V("2.1.0"):
-    raise RuntimeError(f"Torch = {v} too old!")
-elif v <= V("2.1.1"):
-    x = "cu{}{}-torch211"
-elif v <= V("2.1.2"):
-    x = "cu{}{}-torch212"
-elif v < V("2.3.0"):
-    x = "cu{}{}-torch220"
-elif v < V("2.4.0"):
-    x = "cu{}{}-torch230"
-elif v < V("2.5.0"):
-    x = "cu{}{}-torch240"
-elif v < V("2.6.0"):
-    x = "cu{}{}-torch250"
-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'{uv_prefix}pip install unsloth-zoo==2024.12.1 && {uv_prefix}pip install --no-deps "unsloth[{x}]==2024.12.4"'
-)
--- a/setup.py
+++ b/setup.py
@@ -1,230 +0,0 @@
-"""setup.py for axolotl"""
-
-import os
-import platform
-import re
-from importlib.metadata import PackageNotFoundError, version
-from pathlib import Path
-
-from setuptools import find_packages, setup
-
-
-def parse_requirements(extras_require_map):
-    _install_requires = []
-    _dependency_links = []
-    with open("./requirements.txt", encoding="utf-8") as requirements_file:
-        lines = [r.strip() for r in requirements_file.readlines()]
-        for line in lines:
-            is_extras = "deepspeed" in line or "mamba-ssm" in line
-            if line.startswith("--extra-index-url"):
-                # Handle custom index URLs
-                _, url = line.split()
-                _dependency_links.append(url)
-            elif not is_extras and line and line[0] != "#":
-                # Handle standard packages
-                _install_requires.append(line)
-    try:
-        xformers_version = [req for req in _install_requires if "xformers" in req][0]
-        install_xformers = platform.machine() != "aarch64"
-        if platform.machine() == "aarch64":
-            # skip on ARM64
-            skip_packages = [
-                "torchao",
-                "fla-core",
-                "flash-linear-attention",
-            ]
-            _install_requires = [
-                req
-                for req in _install_requires
-                if re.split(r"[>=<]", req)[0].strip() not in skip_packages
-            ]
-        if "Darwin" in platform.system():
-            # skip packages not compatible with OSX
-            skip_packages = [
-                "bitsandbytes",
-                "triton",
-                "mamba-ssm",
-                "xformers",
-                "liger-kernel",
-            ]
-            _install_requires = [
-                req
-                for req in _install_requires
-                if re.split(r"[>=<]", req)[0].strip() not in skip_packages
-            ]
-            print(
-                _install_requires, [req in skip_packages for req in _install_requires]
-            )
-        else:
-            # detect the version of torch already installed
-            # and set it so dependencies don't clobber the torch version
-            try:
-                torch_version = version("torch")
-            except PackageNotFoundError:
-                torch_version = "2.8.0"  # default to torch 2.8.0
-            _install_requires.append(f"torch=={torch_version}")
-
-            version_match = re.match(r"^(\d+)\.(\d+)(?:\.(\d+))?", torch_version)
-            if version_match:
-                major, minor, patch = version_match.groups()
-                major, minor = int(major), int(minor)
-                patch = (
-                    int(patch) if patch is not None else 0
-                )  # Default patch to 0 if not present
-            else:
-                raise ValueError("Invalid version format")
-
-            torch_parts = torch_version.split("+")
-            if len(torch_parts) == 2:
-                torch_cuda_version = torch_parts[1]
-                _dependency_links.append(
-                    f"https://download.pytorch.org/whl/{torch_cuda_version}"
-                )
-
-            if (major, minor) >= (2, 10):
-                extras_require_map.pop("fbgemm-gpu")
-                extras_require_map["fbgemm-gpu"] = [
-                    "fbgemm-gpu==1.5.0",
-                    "fbgemm-gpu-genai==1.5.0",
-                ]
-                if not install_xformers:
-                    _install_requires.pop(_install_requires.index(xformers_version))
-                extras_require_map["vllm"] = ["vllm>=0.19.0"]
-            elif (major, minor) >= (2, 9):
-                extras_require_map.pop("fbgemm-gpu")
-                extras_require_map["fbgemm-gpu"] = [
-                    "fbgemm-gpu==1.4.0",
-                    "fbgemm-gpu-genai==1.4.2",
-                ]
-                if not install_xformers:
-                    _install_requires.pop(_install_requires.index(xformers_version))
-                if patch == 0:
-                    extras_require_map["vllm"] = ["vllm==0.13.0"]
-                else:
-                    extras_require_map["vllm"] = ["vllm==0.14.0"]
-            elif (major, minor) >= (2, 8):
-                extras_require_map.pop("fbgemm-gpu")
-                extras_require_map["fbgemm-gpu"] = ["fbgemm-gpu-genai==1.3.0"]
-                extras_require_map["vllm"] = ["vllm==0.11.0"]
-                if not install_xformers:
-                    _install_requires.pop(_install_requires.index(xformers_version))
-            elif (major, minor) >= (2, 7):
-                _install_requires.pop(_install_requires.index(xformers_version))
-                if patch == 0:
-                    if install_xformers:
-                        _install_requires.append("xformers==0.0.30")
-                    # vllm 0.9.x is incompatible with latest transformers
-                    extras_require_map.pop("vllm")
-                else:
-                    if install_xformers:
-                        _install_requires.append("xformers==0.0.31")
-                    extras_require_map["vllm"] = ["vllm==0.10.1"]
-            elif (major, minor) >= (2, 6):
-                _install_requires.pop(_install_requires.index(xformers_version))
-                if install_xformers:
-                    _install_requires.append("xformers==0.0.29.post3")
-                # since we only support 2.6.0+cu126
-                _dependency_links.append("https://download.pytorch.org/whl/cu126")
-                extras_require_map.pop("vllm")
-            elif (major, minor) >= (2, 5):
-                _install_requires.pop(_install_requires.index(xformers_version))
-                if install_xformers:
-                    if patch == 0:
-                        _install_requires.append("xformers==0.0.28.post2")
-                    else:
-                        _install_requires.append("xformers>=0.0.28.post3")
-                extras_require_map.pop("vllm")
-            elif (major, minor) >= (2, 4):
-                extras_require_map.pop("vllm")
-                if install_xformers:
-                    if patch == 0:
-                        _install_requires.pop(_install_requires.index(xformers_version))
-                        _install_requires.append("xformers>=0.0.27")
-                    else:
-                        _install_requires.pop(_install_requires.index(xformers_version))
-                        _install_requires.append("xformers==0.0.28.post1")
-            else:
-                raise ValueError("axolotl requires torch>=2.4")
-
-    except PackageNotFoundError:
-        pass
-    return _install_requires, _dependency_links, extras_require_map
-
-
-def get_package_version():
-    with open(
-        Path(os.path.dirname(os.path.abspath(__file__))) / "VERSION",
-        "r",
-        encoding="utf-8",
-    ) as fin:
-        version_ = fin.read().strip()
-    return version_
-
-
-extras_require = {
-    "flash-attn": ["flash-attn==2.8.3"],
-    "ring-flash-attn": [
-        "flash-attn==2.8.3",
-        "ring-flash-attn>=0.1.7",
-    ],
-    "deepspeed": [
-        "deepspeed==0.18.2",
-        "deepspeed-kernels",
-    ],
-    "mamba-ssm": [
-        "mamba-ssm==1.2.0.post1",
-        "causal_conv1d",
-    ],
-    "auto-gptq": [
-        "auto-gptq==0.5.1",
-    ],
-    "mlflow": [
-        "mlflow",
-    ],
-    "galore": [
-        "galore_torch",
-    ],
-    "apollo": [
-        "apollo-torch",
-    ],
-    "optimizers": [
-        "galore_torch",
-        "apollo-torch",
-        "lomo-optim==0.1.1",
-        "torch-optimi==0.2.1",
-        "came_pytorch==0.1.3",
-    ],
-    "ray": [
-        "ray[train]>=2.52.1",
-    ],
-    "vllm": [
-        "vllm==0.10.0",
-    ],
-    "llmcompressor": [
-        "llmcompressor==0.5.1",
-    ],
-    "fbgemm-gpu": ["fbgemm-gpu-genai==1.3.0"],
-    "opentelemetry": [
-        "opentelemetry-api",
-        "opentelemetry-sdk",
-        "opentelemetry-exporter-prometheus",
-        "prometheus-client",
-    ],
-}
-install_requires, dependency_links, extras_require_build = parse_requirements(
-    extras_require
-)
-
-setup(
-    version=get_package_version(),
-    package_dir={"": "src"},
-    packages=find_packages("src"),
-    install_requires=install_requires,
-    dependency_links=dependency_links,
-    entry_points={
-        "console_scripts": [
-            "axolotl=axolotl.cli.main:main",
-        ],
-    },
-    extras_require=extras_require_build,
-)
--- a/src/axolotl/cli/utils/lora_merge.py
+++ b/src/axolotl/cli/utils/lora_merge.py
@@ -339,7 +339,11 @@ def _build_peft_layer_and_get_delta(
            )
        layer.lora_A[adapter_name].weight.data = lora_a
        layer.lora_B[adapter_name].weight.data = lora_b
-        return layer.get_delta_weight(adapter_name)
+        delta = layer.get_delta_weight(adapter_name)
+        # peft >=0.19.1 may return delta with transposed dims for 3D params
+        if delta.shape != base_tensor.shape and delta.ndim == 3:
+            delta = delta.transpose(1, 2).contiguous()
+        return delta
    elif (
        layer_type and "Conv" in layer_type or (layer_type is None and lora_a.ndim > 2)
    ):
--- a/src/axolotl/integrations/kernels/libs/scattermoe_lora/layers.py
+++ b/src/axolotl/integrations/kernels/libs/scattermoe_lora/layers.py
@@ -60,49 +60,14 @@ def peft_lora_B_to_scattermoe(peft_B, num_experts, rank):


 def peft_lora_to_scattermoe(peft_A, peft_B, num_experts, rank):
-    """Convert peft LoRA weights to scattermoe layout (with A<->B swap).
+    """Convert peft LoRA weights to scattermoe layout.

-    peft operates on the parameter in its native storage layout ``[E, dim1, dim2]``
-    where ``in_features=dim1, out_features=dim2``.  ScatterMoE transposes the
-    parameter (``W = param.transpose(2, 1)``) giving ``[E, dim2, dim1]`` with
-    ``K=dim2, N=dim1``.  Because of this transposition, peft's A and B roles
-    are swapped relative to scattermoe's convention.
-
-    peft gives:
-        lora_A ``[r*E, dim1]``, lora_B ``[dim2, r*E]``
-
-    scattermoe needs:
-        lora_A ``[r*E, K=dim2]``, lora_B ``[N=dim1, r*E]``
-
-    This function swaps A<->B and converts B from rank-major to expert-major.
-    Uses vectorized tensor operations (no Python loop over experts).
-
-    Works for **both** gate_up_proj and down_proj since the transposition
-    issue is the same for any parameter.
+    peft >=0.19.1 assigns in/out features for 3D params such that
+    A and B already align with scattermoe's convention (no A<->B swap).
+    Only B needs rank-major → expert-major layout conversion.
    """
-    peft_B_em = peft_lora_B_to_scattermoe(peft_B, num_experts, rank)
-
-    dim1 = peft_A.shape[1]  # peft in_features -> scattermoe N
-    dim2 = peft_B_em.shape[0]  # peft out_features -> scattermoe K
-
-    # smoe_A: per expert, transpose B_e [dim2, r] -> [r, dim2]
-    # [dim2, E*r] -> [dim2, E, r] -> [E, r, dim2] -> [E*r, dim2]
-    smoe_A = (
-        peft_B_em.reshape(dim2, num_experts, rank)
-        .permute(1, 2, 0)
-        .contiguous()
-        .reshape(rank * num_experts, dim2)
-    )
-
-    # smoe_B: per expert, transpose A_e [r, dim1] -> [dim1, r]
-    # [E*r, dim1] -> [E, r, dim1] -> [dim1, E, r] -> [dim1, E*r]
-    smoe_B = (
-        peft_A.reshape(num_experts, rank, dim1)
-        .permute(2, 0, 1)
-        .contiguous()
-        .reshape(dim1, num_experts * rank)
-    )
-
+    smoe_A = peft_A
+    smoe_B = peft_lora_B_to_scattermoe(peft_B, num_experts, rank)
    return smoe_A, smoe_B


--- a/src/axolotl/loaders/patch_manager.py
+++ b/src/axolotl/loaders/patch_manager.py
@@ -162,7 +162,6 @@ class PatchManager:
    def apply_post_model_load_patches(self, model: PreTrainedModel):
        """Apply patches that require the model instance."""
        self._apply_llama_flash_attn_patches(model)
-        self._apply_unsloth_patches(model)
        self._apply_lora_kernel_patch(model)
        self._apply_scaling_softmax_patch(model)

@@ -674,24 +673,10 @@ class PatchManager:
            )

            patch_fa_llama_cross_entropy()
-        elif self.cfg.unsloth_cross_entropy_loss:
-            from axolotl.monkeypatch.unsloth_ import integrate_cross_entropy_loss_patch
-
-            integrate_cross_entropy_loss_patch(model_type="llama")
-
        if self.cfg.flash_attn_rms_norm and self.has_flash_attn:
            from axolotl.monkeypatch.llama_attn_hijack_flash import patch_llama_rms_norm

            patch_llama_rms_norm()
-        elif self.cfg.unsloth_rms_norm:
-            from axolotl.monkeypatch.unsloth_ import patch_unsloth_layernorm
-
-            patch_unsloth_layernorm()
-
-        if self.cfg.unsloth_lora_qkv or self.cfg.unsloth_lora_o:
-            from axolotl.monkeypatch.unsloth_ import patch_self_attn_lora
-
-            patch_self_attn_lora()

    def _patch_llama_flash_attention(self):
        """Apply Flash Attention patches for LLaMA models."""
@@ -758,23 +743,6 @@ class PatchManager:
                LOG.info("Patching with SwiGLU...")
                replace_llama_mlp_with_swiglu(model)

-    def _apply_unsloth_patches(self, model):
-        """Apply unsloth optimization patches."""
-        if self.cfg.unsloth_lora_mlp:
-            from axolotl.monkeypatch.unsloth_ import integrate_lora_mlp_patch
-
-            integrate_lora_mlp_patch(peft_model=model)
-
-        if self.cfg.unsloth_lora_qkv or self.cfg.unsloth_lora_o:
-            from axolotl.monkeypatch.unsloth_ import integrate_lora_patch
-
-            integrate_lora_patch(peft_model=model, cfg=self.cfg)
-
-        if self.cfg.unsloth_rope:
-            from axolotl.monkeypatch.unsloth_ import integrate_rope_embeddings
-
-            integrate_rope_embeddings()
-
    def _apply_lora_kernel_patch(self, model):
        """Apply LoRA kernel patches."""
        if (
--- a/src/axolotl/monkeypatch/unsloth_.py
+++ b/src/axolotl/monkeypatch/unsloth_.py
@@ -1,252 +0,0 @@
-"""module for patching with unsloth optimizations"""
-
-import inspect
-import types
-
-import torch
-from peft import PeftModelForCausalLM
-from torch import nn
-from transformers.models.llama.modeling_llama import LlamaFlashAttention2
-
-from axolotl.monkeypatch.utils import detab_code
-from axolotl.utils.logging import get_logger
-
-LOG = get_logger(__name__)
-
-ORIGINAL_QKV_CODE = """
-    query_states = self.q_proj(hidden_states)
-    key_states = self.k_proj(hidden_states)
-    value_states = self.v_proj(hidden_states)
-""".lstrip("\n")
-
-PATCHED_QKV_CODE = """
-    query_states, key_states, value_states = self.apply_qkv(self, hidden_states)
-""".lstrip("\n")
-
-ORIGINAL_O_CODE = """
-    attn_output = self.o_proj(attn_output)
-""".lstrip("\n")
-
-PATCHED_O_CODE = """
-    attn_output = self.apply_o(self, attn_output)
-""".lstrip("\n")
-
-
-def original_apply_qkv(self, hidden_states):
-    query_states = self.q_proj(hidden_states)
-    key_states = self.k_proj(hidden_states)
-    value_states = self.v_proj(hidden_states)
-    return query_states, key_states, value_states
-
-
-def original_apply_o(self, hidden_states):
-    attn_output = self.o_proj(hidden_states)
-    return attn_output
-
-
-def get_self_attn_code() -> str:
-    forward = inspect.getsource(LlamaFlashAttention2.forward)
-    return forward
-
-
-def check_self_attn_is_patchable() -> bool:
-    qkv = get_self_attn_code()
-    qkv, _ = detab_code(qkv)
-    return ORIGINAL_QKV_CODE in qkv and ORIGINAL_O_CODE in qkv
-
-
-def integrate_cross_entropy_loss_patch(model_type: str = "llama") -> None:
-    from unsloth.kernels.cross_entropy_loss import fast_cross_entropy_loss
-
-    def UnslothForCausalLMLoss(
-        logits,
-        labels,
-        vocab_size: int,
-        num_items_in_batch: int = None,
-        ignore_index: int = -100,
-        **kwargs,
-    ):
-        # Upcast to float if we need to compute the loss to avoid potential precision issues
-        logits = logits.float()
-        # Shift so that tokens < n predict n
-        shift_logits = logits[..., :-1, :].contiguous()
-        shift_labels = labels[..., 1:].contiguous()
-
-        loss = fast_cross_entropy_loss(
-            logits=shift_logits, labels=shift_labels, n_items=num_items_in_batch
-        )
-        return loss
-
-    if model_type == "llama":
-        from transformers.loss import loss_utils
-
-        loss_utils.ForCausalLMLoss = UnslothForCausalLMLoss  # type: ignore[assignment]
-    else:
-        raise ValueError("Unsupported model type")
-
-
-self_attn_lora_patched = False
-
-
-def patch_self_attn_lora():
-    global self_attn_lora_patched
-    if self_attn_lora_patched:
-        # prevent patching multiple times
-        return
-    self_attn_forward = get_self_attn_code()
-    LlamaFlashAttention2._original_forward = self_attn_forward
-    self_attn_forward, _ = detab_code(self_attn_forward)
-    assert ORIGINAL_QKV_CODE in self_attn_forward, "Original qkv code not found"
-    assert ORIGINAL_O_CODE in self_attn_forward, "Original o code not found"
-
-    self_attn_forward = self_attn_forward.replace(ORIGINAL_QKV_CODE, PATCHED_QKV_CODE)
-    self_attn_forward = self_attn_forward.replace(ORIGINAL_O_CODE, PATCHED_O_CODE)
-    self_attn_forward = self_attn_forward.replace(
-        "def forward(",
-        "def unsloth_attn_forward(",
-        1,
-    )
-
-    # load imports necessary
-    import transformers.models.llama.modeling_llama
-
-    items_to_import = []
-    for item in dir(transformers.models.llama.modeling_llama):
-        if item in self_attn_forward:
-            items_to_import.append(item)
-
-    exec(
-        "from transformers.models.llama.modeling_llama import ("
-        + ", ".join(x for x in items_to_import)
-        + ")",
-        globals(),
-    )
-    exec(self_attn_forward, globals())
-    self_attn_lora_patched = True
-    LOG.info("patching unsloth attn lora")
-    LlamaFlashAttention2.forward = unsloth_attn_forward
-
-
-def integrate_rope_embeddings():
-    import transformers.models.llama.modeling_llama
-    from unsloth.kernels.rope_embedding import fast_rope_embedding
-
-    def apply_rotary_pos_emb(
-        q,
-        k,
-        cos,
-        sin,
-        position_ids=None,
-        unsqueeze_dim=1,
-    ):
-        return fast_rope_embedding(q, k, cos, sin)
-
-    LOG.info("patching unsloth RoPE embeddings")
-    transformers.models.llama.modeling_llama.apply_rotary_pos_emb = apply_rotary_pos_emb
-
-
-def integrate_lora_mlp_patch(peft_model: PeftModelForCausalLM):
-    if peft_model.base_model.config.model_type in ["llama", "mistral"]:
-        from unsloth.kernels import apply_lora_mlp_swiglu
-
-        apply_lora_mlp = apply_lora_mlp_swiglu
-    elif peft_model.base_model.config.model_type == "gemma":
-        from unsloth.kernels import apply_lora_mlp_geglu_approx
-
-        apply_lora_mlp = apply_lora_mlp_geglu_approx
-    else:
-        raise NotImplementedError(
-            f"Model type {peft_model.base_model.config.model_type} not supported"
-        )
-
-    for idx, layer in enumerate(peft_model.model.model.layers):
-        layer_modules = [
-            getattr(layer.mlp, linear_proj)
-            for linear_proj in ["gate_proj", "up_proj", "down_proj"]
-        ]
-        is_mlp_lora = all(hasattr(module, "lora_A") for module in layer_modules)
-        mlp_no_bias = all(
-            getattr(module, "base_layer", module).bias is None
-            for module in layer_modules
-        )
-        mlp_not_dora = all(
-            len(getattr(module, "lora_magnitude_vector", []) or []) == 0
-            for module in layer_modules
-        )
-
-        if is_mlp_lora and mlp_no_bias and mlp_not_dora:
-            layer.mlp.forward = types.MethodType(apply_lora_mlp, layer.mlp)
-        else:
-            LOG.warning(f"unable to apply unsloth lora mlp patch to layer {idx}")
-
-
-def integrate_lora_patch(peft_model: PeftModelForCausalLM, cfg):
-    from unsloth.kernels import apply_lora_o, apply_lora_qkv
-
-    for idx, layer in enumerate(peft_model.model.model.layers):
-        if cfg.unsloth_lora_qkv:
-            layer_modules = [
-                getattr(layer.self_attn, linear_proj)
-                for linear_proj in ["q_proj", "k_proj", "v_proj"]
-            ]
-            is_qkv_lora = all(hasattr(module, "lora_A") for module in layer_modules)
-            qkv_no_bias = all(
-                getattr(module, "base_layer", module).bias is None
-                for module in layer_modules
-            )
-            qkv_not_dora = all(
-                len(getattr(module, "lora_magnitude_vector", []) or []) == 0
-                for module in layer_modules
-            )
-
-            if is_qkv_lora and qkv_no_bias and qkv_not_dora:
-                layer.self_attn.apply_qkv = apply_lora_qkv
-            else:
-                layer.self_attn.apply_qkv = original_apply_qkv
-                LOG.warning(f"unable to apply unsloth lora qkv patch to layer {idx}")
-        if cfg.unsloth_lora_o:
-            layer_modules = [
-                getattr(layer.self_attn, linear_proj) for linear_proj in ["o_proj"]
-            ]
-            is_o_lora = all(hasattr(module, "lora_A") for module in layer_modules)
-            o_no_bias = all(
-                getattr(module, "base_layer", module).bias is None
-                for module in layer_modules
-            )
-            o_not_dora = all(
-                len(getattr(module, "lora_magnitude_vector", []) or []) == 0
-                for module in layer_modules
-            )
-
-            if is_o_lora and o_no_bias and o_not_dora:
-                layer.self_attn.apply_o = apply_lora_o
-            else:
-                layer.self_attn.apply_o = original_apply_o
-                LOG.warning(f"unable to apply unsloth lora o_proj patch to layer {idx}")
-
-
-def patch_unsloth_layernorm():
-    try:
-        import transformers.models.llama.modeling_llama
-        from unsloth.kernels.rms_layernorm import Fast_RMS_Layernorm
-
-        class LlamaRMSNorm(nn.Module):
-            """LlamaRMSNorm"""
-
-            def __init__(self, hidden_size, eps=1e-6):
-                """
-                LlamaRMSNorm is equivalent to T5LayerNorm
-                """
-                super().__init__()
-                self.weight = nn.Parameter(torch.ones(hidden_size))
-                self.variance_epsilon = eps
-
-            def forward(self, hidden_states):
-                return Fast_RMS_Layernorm.apply(
-                    hidden_states, self.weight, self.variance_epsilon, False
-                )
-
-        LOG.info("patching with unsloth.kernels.rms_layernorm")
-        transformers.models.llama.modeling_llama.LlamaRMSNorm = LlamaRMSNorm
-    except ImportError:
-        LOG.warning("missing unsloth library")
--- a/src/axolotl/utils/schemas/config.py
+++ b/src/axolotl/utils/schemas/config.py
@@ -823,13 +823,6 @@ class AxolotlInputConfig(
        },
    )

-    unsloth_cross_entropy_loss: bool | None = None
-    unsloth_lora_mlp: bool | None = None
-    unsloth_lora_qkv: bool | None = None
-    unsloth_lora_o: bool | None = None
-    unsloth_rms_norm: bool | None = None
-    unsloth_rope: bool | None = None
-
    lora_mlp_kernel: bool | None = Field(
        default=None,
        json_schema_extra={
@@ -1469,21 +1462,6 @@ class AxolotlConfigWCapabilities(AxolotlInputConfig):
            )
        return data

-    @model_validator(mode="before")
-    @classmethod
-    def check_multigpu_unsloth(cls, data):
-        if (
-            data.get("unsloth_lora_mlp")
-            or data.get("unsloth_lora_qkv")
-            or data.get("unsloth_lora_o")
-        ):
-            capabilities = data.get("capabilities")
-            if capabilities and capabilities.get("n_gpu", 0) > 1:
-                raise ValueError(
-                    "unsloth_lora_mlp, unsloth_lora_qkv, and unsloth_lora_o are not compatible with multi-GPU training."
-                )
-        return data
-
    @model_validator(mode="before")
    @classmethod
    def check_multigpu_lora_kernels(cls, data):
@@ -1537,8 +1515,7 @@ class AxolotlConfigWCapabilities(AxolotlInputConfig):
            # RL trainers not tested so don't enable kernels by default
            return data
        if data.get("adapter") in ["lora", "qlora"]:
-            # Skip if already set, using unsloth optimizations, or using 8-bit
-            unsloth_fields = ["unsloth_lora_mlp", "unsloth_lora_qkv", "unsloth_lora_o"]
+            # Skip if already set or using 8-bit
            kernel_fields = [
                "lora_mlp_kernel",
                "lora_qkv_kernel",
@@ -1547,7 +1524,6 @@ class AxolotlConfigWCapabilities(AxolotlInputConfig):
            ]
            if (
                any(data.get(k) is not None for k in kernel_fields)
-                or any(data.get(k) for k in unsloth_fields)
                or data.get("adapter") == "lora"
                and data.get("load_in_8bit")
            ):
--- a/src/axolotl/utils/schemas/validation.py
+++ b/src/axolotl/utils/schemas/validation.py
@@ -52,6 +52,26 @@ class DatasetValidationMixin:

        return datasets

+    @model_validator(mode="before")
+    @classmethod
+    def check_deprecated_unsloth_fields(cls, data):
+        deprecated_fields = [
+            "unsloth_cross_entropy_loss",
+            "unsloth_lora_mlp",
+            "unsloth_lora_qkv",
+            "unsloth_lora_o",
+            "unsloth_rms_norm",
+            "unsloth_rope",
+        ]
+        found = [f for f in deprecated_fields if data.get(f)]
+        if found:
+            raise ValueError(
+                f"`{'`, `'.join(found)}` {'has' if len(found) == 1 else 'have'} been removed. "
+                "Please use `lora_mlp_kernel`, `lora_qkv_kernel`, `lora_o_kernel` instead. "
+                "See: https://docs.axolotl.ai/docs/lora_optims.html"
+            )
+        return data
+
    @model_validator(mode="before")
    @classmethod
    def check_dataset_or_pretraining_dataset(cls, data):
@@ -607,36 +627,6 @@ class LoRAValidationMixin:
            )
        return data

-    @model_validator(mode="before")
-    @classmethod
-    def check_qlora_unsloth(cls, data):
-        if (
-            data.get("unsloth_lora_mlp")
-            or data.get("unsloth_lora_qkv")
-            or data.get("unsloth_lora_o")
-        ):
-            if data.get("adapter") == "lora" and data.get("load_in_8bit"):
-                raise ValueError(
-                    "unsloth_lora_mlp, unsloth_lora_qkv, and unsloth_lora_o are not compatible with 8-bit LoRA"
-                )
-        return data
-
-    @model_validator(mode="before")
-    @classmethod
-    def check_lora_axolotl_unsloth(cls, data):
-        is_lora_kernel = any(
-            data.get(k) for k in ["lora_mlp_kernel", "lora_qkv_kernel", "lora_o_kernel"]
-        )
-        is_unsloth_lora = any(
-            data.get(k)
-            for k in ["unsloth_lora_mlp", "unsloth_lora_qkv", "unsloth_lora_o"]
-        )
-        if is_lora_kernel and is_unsloth_lora:
-            raise ValueError(
-                "both lora_mlp_kernel and unsloth_lora_mlp cannot be true (similarly for lora_qkv_kernel, lora_o_kernel)"
-            )
-        return data
-
    @model_validator(mode="after")
    def check_fused_lora(self):
        if self.adapter in ["lora", "qlora"] and self.flash_attn_fuse_mlp:
@@ -860,17 +850,6 @@ class OptimizationValidationMixin:

        return data

-    @model_validator(mode="before")
-    @classmethod
-    def check_xentropy_patch_conflicts(cls, data):
-        if data.get("flash_attn_cross_entropy") and data.get(
-            "unsloth_cross_entropy_loss"
-        ):
-            raise ValueError(
-                "flash_attn_cross_entropy and unsloth_cross_entropy_loss cannot be both enabled"
-            )
-        return data
-
    @model_validator(mode="before")
    @classmethod
    def check_cross_entropy_conflicts(cls, data):
--- a/src/setuptools_axolotl_dynamic_dependencies.py
+++ b/src/setuptools_axolotl_dynamic_dependencies.py
@@ -1,102 +0,0 @@
-"""
-dynamic requirements for axolotl
-"""
-
-import platform
-import re
-from importlib.metadata import PackageNotFoundError, version
-
-from setuptools.command.build_py import build_py as _build_py
-
-
-def parse_requirements():
-    _install_requires = []
-    _dependency_links = []
-    with open("./requirements.txt", encoding="utf-8") as requirements_file:
-        lines = [r.strip() for r in requirements_file.readlines()]
-        for line in lines:
-            is_extras = (
-                "flash-attn" in line
-                or "flash-attention" in line
-                or "deepspeed" in line
-                or "mamba-ssm" in line
-                or "lion-pytorch" in line
-            )
-            if line.startswith("--extra-index-url"):
-                # Handle custom index URLs
-                _, url = line.split()
-                _dependency_links.append(url)
-            elif not is_extras and line and line[0] != "#":
-                # Handle standard packages
-                _install_requires.append(line)
-
-    try:
-        xformers_version = [req for req in _install_requires if "xformers" in req][0]
-        torchao_version = [req for req in _install_requires if "torchao" in req][0]
-
-        if "Darwin" in platform.system():
-            # don't install xformers on MacOS
-            _install_requires.pop(_install_requires.index(xformers_version))
-        else:
-            # detect the version of torch already installed
-            # and set it so dependencies don't clobber the torch version
-            try:
-                torch_version = version("torch")
-            except PackageNotFoundError:
-                torch_version = "2.5.1"
-            _install_requires.append(f"torch=={torch_version}")
-
-            version_match = re.match(r"^(\d+)\.(\d+)(?:\.(\d+))?", torch_version)
-            if version_match:
-                major, minor, patch = version_match.groups()
-                major, minor = int(major), int(minor)
-                patch = (
-                    int(patch) if patch is not None else 0
-                )  # Default patch to 0 if not present
-            else:
-                raise ValueError("Invalid version format")
-
-            if (major, minor) >= (2, 5):
-                _install_requires.pop(_install_requires.index(xformers_version))
-                if patch == 0:
-                    _install_requires.append("xformers==0.0.28.post2")
-                else:
-                    _install_requires.append("xformers==0.0.28.post3")
-            elif (major, minor) >= (2, 4):
-                if patch == 0:
-                    _install_requires.pop(_install_requires.index(xformers_version))
-                    _install_requires.append("xformers>=0.0.27")
-                else:
-                    _install_requires.pop(_install_requires.index(xformers_version))
-                    _install_requires.append("xformers==0.0.28.post1")
-            elif (major, minor) >= (2, 3):
-                _install_requires.pop(_install_requires.index(torchao_version))
-                if patch == 0:
-                    _install_requires.pop(_install_requires.index(xformers_version))
-                    _install_requires.append("xformers>=0.0.26.post1")
-                else:
-                    _install_requires.pop(_install_requires.index(xformers_version))
-                    _install_requires.append("xformers>=0.0.27")
-            elif (major, minor) >= (2, 2):
-                _install_requires.pop(_install_requires.index(torchao_version))
-                _install_requires.pop(_install_requires.index(xformers_version))
-                _install_requires.append("xformers>=0.0.25.post1")
-            else:
-                _install_requires.pop(_install_requires.index(torchao_version))
-                _install_requires.pop(_install_requires.index(xformers_version))
-                _install_requires.append("xformers>=0.0.23.post1")
-
-    except PackageNotFoundError:
-        pass
-    return _install_requires, _dependency_links
-
-
-class BuildPyCommand(_build_py):
-    """
-    custom build_py command to parse dynamic requirements
-    """
-
-    def finalize_options(self):
-        super().finalize_options()
-        install_requires, _ = parse_requirements()
-        self.distribution.install_requires = install_requires
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -325,10 +325,10 @@ def download_phi_4_reasoning_model_fixture():


@pytest.fixture(scope="session", autouse=True)
-def download_phi_3_medium_model_fixture():
+def download_phi_3_mini_model_fixture():
    # download the tokenizer only
    snapshot_download_w_retry(
-        "microsoft/Phi-3-medium-128k-instruct",
+        "microsoft/Phi-3-mini-4k-instruct",
        repo_type="model",
        allow_patterns=["*token*", "config.json"],
    )
--- a/tests/e2e/integrations/test_scattermoe_lora_olmoe.py
+++ b/tests/e2e/integrations/test_scattermoe_lora_olmoe.py
@@ -54,24 +54,8 @@ except (ImportError, ModuleNotFoundError):
        )

    def peft_lora_to_scattermoe(peft_A, peft_B, num_experts, rank):
-        peft_B_em = peft_lora_B_to_scattermoe(peft_B, num_experts, rank)
-        K_inter, N_hidden = peft_B.shape[0], peft_A.shape[1]
-        smoe_A = torch.zeros(
-            rank * num_experts,
-            K_inter,
-            device=peft_A.device,
-            dtype=peft_A.dtype,
-        )
-        smoe_B = torch.zeros(
-            N_hidden,
-            rank * num_experts,
-            device=peft_A.device,
-            dtype=peft_A.dtype,
-        )
-        for e in range(num_experts):
-            s = e * rank
-            smoe_A[s : s + rank, :] = peft_B_em[:, s : s + rank].T
-            smoe_B[:, s : s + rank] = peft_A[s : s + rank, :].T
+        smoe_A = peft_A
+        smoe_B = peft_lora_B_to_scattermoe(peft_B, num_experts, rank)
        return smoe_A, smoe_B

    def _unwrap_experts_lora(experts_module):
@@ -322,12 +306,14 @@ class TestLoRABLayoutConversion:
        hidden, inter = 32, 16
        scaling = 2.0

-        peft_A = torch.randn(E * r, hidden)
-        peft_B = torch.randn(inter, E * r)
+        # peft >=0.19.1 for down_proj [E, hidden, inter]:
+        # swaps in/out, lora_A [r*E, inter], lora_B [hidden, r*E]
+        peft_A = torch.randn(E * r, inter)
+        peft_B = torch.randn(hidden, E * r)

-        A_r = peft_A.reshape(E, r, hidden)
-        B_r = peft_B.reshape(inter, r, E)
-        delta_peft = torch.einsum("o r e, e r i -> e i o", B_r, A_r) * scaling
+        A_r = peft_A.reshape(E, r, inter)
+        B_r = peft_B.reshape(hidden, r, E)
+        delta_peft = torch.einsum("o r e, e r i -> e o i", B_r, A_r) * scaling

        smoe_A, smoe_B = peft_lora_to_scattermoe(peft_A, peft_B, E, r)
        for e in range(E):
@@ -339,31 +325,22 @@ class TestLoRABLayoutConversion:
            )

    def test_gate_up_proj_conversion(self):
-        """Verify gate_up_proj LoRA conversion with non-square dims (Qwen3-like).
+        """Verify gate_up_proj LoRA conversion with non-square dims.

        gate_up_proj param: [E, 2*inter, hidden].
-        peft: in_features=2*inter, out_features=hidden.
-        peft lora_A: [r*E, 2*inter], lora_B: [hidden, r*E].
-
-        scattermoe W = param.T = [E, hidden, 2*inter], K=hidden, N=2*inter.
+        peft swaps in/out for 3D: lora_A [r*E, hidden], lora_B [2*inter, r*E].
        scattermoe needs: lora_A [r*E, K=hidden], lora_B [N=2*inter, r*E].
-
-        Uses non-square dims (hidden=32 != 2*inter=24) to catch A<->B swap bugs.
        """
        E, r = 4, 2
        hidden, inter = 32, 12  # 2*inter=24 != hidden=32
        scaling = 2.0

-        # peft assigns: in_features=2*inter, out_features=hidden
-        peft_A = torch.randn(E * r, 2 * inter)  # [r*E, in_features=2*inter]
-        peft_B = torch.randn(hidden, E * r)  # [out_features=hidden, r*E]
+        peft_A = torch.randn(E * r, hidden)  # [r*E, in=hidden]
+        peft_B = torch.randn(2 * inter, E * r)  # [out=2*inter, r*E]

-        # peft delta via einsum: "o r e, e r i -> e i o"
-        A_r = peft_A.reshape(E, r, 2 * inter)
-        B_r = peft_B.reshape(hidden, r, E)
-        delta_peft = torch.einsum("o r e, e r i -> e i o", B_r, A_r) * scaling
-        # delta_peft[e] has shape [in_features, out_features] = [2*inter, hidden]
-        # = param[e] shape [2*inter, hidden]
+        A_r = peft_A.reshape(E, r, hidden)
+        B_r = peft_B.reshape(2 * inter, r, E)
+        delta_peft = torch.einsum("o r e, e r i -> e o i", B_r, A_r) * scaling

        smoe_A, smoe_B = peft_gate_up_lora_to_scattermoe(peft_A, peft_B, E, r)
        # smoe_A should be [r*E, K=hidden], smoe_B should be [N=2*inter, r*E]
@@ -421,23 +398,21 @@ class TestPeftLoRAWeightExtraction:
            r,
        )

-        # gate_up_proj [E, 2*inter, hidden]
-        # peft: in_features=2*inter (dim 1), out_features=hidden (dim 2)
+        # gate_up_proj [E, 2*inter, hidden] — peft swaps in/out for 3D
        assert trainable[
            "base_model.model.moe.experts.base_layer.lora_A.default.weight"
-        ].shape == (E * r, 2 * config.intermediate_size)
-        assert trainable[
-            "base_model.model.moe.experts.base_layer.lora_B.default.weight"
-        ].shape == (config.hidden_size, E * r)
-
-        # down_proj [E, hidden, inter]
-        # peft: in_features=hidden (dim 1), out_features=inter (dim 2)
-        assert trainable[
-            "base_model.model.moe.experts.lora_A.default.weight"
        ].shape == (E * r, config.hidden_size)
+        assert trainable[
+            "base_model.model.moe.experts.base_layer.lora_B.default.weight"
+        ].shape == (2 * config.intermediate_size, E * r)
+
+        # down_proj [E, hidden, inter] — peft swaps in/out for 3D
+        assert trainable[
+            "base_model.model.moe.experts.lora_A.default.weight"
+        ].shape == (E * r, config.intermediate_size)
        assert trainable[
            "base_model.model.moe.experts.lora_B.default.weight"
-        ].shape == (config.intermediate_size, E * r)
+        ].shape == (config.hidden_size, E * r)

    @requires_cuda
    def test_peft_forward_runs(self):
@@ -488,8 +463,7 @@ class TestPeftLoRAWeightExtraction:
        assert gup_lora is not None, "gate_up_proj LoRA not detected"
        assert down_lora is not None, "down_proj LoRA not detected"

-        # Check shapes (after peft->scattermoe conversion with A<->B swap)
-        # gate_up_proj W = param.T = [E, hidden, 2*inter], K=hidden, N=2*inter
+        # gate_up_proj: K=hidden, N=2*inter
        E, r = config.num_experts, 4
        gup_A, gup_B, gup_s = gup_lora
        assert gup_A.shape == (E * r, config.hidden_size), (
@@ -501,7 +475,7 @@ class TestPeftLoRAWeightExtraction:
            f"{(2 * config.intermediate_size, E * r)}, got {gup_B.shape}"
        )

-        # down_proj W = param.T = [E, inter, hidden], K=inter, N=hidden
+        # down_proj: K=inter, N=hidden
        down_A, down_B, down_s = down_lora
        assert down_A.shape == (E * r, config.intermediate_size), (
            f"down_proj smoe_A: expected [r*E, K=inter]={(E * r, config.intermediate_size)}, "
--- a/tests/e2e/patched/test_unsloth_integration.py
+++ b/tests/e2e/patched/test_unsloth_integration.py
@@ -1,21 +0,0 @@
-"""Test module for checking whether the integration of Unsloth with Hugging Face Transformers is working as expected."""
-
-import unittest
-
-import pytest
-
-
-@pytest.mark.skip(
-    reason="Unsloth integration will be broken going into latest transformers"
-)
-class TestUnslothIntegration(unittest.TestCase):
-    """Unsloth monkeypatch integration tests."""
-
-    def test_is_self_attn_patchable(self):
-        from axolotl.monkeypatch.unsloth_ import check_self_attn_is_patchable
-
-        # ensures the current version of transformers has loss code that matches our patching code
-        self.assertTrue(
-            check_self_attn_is_patchable(),
-            "HF transformers self attention code has changed and isn't patchable",
-        )
--- a/tests/e2e/patched/test_unsloth_qlora.py
+++ b/tests/e2e/patched/test_unsloth_qlora.py
@@ -1,184 +0,0 @@
-"""
-e2e tests for unsloth qlora
-"""
-
-import pytest
-
-from axolotl.common.datasets import load_datasets
-from axolotl.train import train
-from axolotl.utils.config import normalize_config, validate_config
-from axolotl.utils.dict import DictDefault
-
-from ..utils import check_model_output_exists, check_tensorboard
-
-
-@pytest.mark.skip(
-    reason="Unsloth integration will be broken going into latest transformers"
-)
-class TestUnslothQLoRA:
-    """
-    Test class for Unsloth QLoRA Llama models
-    """
-
-    @pytest.mark.parametrize(
-        "sample_packing",
-        [True, False],
-    )
-    def test_unsloth_llama_qlora_fa2(self, temp_dir, sample_packing):
-        cfg = DictDefault(
-            {
-                "base_model": "HuggingFaceTB/SmolLM2-135M",
-                "sequence_len": 1024,
-                "sample_packing": sample_packing,
-                "flash_attention": True,
-                "unsloth_lora_mlp": True,
-                "unsloth_lora_qkv": True,
-                "unsloth_lora_o": True,
-                "load_in_4bit": True,
-                "adapter": "qlora",
-                "lora_r": 16,
-                "lora_alpha": 16,
-                "lora_dropout": 0.05,
-                "lora_target_linear": True,
-                "val_set_size": 0.05,
-                "special_tokens": {
-                    "pad_token": "<|endoftext|>",
-                },
-                "datasets": [
-                    {
-                        "path": "mhenrichsen/alpaca_2k_test",
-                        "type": "alpaca",
-                    },
-                ],
-                "num_epochs": 1,
-                "max_steps": 5,
-                "save_steps": 10,
-                "micro_batch_size": 4,
-                "gradient_accumulation_steps": 2,
-                "output_dir": temp_dir,
-                "learning_rate": 0.00001,
-                "optimizer": "adamw_8bit",
-                "lr_scheduler": "cosine",
-                "use_tensorboard": True,
-                "bf16": "auto",
-                "save_first_step": False,
-            }
-        )
-
-        cfg = validate_config(cfg)
-        normalize_config(cfg)
-        dataset_meta = load_datasets(cfg=cfg)
-
-        train(cfg=cfg, dataset_meta=dataset_meta)
-        check_model_output_exists(temp_dir, cfg)
-
-        check_tensorboard(
-            temp_dir + "/runs", "train/train_loss", 2.0, "Train Loss (%s) is too high"
-        )
-
-    def test_unsloth_llama_qlora_unpacked(self, temp_dir):
-        cfg = DictDefault(
-            {
-                "base_model": "HuggingFaceTB/SmolLM2-135M",
-                "sequence_len": 1024,
-                "unsloth_lora_mlp": True,
-                "unsloth_lora_qkv": True,
-                "unsloth_lora_o": True,
-                "sample_packing": False,
-                "load_in_4bit": True,
-                "adapter": "qlora",
-                "lora_r": 16,
-                "lora_alpha": 16,
-                "lora_dropout": 0.05,
-                "lora_target_linear": True,
-                "val_set_size": 0.05,
-                "special_tokens": {
-                    "pad_token": "<|endoftext|>",
-                },
-                "datasets": [
-                    {
-                        "path": "mhenrichsen/alpaca_2k_test",
-                        "type": "alpaca",
-                    },
-                ],
-                "num_epochs": 1,
-                "max_steps": 5,
-                "save_steps": 10,
-                "micro_batch_size": 4,
-                "gradient_accumulation_steps": 2,
-                "output_dir": temp_dir,
-                "learning_rate": 0.00001,
-                "optimizer": "adamw_8bit",
-                "lr_scheduler": "cosine",
-                "use_tensorboard": True,
-                "bf16": "auto",
-                "save_first_step": False,
-            }
-        )
-
-        cfg = validate_config(cfg)
-        normalize_config(cfg)
-        dataset_meta = load_datasets(cfg=cfg)
-
-        train(cfg=cfg, dataset_meta=dataset_meta)
-        check_model_output_exists(temp_dir, cfg)
-
-        check_tensorboard(
-            temp_dir + "/runs", "train/train_loss", 2.0, "Train Loss (%s) is too high"
-        )
-
-    @pytest.mark.parametrize(
-        "sdp_attention",
-        [True, False],
-    )
-    def test_unsloth_llama_qlora_unpacked_no_fa2_fp16(self, temp_dir, sdp_attention):
-        cfg = DictDefault(
-            {
-                "base_model": "HuggingFaceTB/SmolLM2-135M",
-                "sequence_len": 1024,
-                "unsloth_lora_mlp": True,
-                "unsloth_lora_qkv": True,
-                "unsloth_lora_o": True,
-                "sample_packing": False,
-                "load_in_4bit": True,
-                "adapter": "qlora",
-                "lora_r": 16,
-                "lora_alpha": 16,
-                "lora_dropout": 0.05,
-                "lora_target_linear": True,
-                "val_set_size": 0.05,
-                "special_tokens": {
-                    "pad_token": "<|endoftext|>",
-                },
-                "datasets": [
-                    {
-                        "path": "mhenrichsen/alpaca_2k_test",
-                        "type": "alpaca",
-                    },
-                ],
-                "num_epochs": 1,
-                "max_steps": 5,
-                "save_steps": 10,
-                "micro_batch_size": 4,
-                "gradient_accumulation_steps": 2,
-                "sdp_attention": sdp_attention,
-                "output_dir": temp_dir,
-                "learning_rate": 0.00001,
-                "optimizer": "adamw_8bit",
-                "lr_scheduler": "cosine",
-                "use_tensorboard": True,
-                "fp16": True,
-                "save_first_step": False,
-            }
-        )
-
-        cfg = validate_config(cfg)
-        normalize_config(cfg)
-        dataset_meta = load_datasets(cfg=cfg)
-
-        train(cfg=cfg, dataset_meta=dataset_meta)
-        check_model_output_exists(temp_dir, cfg)
-
-        check_tensorboard(
-            temp_dir + "/runs", "train/train_loss", 2.0, "Train Loss (%s) is too high"
-        )
--- a/tests/prompt_strategies/test_dpo_chat_templates.py
+++ b/tests/prompt_strategies/test_dpo_chat_templates.py
@@ -111,7 +111,7 @@ def fixture_argilla_chat_dataset():
@pytest.fixture(name="phi3_tokenizer")
@enable_hf_offline
 def fixture_phi3_tokenizer():
-    tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-medium-128k-instruct")
+    tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-4k-instruct")

    return tokenizer

@@ -214,8 +214,8 @@ class TestAssistantDPOChatTemplatePhi3:
            + "<|user|>\ngoodbye<|end|>\n"
            + "<|assistant|>\n"
        )
-        assert result["chosen"] == "goodbye<|end|>"
-        assert result["rejected"] == "party on<|end|>"
+        assert result["chosen"] == "goodbye<|end|>\n<|endoftext|>"
+        assert result["rejected"] == "party on<|end|>\n<|endoftext|>"


 class TestAssistantDPOChatTemplateGemma:
@@ -290,8 +290,8 @@ class TestArgillaChatDPOChatTemplate:
        )
        result = transform_fn(argilla_chat_dataset[0], tokenizer=phi3_tokenizer)
        assert result["prompt"] == "<|user|>\nhello<|end|>\n" + "<|assistant|>\n"
-        assert result["chosen"] == "goodbye<|end|>"
-        assert result["rejected"] == "party on<|end|>"
+        assert result["chosen"] == "goodbye<|end|>\n<|endoftext|>"
+        assert result["rejected"] == "party on<|end|>\n<|endoftext|>"


 class TestDPOChatTemplateToolRole: