feat: add :cpu tag for amd64 CPU-only image

Introduces a VARIANT=gpu|cpu build arg to the Dockerfile. The cpu
variant uses ubuntu:22.04 (no CUDA base), installs torch+cpu and
onnxruntime (no GPU deps) via a separate pyproject-cpu.toml / uv-cpu.lock,
and is published as :cpu (dev-cpu on the dev branch) via a new
build-cpu CI job. Saves ~2 GB over the default GPU image.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

.github/workflows/docker-publish.yml

@@ -126,3 +126,58 @@ jobs:
       - name: Inspect image
         run: |
           docker buildx imagetools inspect ${{ steps.tags.outputs.tags }}
+
+  build-cpu:
+    name: Build CPU-only (amd64)
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+
+    steps:
+      - name: Free up disk space
+        run: |
+          sudo rm -rf /usr/share/dotnet
+          sudo rm -rf /opt/ghc
+          sudo rm -rf "/usr/local/share/boost"
+          sudo rm -rf "$AGENT_TOOLSDIRECTORY"
+          echo "Disk space freed."
+
+      - name: Checkout repository
+        uses: actions/checkout@v6
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v4
+
+      - name: Log in to GHCR
+        uses: docker/login-action@v4
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Determine CPU image tag
+        id: cpu-tag
+        run: |
+          if [ "${{ github.ref_name }}" = "dev" ]; then
+            echo "tag=${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:dev-cpu" >> "$GITHUB_OUTPUT"
+          else
+            echo "tag=${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:cpu" >> "$GITHUB_OUTPUT"
+          fi
+
+      - name: Build and push CPU image
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          file: ./Dockerfile
+          platforms: linux/amd64
+          build-args: VARIANT=cpu
+          cache-from: type=gha,scope=linux/amd64-cpu
+          cache-to: type=gha,mode=max,scope=linux/amd64-cpu
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          push: true
+          tags: ${{ steps.cpu-tag.outputs.tag }}
+
+      - name: Inspect CPU image
+        run: |
+          docker buildx imagetools inspect ${{ steps.cpu-tag.outputs.tag }}

Dockerfile

@@ -1,20 +1,25 @@
-# ── Platform-conditional base ─────────────────────────────────────────────
+# ── Base images ───────────────────────────────────────────────────────────────
-#   amd64:  NVIDIA CUDA 13.3 (GPU acceleration when available, CPU fallback)
+#   amd64 + gpu:  NVIDIA CUDA 13.3 + cuDNN (GPU acceleration when available)
-#   arm64:  Ubuntu 24.04 (CPU-only; no CUDA on ARM)
+#   amd64 + cpu:  Ubuntu 22.04 (CPU-only, ~2 GB smaller image)
+#   arm64:        Ubuntu 24.04 (CPU-only; no CUDA wheels on ARM)
 
-FROM --platform=$BUILDPLATFORM nvidia/cuda:13.3.0-cudnn-runtime-ubuntu22.04 AS base-amd64
+ARG VARIANT=gpu
-FROM ubuntu:24.04 AS base-arm64
 
-# ── Build stage ───────────────────────────────────────────────────────────
+FROM --platform=$BUILDPLATFORM nvidia/cuda:13.3.0-cudnn-runtime-ubuntu22.04 AS base-amd64-gpu
+FROM ubuntu:22.04 AS base-amd64-cpu
+FROM ubuntu:24.04 AS base-arm64-gpu
+FROM ubuntu:24.04 AS base-arm64-cpu
+
+# ── Build stage ───────────────────────────────────────────────────────────────
 ARG TARGETARCH
 
-FROM base-${TARGETARCH} AS build
+FROM base-${TARGETARCH}-${VARIANT} AS build
 
+ARG VARIANT=gpu
 ENV DEBIAN_FRONTEND=noninteractive
 
-# Both bases (Ubuntu 22.04 CUDA / Ubuntu 24.04) need Python 3.13 from the
+# Both Ubuntu 22.04 and 24.04 get Python 3.13 from the deadsnakes PPA.
-# deadsnakes PPA. GNUPGHOME is isolated to a tmpdir so gpg never tries to
+# GNUPGHOME is isolated so gpg never contacts an agent socket under QEMU.
-# contact an agent socket, which fails silently under QEMU.
 RUN apt-get update && apt-get install -y --no-install-recommends \
     ca-certificates curl gnupg software-properties-common \
     && GNUPGHOME=$(mktemp -d) add-apt-repository ppa:deadsnakes/ppa -y \
@@ -30,20 +35,26 @@ RUN curl -LsSf https://astral.sh/uv/install.sh | sh \
 
 WORKDIR /app
 
-COPY pyproject.toml uv.lock ./
+# For cpu variant, swap in the CPU-only pyproject and lockfile before syncing.
-RUN uv sync --frozen --no-dev \
+COPY pyproject.toml uv.lock pyproject-cpu.toml uv-cpu.lock ./
+RUN if [ "$VARIANT" = "cpu" ]; then \
+        cp pyproject-cpu.toml pyproject.toml && \
+        cp uv-cpu.lock uv.lock; \
+    fi && \
+    uv sync --frozen --no-dev \
     && uv cache clean
 
 COPY winnow/ winnow/
 COPY entrypoint.sh scheduler.py ./
 RUN chmod +x /app/entrypoint.sh
 
-# ── Runtime stage ─────────────────────────────────────────────────────────
+# ── Runtime stage ─────────────────────────────────────────────────────────────
 #   Starts fresh from the base image — excludes build tools (g++,
 #   python3.13-dev, gnupg, software-properties-common) not needed at runtime.
 
-FROM base-${TARGETARCH} AS runtime
+FROM base-${TARGETARCH}-${VARIANT} AS runtime
 
+ARG VARIANT=gpu
 ENV DEBIAN_FRONTEND=noninteractive
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
@@ -61,8 +72,9 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
 COPY --from=build /app /app
 COPY --from=build /usr/local/bin/uv /usr/local/bin/uv
 
-# Expose CUDA/cuDNN libraries from pip packages so onnxruntime-gpu
+# Expose CUDA/cuDNN libraries from pip packages so onnxruntime-gpu can find
-# can find libcublasLt.so.12 and libcudnn.so.9 at runtime (amd64 only)
+# libcublasLt.so.12 and libcudnn.so.9 at runtime (amd64-gpu only).
+# On cpu builds these paths don't exist; non-existent entries are ignored.
 ENV LD_LIBRARY_PATH="/app/.venv/lib/python3.13/site-packages/nvidia/cudnn/lib:/app/.venv/lib/python3.13/site-packages/nvidia/cuda_runtime/lib:${LD_LIBRARY_PATH}"
 
 RUN groupadd -g 568 apps && useradd -u 568 -g apps -m -s /bin/bash appuser \

README.md

@@ -111,12 +111,19 @@ If the embedding model is unavailable, the tool falls back to **time spread**: e
 
 ## Running in Docker
 
+### Image Tags
+
+| Tag | Arch | GPU | Notes |
+| :-- | :-- | :-- | :-- |
+| `:latest` | amd64 + arm64 | CUDA 13.3 (amd64) | Requires NVIDIA Container Toolkit on amd64 |
+| `:cpu` | amd64 | None | ~2 GB smaller; use if you have no NVIDIA GPU |
+
 ### Quick Start
 
 ```yaml
 services:
   winnow:
-    image: ghcr.io/sudolulo/winnow:latest
+    image: ghcr.io/sudolulo/winnow:latest   # or :cpu for CPU-only amd64
     environment:
       - IMMICH_URL=http://192.168.1.10:2283
       - API_KEY=your-immich-api-key
@@ -136,6 +143,8 @@ services:
               capabilities: [gpu]
 ```
 
+> **CPU users (`:cpu` tag):** remove the `deploy.resources` block — no NVIDIA runtime needed.
+
 See [compose.yml](compose.yml) for the full annotated example.
 
 ### Scheduling Behaviour

pyproject-cpu.toml

@@ -0,0 +1,93 @@
+[project]
+name = "winnow"
+version = "0.2.9"
+description = "Immich to Frigate training sets"
+license = "AGPL-3.0-or-later"
+requires-python = ">=3.13"
+authors = [{ name = "Holden Salomon", email = "holden@arch.fyi" }]
+keywords = ["immich", "frigate", "face-recognition", "training-data", "arcface", "insightface"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: GNU Affero General Public License v3 or later (AGPLv3+)",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Scientific/Engineering :: Image Recognition",
+]
+dependencies = [
+    "croniter>=5.0.2",
+    "insightface>=0.7.3",
+    "numpy>=2.2.6",
+    "onnxruntime>=1.23.2",
+    "opencv-python-headless>=4.12.0.88",
+    "pillow>=12.1.0",
+    "python-dotenv>=1.2.1",
+    "requests>=2.32.5",
+    "rich>=14.2.0",
+    "torch>=2.12.0",
+    "torchvision>=0.27.0",
+    "transformers>=4.57.6",
+    "ultralytics>=8.4.66",
+]
+
+[project.scripts]
+winnow = "winnow.cli:main"
+
+[project.urls]
+Repository = "https://github.com/sudolulo/winnow"
+
+[tool.uv]
+required-environments = [
+    "sys_platform == 'linux' and platform_machine == 'x86_64'",
+]
+
+[tool.uv.sources]
+torch = [
+    { index = "pytorch-cpu", marker = "sys_platform == 'linux' and platform_machine == 'x86_64'" },
+]
+torchvision = [
+    { index = "pytorch-cpu", marker = "sys_platform == 'linux' and platform_machine == 'x86_64'" },
+]
+
+[[tool.uv.index]]
+name = "pytorch-cpu"
+url = "https://download.pytorch.org/whl/cpu"
+explicit = true
+
+[dependency-groups]
+dev = [
+    "pytest>=8.0",
+    "ruff>=0.15.17",
+]
+
+[tool.hatch.build.targets.wheel]
+packages = ["winnow"]
+
+[tool.ruff]
+line-length = 120
+target-version = "py313"
+
+[tool.ruff.lint]
+select = ["E", "F", "I"]
+
+[tool.deptry]
+pep621_dev_dependency_groups = ["dev"]
+
+[tool.deptry.package_module_name_map]
+pillow = "PIL"
+opencv-python-headless = "cv2"
+python-dotenv = "dotenv"
+insightface = "insightface"
+numpy = "numpy"
+onnxruntime = "onnxruntime"
+requests = "requests"
+rich = "rich"
+torch = "torch"
+transformers = "transformers"
+ultralytics = "ultralytics"
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"