chore: sync dev to main (0.2.11 release)

- fix: resolve onnxruntime/onnxruntime-gpu conflict clobbering GPU support
- perf: stream thumbnail download in bounded batches to cap peak RAM
- fix: log thumbnail fetch failures; restore get() for duplicate-ID safety
- ci: cancel in-progress Docker builds on superseding push
- ci: enforce GHCR package visibility public after each push
- docs: README and wiki updated with memory guidance and GPU troubleshooting

.env.example

@@ -4,7 +4,10 @@ API_KEY=your-immich-api-key
 FRIGATE_URL=http://192.168.1.10:5000
 
 # ── Mode & Strategy ───────────────────────────────────────────────────────────
-AUTO_MODE=true
+# Auto mode is active by default when no TTY is present (Docker/cron).
+# Set AUTO_MODE=true to force auto mode even in an interactive terminal.
+# AUTO_MODE=true
+# VERBOSE=true                # Enable DEBUG-level console output (log file is always DEBUG)
 # TRAINING_MODE: face = upload to Frigate face recognition API
 #                object = save crops to output dir for manual Frigate placement
 TRAINING_MODE=face
@@ -29,8 +32,8 @@ STRATEGY=auto
 # MAX_AUTO_IMAGES=80          # Hard cap on auto-diversity selection (default: 80)
 
 # ── Caching & Models ──────────────────────────────────────────────────────────
-FORCE_CPU=false
+# FORCE_CPU=true              # Disable GPU, fall back to CPU
-ENABLE_CACHE=true
+# ENABLE_CACHE=false          # Disable embedding cache (default: true)
 CACHE_DIR=/app/.if_cache
 HF_HOME=/models/huggingface
 INSIGHTFACE_HOME=/models/.insightface
@@ -41,5 +44,10 @@ INSIGHTFACE_HOME=/models/.insightface
 # RESET_PERSON=John           # Clear uploaded+rejected history for one person
 
 # ── Scheduling ────────────────────────────────────────────────────────────────
-# Cron expression (unset = run once and exit)
+# CRON_SCHEDULE controls container lifetime:
-CRON_SCHEDULE=0 3 * * 0     # Every Sunday at 3 AM
+#   unset          — run once on startup, then exit
+#   empty string   — stay alive, run nothing (trigger manually: docker exec -it winnow winnow)
+#   cron expression — run on startup, then on schedule
+# CRON_SCHEDULE=              # Manual mode (keep alive, no auto-run)
+# CRON_SCHEDULE=0 3 * * 0    # Every Sunday at 3 AM
+# CRON_SCHEDULE=0 3 1 * *    # First of every month

.github/workflows/docker-publish.yml

@@ -10,6 +10,10 @@ on:
       - ".github/workflows/lint.yml"
       - ".github/dependabot.yml"
 
+concurrency:
+  group: docker-${{ github.ref }}
+  cancel-in-progress: true
+
 env:
   REGISTRY: ghcr.io
   IMAGE_NAME: sudolulo/winnow
@@ -126,3 +130,72 @@ jobs:
       - name: Inspect image
         run: |
           docker buildx imagetools inspect ${{ steps.tags.outputs.tags }}
+
+      - name: Ensure package is public
+        run: |
+          gh api -X PATCH /user/packages/container/winnow \
+            -f visibility=public || true
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+  build-cpu:
+    name: Build CPU-only (amd64)
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+
+    steps:
+      - name: Free up disk space
+        run: |
+          sudo rm -rf /usr/share/dotnet
+          sudo rm -rf /opt/ghc
+          sudo rm -rf "/usr/local/share/boost"
+          sudo rm -rf "$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 }}
+
+      - name: Ensure package is public
+        run: |
+          gh api -X PATCH /user/packages/container/winnow \
+            -f visibility=public || true
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.gitignore

@@ -1,239 +1,36 @@
-# Custom
+# Output and runtime artefacts
 frigate_train/
 *.log
 runs/
+
+# Model and cache files
 yolov9c.pt
 .insightface/
 .huggingface/
-.cache/huggingface
 .if_cache/
-
 .immich_config.json
-# Python-generated files
-__pycache__/
-*.py[oc]
-build/
-dist/
-wheels/
-*.egg-info
 
-# Virtual environments
+# Secrets
-.venv
-
-# Byte-compiled / optimized / DLL files
-__pycache__/
-*.py[codz]
-*$py.class
-
-# C extensions
-*.so
-
-# Distribution / packaging
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-share/python-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
-
-# PyInstaller
-#   Usually these files are written by a python script from a template
-#   before PyInstaller builds the exe, so as to inject date/other infos into it.
-*.manifest
-*.spec
-
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
-
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.nox/
-.coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-*.py.cover
-.hypothesis/
-.pytest_cache/
-cover/
-
-# Translations
-*.mo
-*.pot
-
-# Django stuff:
-*.log
-local_settings.py
-db.sqlite3
-db.sqlite3-journal
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-.pybuilder/
-target/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# IPython
-profile_default/
-ipython_config.py
-
-# pyenv
-#   For a library or package, you might want to ignore these files since the code is
-#   intended to run in multiple environments; otherwise, check them in:
-# .python-version
-
-# pipenv
-#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
-#   However, in case of collaboration, if having platform-specific dependencies or dependencies
-#   having no cross-platform support, pipenv may install dependencies that don't work, or not
-#   install all needed dependencies.
-# Pipfile.lock
-
-# UV
-#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-# uv.lock
-
-# poetry
-#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
-# poetry.lock
-# poetry.toml
-
-# pdm
-#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
-#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
-#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
-# pdm.lock
-# pdm.toml
-.pdm-python
-.pdm-build/
-
-# pixi
-#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
-# pixi.lock
-#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
-#   in the .venv directory. It is recommended not to include this directory in version control.
-.pixi
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
-__pypackages__/
-
-# Celery stuff
-celerybeat-schedule
-celerybeat.pid
-
-# Redis
-*.rdb
-*.aof
-*.pid
-
-# RabbitMQ
-mnesia/
-rabbitmq/
-rabbitmq-data/
-
-# ActiveMQ
-activemq-data/
-
-# SageMath parsed files
-*.sage.py
-
-# Environments
 .env
 .envrc
-.venv
-env/
-venv/
-ENV/
-env.bak/
-venv.bak/
 
-# Spyder project settings
+# Python
-.spyderproject
+__pycache__/
-.spyproject
+*.py[oc]
+*.so
+.Python
 
-# Rope project settings
+# Packaging
-.ropeproject
+build/
+dist/
+*.egg-info/
+wheels/
 
-# mkdocs documentation
+# Virtual environments
-/site
+.venv/
 
-# mypy
+# Tools
-.mypy_cache/
-.dmypy.json
-dmypy.json
-
-# Pyre type checker
-.pyre/
-
-# pytype static type analyzer
-.pytype/
-
-# Cython debug symbols
-cython_debug/
-
-# PyCharm
-#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
-#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
-#   and can be added to the global gitignore or merged into this file.  For a more nuclear
-#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
-# .idea/
-
-# Abstra
-#   Abstra is an AI-powered process automation framework.
-#   Ignore directories containing user credentials, local state, and settings.
-#   Learn more at https://abstra.io/docs
-.abstra/
-
-# Visual Studio Code
-#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
-#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
-#   and can be added to the global gitignore or merged into this file. However, if you prefer, 
-#   you could uncomment the following to ignore the entire vscode folder
-# .vscode/
-
-# Ruff stuff:
 .ruff_cache/
-
+.pytest_cache/
-# PyPI configuration file
+.mypy_cache/
-.pypirc
+.python-version
-
-# Marimo
-marimo/_static/
-marimo/_lsp/
-__marimo__/
-
-# Streamlit
-.streamlit/secrets.toml
-compose.override.yml

.python-version

@@ -1 +0,0 @@
-3.13

CHANGELOG.md

@@ -7,6 +7,76 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.2.11] - 2026-06-12
+
+### Fixed
+
+- **GPU broken on x86_64 Linux**: `insightface` 1.0.1 (pulled in by the 0.2.10 lock update) added a hard dependency on the CPU `onnxruntime` package. Combined with an incorrect `override-dependencies` entry introduced in 0.2.10, both `onnxruntime` (CPU) and `onnxruntime-gpu` were being installed into the same venv. The CPU package landed last and overwrote the GPU one, causing `CUDAExecutionProvider` to disappear from the provider list even when a GPU was present. Fixed by declaring `onnxruntime` and `onnxruntime-gpu` as conflicting packages in uv's resolver, ensuring only the correct one is installed per platform.
+- **OOM crash on large person libraries (CPU mode)**: All candidate thumbnails were downloaded into a single in-memory dict before any processing began. At ~5 MB per decoded preview image, a person with 472 candidates would accumulate ~2.4 GB of thumbnail data alone, exhausting a 4 GB container memory limit. Thumbnails are now downloaded and processed in batches of 32, with each image released immediately after embedding. Peak in-flight thumbnail memory is now bounded to ~256 MB regardless of candidate pool size. GPU users also benefit from lower host RAM pressure and faster time-to-first-result on large libraries.
+
+## [0.2.10] - 2026-06-12
+
+### Added
+
+- **`VERBOSE` env var**: set `VERBOSE=true` to enable DEBUG-level console output. The log file always captures DEBUG; this flag controls what appears on the terminal. Useful when diagnosing issues without a full shell into the container.
+- **`:cpu` Docker image tag**: a separate CPU-only image (`ghcr.io/sudolulo/winnow:cpu`) is now built and pushed alongside `:latest`. Uses `onnxruntime` instead of `onnxruntime-gpu`; ~2 GB smaller. Suitable for systems without an NVIDIA GPU.
+- **Empty `CRON_SCHEDULE` keeps container alive**: setting `CRON_SCHEDULE=` (empty string) starts the container without running immediately and without exiting — useful for `docker exec` ad-hoc runs on a long-lived container. Previously, an empty value was treated the same as unset (run once, then exit).
+
+### Changed
+
+- **TTY auto-detection replaces `AUTO_MODE`**: winnow now detects whether a TTY is attached (`sys.stdin.isatty()`) and switches between interactive and auto mode automatically. `AUTO_MODE=true` becomes an explicit override for forcing auto mode in a terminal session. No config change needed for normal Docker deployments.
+- **Logging levels audited**: internal algorithmic detail (clustering steps, asset fetch progress, per-page pagination) demoted from INFO to DEBUG. INFO now reflects meaningful pipeline milestones only (model ready, selection complete, quality filtered). Reduces noise in production logs without losing information.
+- **Model load logging improved**: SigLIP and InsightFace loading now reports cache hit/miss, download size estimate, device used, and load time.
+
+### Fixed
+
+- **GPU OOM crash loop (production)**: `CUDAExecutionProvider` was silently absent even with a GPU attached, causing InsightFace to run on CPU and exhaust RAM processing large person libraries. Root cause: CUDA/cuDNN libraries in nvidia pip packages were invisible to onnxruntime. Fixed by running `ldconfig` over all `nvidia-*/lib/` directories in the venv at image build time.
+- **ldconfig path now Python-version-agnostic**: the `find` command used to register nvidia pip libraries hardcoded `python3.13`; replaced with `python3.*` glob so the path survives a Python upgrade without silently producing an empty ldconfig config.
+- **`PYTHONPATH=/app` added to Dockerfile**: the entry point script sets `sys.path[0]` to the script directory, not `/app`. Since `uv sync` runs before `COPY winnow/`, the wheel has only dist-info in site-packages. `PYTHONPATH=/app` makes the `winnow` package importable without reverting to `python -m`.
+- **CPU fallback retrying broken GPU provider**: InsightFace CPU fallback omitted `providers=["CPUExecutionProvider"]`, causing onnxruntime to retry `CUDAExecutionProvider` on every inference call. Now explicitly sets the CPU provider and suppresses C-extension noise via fd-level redirect.
+- **`_suppress_output` stderr loss on fd exhaustion**: if the first `os.dup2` in the finally block raised `OSError`, the second call was skipped, permanently redirecting stderr to `/dev/null` for the process lifetime. Wrapped in nested `try/finally` so both restores are always attempted.
+- **Frigate `/api/faces` response parsing**: the response is `{person_name: [files], "train": [...]}` — `"train"` is a flat pending list, not a person. Previous code called `.items()` on the `"train"` value (a list), crashing with `AttributeError`. Now skips the `"train"` key explicitly.
+- **Immich 401 detection**: a stale or invalid API key now logs a clear error message (`Immich API key is invalid or expired (401 Unauthorized)`) instead of raising an unhandled exception.
+- **Falsy-zero detection confidence**: `face.get("score") or face.get("confidence")` treated a valid `score=0.0` as falsy, falling through to the `confidence` field (often `None`). Replaced with an explicit `None` check. Affected both quality filtering and hard-example weighting in diversity selection.
+- **Face crop using wrong person's image dimensions**: in multi-person assets, `_crop_face_from_thumbnail`'s scale-factor loop matched the first person with any face regardless of `person_id`, producing incorrectly scaled bounding box coordinates for the target person. Loop now applies the same `person_id` filter as `_get_face_bbox`.
+- **Adaptive stopping bypassed for partially-trained people**: in auto mode with `already_uploaded > 0`, `limit` was converted from `"auto"` to an integer, disabling the FPS adaptive threshold and early-stop check. Now keeps `limit="auto"` through selection and trims the result to the remaining capacity afterward.
+- **Embedding cache key mismatch**: HuggingFace cache path check hardcoded the model slug string; replaced with a derivation from `model_name` using `"models--" + model_name.replace("/", "--")` so the check stays correct if the model name changes.
+- **Scheduler: sleep until next run**: the loop slept a fixed 60 seconds regardless of schedule interval, causing runs to fire up to 59 seconds late and waking the process unnecessarily on long schedules (e.g. weekly). Now sleeps exactly until `next_run`.
+- **Scheduler swallowing `SystemExit`**: `except BaseException` in the run wrapper was replaced with `except Exception` (with `KeyboardInterrupt` re-raised above), so `sys.exit()` calls propagate correctly.
+- **Log handler leak**: `setup_logging` now closes and removes existing handlers before adding new ones, preventing file handle accumulation across repeated calls.
+- **`RETRY_REJECTED` silently applied in interactive mode**: the env var was applied unconditionally even in interactive sessions. Now used only as the default for the interactive prompt so users can override it per-run.
+- **`compose.yml` comment inverted**: a comment stated `-it` forces non-interactive mode; corrected to reflect that `-it` allocates a TTY (interactive mode).
+
+### Security
+
+- API key is no longer stored in any config file. All authentication uses environment variables or `.env` only.
+
+## [0.2.9] - 2026-06-12
+
+### Fixed
+
+- **arm64: `onnxruntime-gpu` has no arm64 wheels**: `onnxruntime-gpu` only publishes `manylinux_2_27_x86_64` and `manylinux_2_28_x86_64` wheels — `uv sync` on arm64 failed with exit code 2. Gated `onnxruntime-gpu` behind `sys_platform == 'linux' and platform_machine == 'x86_64'`; arm64 and non-Linux installs now get the CPU `onnxruntime` package instead.
+- **uv lockfile now covers arm64**: Added `required-environments` to `[tool.uv]` so the lockfile is solved for both `linux/x86_64` and `linux/aarch64`, preventing silent resolution gaps for the non-build platform.
+
+## [0.2.8] - 2026-06-12
+
+### Fixed
+
+- **Dockerfile: use `add-apt-repository` with isolated GNUPGHOME**: the `curl | gpg --dearmor` approach was silently failing — gpg exits 0 on bad/empty input, leaving an invalid keyring and causing apt to skip the deadsnakes PPA entirely. Reverted to `add-apt-repository ppa:deadsnakes/ppa` with `GNUPGHOME=$(mktemp -d)` to prevent gpg from touching any pre-existing agent socket (the original QEMU crash cause).
+- **arm64 base: removed `--platform=$BUILDPLATFORM`**: the Ubuntu 24.04 base for arm64 is now pulled for the target platform, so the arm64 image contains real arm64 binaries rather than amd64 binaries in an arm64 manifest.
+
+### Changed
+
+- **License changed from MIT to AGPLv3+**: source and network use of winnow now require derivative works to be open-sourced under the same terms.
+
+## [0.2.7] - 2026-06-12
+
+### Fixed
+
+- **arm64 base reverted to Ubuntu 24.04**: Ubuntu 26.04 ships Python 3.14, not 3.13 — `python3.13` was not locatable in its repos. Reverted arm64 base to `ubuntu:24.04`.
+- **Deadsnakes PPA now uses curl+gpg instead of `add-apt-repository`**: `add-apt-repository` spawns a gpg-agent which crashes under QEMU (arm64 CI). The PPA is now added by fetching the key via `curl` and piping through `gpg --dearmor` — no agent, works on both architectures.
+- **PPA conditional removed**: both amd64 (Ubuntu 22.04 CUDA) and arm64 (Ubuntu 24.04) now go through the same deadsnakes install path, eliminating the per-arch branching and the `ARG TARGETARCH` dependency in RUN commands.
+
 ## [0.2.6] - 2026-06-12
 
 ### Fixed

Dockerfile

@@ -1,28 +1,29 @@
-# ── Platform-conditional base ─────────────────────────────────────────────
+# ── Base images ───────────────────────────────────────────────────────────────
-#   amd64:  NVIDIA CUDA 12.6 (GPU acceleration when available, CPU fallback)
+#   amd64 + gpu:  NVIDIA CUDA 13.3 + cuDNN (GPU acceleration when available)
-#   arm64:  Ubuntu 26.04 (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=$BUILDPLATFORM nvidia/cuda:13.3.0-cudnn-runtime-ubuntu22.04 AS base-amd64
+ARG VARIANT=gpu
-FROM --platform=$BUILDPLATFORM ubuntu:26.04 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 TARGETARCH
+ARG VARIANT=gpu
 ENV DEBIAN_FRONTEND=noninteractive
 
-# amd64 (Ubuntu 22.04 CUDA base): Python 3.13 via deadsnakes PPA
+# Both Ubuntu 22.04 and 24.04 get Python 3.13 from the deadsnakes PPA.
-# arm64 (Ubuntu 26.04): Python 3.13 available natively in repos
+# GNUPGHOME is isolated so gpg never contacts an agent socket under QEMU.
 RUN apt-get update && apt-get install -y --no-install-recommends \
-    ca-certificates \
+    ca-certificates curl gnupg software-properties-common \
-    curl \
+    && GNUPGHOME=$(mktemp -d) add-apt-repository ppa:deadsnakes/ppa -y \
-    && if [ "$TARGETARCH" = "amd64" ]; then \
+    && apt-get update \
-        apt-get install -y --no-install-recommends gnupg software-properties-common \
-        && add-apt-repository ppa:deadsnakes/ppa -y \
-        && apt-get update; \
-    fi \
     && apt-get install -y --no-install-recommends \
     python3.13 python3.13-venv python3.13-dev \
     libgl1 libglib2.0-0 libxext6 g++ \
@@ -34,34 +35,36 @@ 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, curl, gnupg) that are not needed at runtime.
+#   python3.13-dev, gnupg, software-properties-common) not needed at runtime.
 
-FROM base-${TARGETARCH} AS runtime
+FROM base-${TARGETARCH}-${VARIANT} AS runtime
 
-ARG TARGETARCH
+ARG VARIANT=gpu
 ENV DEBIAN_FRONTEND=noninteractive
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
-    ca-certificates \
+    ca-certificates curl gnupg software-properties-common tini \
-    tini \
+    && GNUPGHOME=$(mktemp -d) add-apt-repository ppa:deadsnakes/ppa -y \
-    && if [ "$TARGETARCH" = "amd64" ]; then \
+    && apt-get update \
-        apt-get install -y --no-install-recommends gnupg software-properties-common \
-        && add-apt-repository ppa:deadsnakes/ppa -y \
-        && apt-get update; \
-    fi \
     && apt-get install -y --no-install-recommends \
     python3.13 python3.13-venv \
     libgl1 libglib2.0-0 libxext6 \
+    && apt-get purge -y --auto-remove curl gnupg software-properties-common \
     && rm -rf /var/lib/apt/lists/* \
     && ln -sf /usr/bin/python3.13 /usr/bin/python3
 
@@ -69,9 +72,11 @@ 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
+# Register every nvidia pip-package lib/ directory with ldconfig so that
-# can find libcublasLt.so.12 and libcudnn.so.9 at runtime (amd64 only)
+# onnxruntime-gpu and torch can find libcudnn, libcublas, libcufft, etc.
-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}"
+# without a hand-maintained LD_LIBRARY_PATH. Skipped silently on cpu builds.
+RUN find /app/.venv/lib/python3.*/site-packages/nvidia -type d -name "lib" \
+        2>/dev/null > /etc/ld.so.conf.d/nvidia-pip.conf && ldconfig || true
 
 RUN groupadd -g 568 apps && useradd -u 568 -g apps -m -s /bin/bash appuser \
     && mkdir -p /models/.insightface /models/huggingface \
@@ -79,7 +84,10 @@ RUN groupadd -g 568 apps && useradd -u 568 -g apps -m -s /bin/bash appuser \
 
 WORKDIR /app
 USER appuser
-ENV HF_HOME=/models/huggingface INSIGHTFACE_HOME=/models
+# PYTHONPATH=/app makes the winnow package importable from the entry point script.
+# uv sync builds the wheel before winnow/ is COPY'd, so site-packages has only
+# the dist-info. Explicitly adding /app lets Python find winnow/__init__.py there.
+ENV HF_HOME=/models/huggingface INSIGHTFACE_HOME=/models/.insightface PYTHONPATH=/app
 
 HEALTHCHECK CMD test -f /app/entrypoint.sh || exit 1
 ENTRYPOINT ["tini", "--", "/app/entrypoint.sh"]

LICENSE

@@ -1,22 +1,661 @@
-MIT License
+                    GNU AFFERO GENERAL PUBLIC LICENSE
+                       Version 3, 19 November 2007
 
-Copyright (c) 2026 Holden Salomon
+ Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
-Copyright (c) 2026 Sebastian
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
 
-Permission is hereby granted, free of charge, to any person obtaining a copy
+                            Preamble
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
 
-The above copyright notice and this permission notice shall be included in all
+  The GNU Affero General Public License is a free, copyleft license for
-copies or substantial portions of the Software.
+software and other kinds of works, specifically designed to ensure
+cooperation with the community in the case of network server software.
 
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+  The licenses for most software and other practical works are designed
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+to take away your freedom to share and change the works.  By contrast,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+our General Public Licenses are intended to guarantee your freedom to
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+share and change all versions of a program--to make sure it remains free
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+software for all its users.
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+
-SOFTWARE.
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+them if you wish), that you receive source code or can get it if you
+want it, that you can change the software or use pieces of it in new
+free programs, and that you know you can do these things.
+
+  Developers that use our General Public Licenses protect your rights
+with two steps: (1) assert copyright on the software, and (2) offer
+you this License which gives you legal permission to copy, distribute
+and/or modify the software.
+
+  A secondary benefit of defending all users' freedom is that
+improvements made in alternate versions of the program, if they
+receive widespread use, become available for other developers to
+incorporate.  Many developers of free software are heartened and
+encouraged by the resulting cooperation.  However, in the case of
+software used on network servers, this result may fail to come about.
+The GNU General Public License permits making a modified version and
+letting the public access it on a server without ever releasing its
+source code to the public.
+
+  The GNU Affero General Public License is designed specifically to
+ensure that, in such cases, the modified source code becomes available
+to the community.  It requires the operator of a network server to
+provide the source code of the modified version running there to the
+users of that server.  Therefore, public use of a modified version, on
+a publicly accessible server, gives the public access to the source
+code of the modified version.
+
+  An older license, called the Affero General Public License and
+published by Affero, was designed to accomplish similar goals.  This is
+a different license, not a version of the Affero GPL, but Affero has
+released a new version of the Affero GPL which permits relicensing under
+this license.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+                       TERMS AND CONDITIONS
+
+  0. Definitions.
+
+  "This License" refers to version 3 of the GNU Affero General Public License.
+
+  "Copyright" also means copyright-like laws that apply to other kinds of
+works, such as semiconductor masks.
+
+  "The Program" refers to any copyrightable work licensed under this
+License.  Each licensee is addressed as "you".  "Licensees" and
+"recipients" may be individuals or organizations.
+
+  To "modify" a work means to copy from or adapt all or part of the work
+in a fashion requiring copyright permission, other than the making of an
+exact copy.  The resulting work is called a "modified version" of the
+earlier work or a work "based on" the earlier work.
+
+  A "covered work" means either the unmodified Program or a work based
+on the Program.
+
+  To "propagate" a work means to do anything with it that, without
+permission, would make you directly or secondarily liable for
+infringement under applicable copyright law, except executing it on a
+computer or modifying a private copy.  Propagation includes copying,
+distribution (with or without modification), making available to the
+public, and in some countries other activities as well.
+
+  To "convey" a work means any kind of propagation that enables other
+parties to make or receive copies.  Mere interaction with a user through
+a computer network, with no transfer of a copy, is not conveying.
+
+  An interactive user interface displays "Appropriate Legal Notices"
+to the extent that it includes a convenient and prominently visible
+feature that (1) displays an appropriate copyright notice, and (2)
+tells the user that there is no warranty for the work (except to the
+extent that warranties are provided), that licensees may convey the
+work under this License, and how to view a copy of this License.  If
+the interface presents a list of user commands or options, such as a
+menu, a prominent item in the list meets this criterion.
+
+  1. Source Code.
+
+  The "source code" for a work means the preferred form of the work
+for making modifications to it.  "Object code" means any non-source
+form of a work.
+
+  A "Standard Interface" means an interface that either is an official
+standard defined by a recognized standards body, or, in the case of
+interfaces specified for a particular programming language, one that
+is widely used among developers working in that language.
+
+  The "System Libraries" of an executable work include anything, other
+than the work as a whole, that (a) is included in the normal form of
+packaging a Major Component, but which is not part of that Major
+Component, and (b) serves only to enable use of the work with that
+Major Component, or to implement a Standard Interface for which an
+implementation is available to the public in source code form.  A
+"Major Component", in this context, means a major essential component
+(kernel, window system, and so on) of the specific operating system
+(if any) on which the executable work runs, or a compiler used to
+produce the work, or an object code interpreter used to run it.
+
+  The "Corresponding Source" for a work in object code form means all
+the source code needed to generate, install, and (for an executable
+work) run the object code and to modify the work, including scripts to
+control those activities.  However, it does not include the work's
+System Libraries, or general-purpose tools or generally available free
+programs which are used unmodified in performing those activities but
+which are not part of the work.  For example, Corresponding Source
+includes interface definition files associated with source files for
+the work, and the source code for shared libraries and dynamically
+linked subprograms that the work is specifically designed to require,
+such as by intimate data communication or control flow between those
+subprograms and other parts of the work.
+
+  The Corresponding Source need not include anything that users
+can regenerate automatically from other parts of the Corresponding
+Source.
+
+  The Corresponding Source for a work in source code form is that
+same work.
+
+  2. Basic Permissions.
+
+  All rights granted under this License are granted for the term of
+copyright on the Program, and are irrevocable provided the stated
+conditions are met.  This License explicitly affirms your unlimited
+permission to run the unmodified Program.  The output from running a
+covered work is covered by this License only if the output, given its
+content, constitutes a covered work.  This License acknowledges your
+rights of fair use or other equivalent, as provided by copyright law.
+
+  You may make, run and propagate covered works that you do not
+convey, without conditions so long as your license otherwise remains
+in force.  You may convey covered works to others for the sole purpose
+of having them make modifications exclusively for you, or provide you
+with facilities for running those works, provided that you comply with
+the terms of this License in conveying all material for which you do
+not control copyright.  Those thus making or running the covered works
+for you must do so exclusively on your behalf, under your direction
+and control, on terms that prohibit them from making any copies of
+your copyrighted material outside their relationship with you.
+
+  Conveying under any other circumstances is permitted solely under
+the conditions stated below.  Sublicensing is not allowed; section 10
+makes it unnecessary.
+
+  3. Protecting Users' Legal Rights From Anti-Circumvention Law.
+
+  No covered work shall be deemed part of an effective technological
+measure under any applicable law fulfilling obligations under article
+11 of the WIPO copyright treaty adopted on 20 December 1996, or
+similar laws prohibiting or restricting circumvention of such
+measures.
+
+  When you convey a covered work, you waive any legal power to forbid
+circumvention of technological measures to the extent such circumvention
+is effected by exercising rights under this License with respect to
+the covered work, and you disclaim any intention to limit operation or
+modification of the work as a means of enforcing, against the work's
+users, your or third parties' legal rights to forbid circumvention of
+technological measures.
+
+  4. Conveying Verbatim Copies.
+
+  You may convey verbatim copies of the Program's source code as you
+receive it, in any medium, provided that you conspicuously and
+appropriately publish on each copy an appropriate copyright notice;
+keep intact all notices stating that this License and any
+non-permissive terms added in accord with section 7 apply to the code;
+keep intact all notices of the absence of any warranty; and give all
+recipients a copy of this License along with the Program.
+
+  You may charge any price or no price for each copy that you convey,
+and you may offer support or warranty protection for a fee.
+
+  5. Conveying Modified Source Versions.
+
+  You may convey a work based on the Program, or the modifications to
+produce it from the Program, in the form of source code under the
+terms of section 4, provided that you also meet all of these conditions:
+
+    a) The work must carry prominent notices stating that you modified
+    it, and giving a relevant date.
+
+    b) The work must carry prominent notices stating that it is
+    released under this License and any conditions added under section
+    7.  This requirement modifies the requirement in section 4 to
+    "keep intact all notices".
+
+    c) You must license the entire work, as a whole, under this
+    License to anyone who comes into possession of a copy.  This
+    License will therefore apply, along with any applicable section 7
+    additional terms, to the whole of the work, and all its parts,
+    regardless of how they are packaged.  This License gives no
+    permission to license the work in any other way, but it does not
+    invalidate such permission if you have separately received it.
+
+    d) If the work has interactive user interfaces, each must display
+    Appropriate Legal Notices; however, if the Program has interactive
+    interfaces that do not display Appropriate Legal Notices, your
+    work need not make them do so.
+
+  A compilation of a covered work with other separate and independent
+works, which are not by their nature extensions of the covered work,
+and which are not combined with it such as to form a larger program,
+in or on a volume of a storage or distribution medium, is called an
+"aggregate" if the compilation and its resulting copyright are not
+used to limit the access or legal rights of the compilation's users
+beyond what the individual works permit.  Inclusion of a covered work
+in an aggregate does not cause this License to apply to the other
+parts of the aggregate.
+
+  6. Conveying Non-Source Forms.
+
+  You may convey a covered work in object code form under the terms
+of sections 4 and 5, provided that you also convey the
+machine-readable Corresponding Source under the terms of this License,
+in one of these ways:
+
+    a) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by the
+    Corresponding Source fixed on a durable physical medium
+    customarily used for software interchange.
+
+    b) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by a
+    written offer, valid for at least three years and valid for as
+    long as you offer spare parts or customer support for that product
+    model, to give anyone who possesses the object code either (1) a
+    copy of the Corresponding Source for all the software in the
+    product that is covered by this License, on a durable physical
+    medium customarily used for software interchange, for a price no
+    more than your reasonable cost of physically performing this
+    conveying of source, or (2) access to copy the
+    Corresponding Source from a network server at no charge.
+
+    c) Convey individual copies of the object code with a copy of the
+    written offer to provide the Corresponding Source.  This
+    alternative is allowed only occasionally and noncommercially, and
+    only if you received the object code with such an offer, in accord
+    with subsection 6b.
+
+    d) Convey the object code by offering access from a designated
+    place (gratis or for a charge), and offer equivalent access to the
+    Corresponding Source in the same way through the same place at no
+    further charge.  You need not require recipients to copy the
+    Corresponding Source along with the object code.  If the place to
+    copy the object code is a network server, the Corresponding Source
+    may be on a different server (operated by you or a third party)
+    that supports equivalent copying facilities, provided you maintain
+    clear directions next to the object code saying where to find the
+    Corresponding Source.  Regardless of what server hosts the
+    Corresponding Source, you remain obligated to ensure that it is
+    available for as long as needed to satisfy these requirements.
+
+    e) Convey the object code using peer-to-peer transmission, provided
+    you inform other peers where the object code and Corresponding
+    Source of the work are being offered to the general public at no
+    charge under subsection 6d.
+
+  A separable portion of the object code, whose source code is excluded
+from the Corresponding Source as a System Library, need not be
+included in conveying the object code work.
+
+  A "User Product" is either (1) a "consumer product", which means any
+tangible personal property which is normally used for personal, family,
+or household purposes, or (2) anything designed or sold for incorporation
+into a dwelling.  In determining whether a product is a consumer product,
+doubtful cases shall be resolved in favor of coverage.  For a particular
+product received by a particular user, "normally used" refers to a
+typical or common use of that class of product, regardless of the status
+of the particular user or of the way in which the particular user
+actually uses, or expects or is expected to use, the product.  A product
+is a consumer product regardless of whether the product has substantial
+commercial, industrial or non-consumer uses, unless such uses represent
+the only significant mode of use of the product.
+
+  "Installation Information" for a User Product means any methods,
+procedures, authorization keys, or other information required to install
+and execute modified versions of a covered work in that User Product from
+a modified version of its Corresponding Source.  The information must
+suffice to ensure that the continued functioning of the modified object
+code is in no case prevented or interfered with solely because
+modification has been made.
+
+  If you convey an object code work under this section in, or with, or
+specifically for use in, a User Product, and the conveying occurs as
+part of a transaction in which the right of possession and use of the
+User Product is transferred to the recipient in perpetuity or for a
+fixed term (regardless of how the transaction is characterized), the
+Corresponding Source conveyed under this section must be accompanied
+by the Installation Information.  But this requirement does not apply
+if neither you nor any third party retains the ability to install
+modified object code on the User Product (for example, the work has
+been installed in ROM).
+
+  The requirement to provide Installation Information does not include a
+requirement to continue to provide support service, warranty, or updates
+for a work that has been modified or installed by the recipient, or for
+the User Product in which it has been modified or installed.  Access to a
+network may be denied when the modification itself materially and
+adversely affects the operation of the network or violates the rules and
+protocols for communication across the network.
+
+  Corresponding Source conveyed, and Installation Information provided,
+in accord with this section must be in a format that is publicly
+documented (and with an implementation available to the public in
+source code form), and must require no special password or key for
+unpacking, reading or copying.
+
+  7. Additional Terms.
+
+  "Additional permissions" are terms that supplement the terms of this
+License by making exceptions from one or more of its conditions.
+Additional permissions that are applicable to the entire Program shall
+be treated as though they were included in this License, to the extent
+that they are valid under applicable law.  If additional permissions
+apply only to part of the Program, that part may be used separately
+under those permissions, but the entire Program remains governed by
+this License without regard to the additional permissions.
+
+  When you convey a copy of a covered work, you may at your option
+remove any additional permissions from that copy, or from any part of
+it.  (Additional permissions may be written to require their own
+removal in certain cases when you modify the work.)  You may place
+additional permissions on material, added by you to a covered work,
+for which you have or can give appropriate copyright permission.
+
+  Notwithstanding any other provision of this License, for material you
+add to a covered work, you may (if authorized by the copyright holders of
+that material) supplement the terms of this License with terms:
+
+    a) Disclaiming warranty or limiting liability differently from the
+    terms of sections 15 and 16 of this License; or
+
+    b) Requiring preservation of specified reasonable legal notices or
+    author attributions in that material or in the Appropriate Legal
+    Notices displayed by works containing it; or
+
+    c) Prohibiting misrepresentation of the origin of that material, or
+    requiring that modified versions of such material be marked in
+    reasonable ways as different from the original version; or
+
+    d) Limiting the use for publicity purposes of names of licensors or
+    authors of the material; or
+
+    e) Declining to grant rights under trademark law for use of some
+    trade names, trademarks, or service marks; or
+
+    f) Requiring indemnification of licensors and authors of that
+    material by anyone who conveys the material (or modified versions of
+    it) with contractual assumptions of liability to the recipient, for
+    any liability that these contractual assumptions directly impose on
+    those licensors and authors.
+
+  All other non-permissive additional terms are considered "further
+restrictions" within the meaning of section 10.  If the Program as you
+received it, or any part of it, contains a notice stating that it is
+governed by this License along with a term that is a further
+restriction, you may remove that term.  If a license document contains
+a further restriction but permits relicensing or conveying under this
+License, you may add to a covered work material governed by the terms
+of that license document, provided that the further restriction does
+not survive such relicensing or conveying.
+
+  If you add terms to a covered work in accord with this section, you
+must place, in the relevant source files, a statement of the
+additional terms that apply to those files, or a notice indicating
+where to find the applicable terms.
+
+  Additional terms, permissive or non-permissive, may be stated in the
+form of a separately written license, or stated as exceptions;
+the above requirements apply either way.
+
+  8. Termination.
+
+  You may not propagate or modify a covered work except as expressly
+provided under this License.  Any attempt otherwise to propagate or
+modify it is void, and will automatically terminate your rights under
+this License (including any patent licenses granted under the third
+paragraph of section 11).
+
+  However, if you cease all violation of this License, then your
+license from a particular copyright holder is reinstated (a)
+provisionally, unless and until the copyright holder explicitly and
+finally terminates your license, and (b) permanently, if the copyright
+holder fails to notify you of the violation by some reasonable means
+prior to 60 days after the cessation.
+
+  Moreover, your license from a particular copyright holder is
+reinstated permanently if the copyright holder notifies you of the
+violation by some reasonable means, this is the first time you have
+received notice of violation of this License (for any work) from that
+copyright holder, and you cure the violation prior to 30 days after
+your receipt of the notice.
+
+  Termination of your rights under this section does not terminate the
+licenses of parties who have received copies or rights from you under
+this License.  If your rights have been terminated and not permanently
+reinstated, you do not qualify to receive new licenses for the same
+material under section 10.
+
+  9. Acceptance Not Required for Having Copies.
+
+  You are not required to accept this License in order to receive or
+run a copy of the Program.  Ancillary propagation of a covered work
+occurring solely as a consequence of using peer-to-peer transmission
+to receive a copy likewise does not require acceptance.  However,
+nothing other than this License grants you permission to propagate or
+modify any covered work.  These actions infringe copyright if you do
+not accept this License.  Therefore, by modifying or propagating a
+covered work, you indicate your acceptance of this License to do so.
+
+  10. Automatic Licensing of Downstream Recipients.
+
+  Each time you convey a covered work, the recipient automatically
+receives a license from the original licensors, to run, modify and
+propagate that work, subject to this License.  You are not responsible
+for enforcing compliance by third parties with this License.
+
+  An "entity transaction" is a transaction transferring control of an
+organization, or substantially all assets of one, or subdividing an
+organization, or merging organizations.  If propagation of a covered
+work results from an entity transaction, each party to that
+transaction who receives a copy of the work also receives whatever
+licenses to the work the party's predecessor in interest had or could
+give under the previous paragraph, plus a right to possession of the
+Corresponding Source of the work from the predecessor in interest, if
+the predecessor has it or can get it with reasonable efforts.
+
+  You may not impose any further restrictions on the exercise of the
+rights granted or affirmed under this License.  For example, you may
+not impose a license fee, royalty, or other charge for exercise of
+rights granted under this License, and you may not initiate litigation
+(including a cross-claim or counterclaim in a lawsuit) alleging that
+any patent claim is infringed by making, using, selling, offering for
+sale, or importing the Program or any portion of it.
+
+  11. Patents.
+
+  A "contributor" is a copyright holder who authorizes use under this
+License of the Program or a work on which the Program is based.  The
+work thus licensed is called the contributor's "contributor version".
+
+  A contributor's "essential patent claims" are all patent claims
+owned or controlled by the contributor, whether already acquired or
+hereafter acquired, that would be infringed by some manner, permitted
+by this License, of making, using, or selling its contributor version,
+but do not include claims that would be infringed only as a
+consequence of further modification of the contributor version.  For
+purposes of this definition, "control" includes the right to grant
+patent sublicenses in a manner consistent with the requirements of
+this License.
+
+  Each contributor grants you a non-exclusive, worldwide, royalty-free
+patent license under the contributor's essential patent claims, to
+make, use, sell, offer for sale, import and otherwise run, modify and
+propagate the contents of its contributor version.
+
+  In the following three paragraphs, a "patent license" is any express
+agreement or commitment, however denominated, not to enforce a patent
+(such as an express permission to practice a patent or covenant not to
+sue for patent infringement).  To "grant" such a patent license to a
+party means to make such an agreement or commitment not to enforce a
+patent against the party.
+
+  If you convey a covered work, knowingly relying on a patent license,
+and the Corresponding Source of the work is not available for anyone
+to copy, free of charge and under the terms of this License, through a
+publicly available network server or other readily accessible means,
+then you must either (1) cause the Corresponding Source to be so
+available, or (2) arrange to deprive yourself of the benefit of the
+patent license for this particular work, or (3) arrange, in a manner
+consistent with the requirements of this License, to extend the patent
+license to downstream recipients.  "Knowingly relying" means you have
+actual knowledge that, but for the patent license, your conveying the
+covered work in a country, or your recipient's use of the covered work
+in a country, would infringe one or more identifiable patents in that
+country that you have reason to believe are valid.
+
+  If, pursuant to or in connection with a single transaction or
+arrangement, you convey, or propagate by procuring conveyance of, a
+covered work, and grant a patent license to some of the parties
+receiving the covered work authorizing them to use, propagate, modify
+or convey a specific copy of the covered work, then the patent license
+you grant is automatically extended to all recipients of the covered
+work and works based on it.
+
+  A patent license is "discriminatory" if it does not include within
+the scope of its coverage, prohibits the exercise of, or is
+conditioned on the non-exercise of one or more of the rights that are
+specifically granted under this License.  You may not convey a covered
+work if you are a party to an arrangement with a third party that is
+in the business of distributing software, under which you make payment
+to the third party based on the extent of your activity of conveying
+the work, and under which the third party grants, to any of the
+parties who would receive the covered work from you, a discriminatory
+patent license (a) in connection with copies of the covered work
+conveyed by you (or copies made from those copies), or (b) primarily
+for and in connection with specific products or compilations that
+contain the covered work, unless you entered into that arrangement,
+or that patent license was granted, prior to 28 March 2007.
+
+  Nothing in this License shall be construed as excluding or limiting
+any implied license or other defenses to infringement that may
+otherwise be available to you under applicable patent law.
+
+  12. No Surrender of Others' Freedom.
+
+  If conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot convey a
+covered work so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you may
+not convey it at all.  For example, if you agree to terms that obligate you
+to collect a royalty for further conveying from those to whom you convey
+the Program, the only way you could satisfy both those terms and this
+License would be to refrain entirely from conveying the Program.
+
+  13. Remote Network Interaction; Use with the GNU General Public License.
+
+  Notwithstanding any other provision of this License, if you modify the
+Program, your modified version must prominently offer all users
+interacting with it remotely through a computer network (if your version
+supports such interaction) an opportunity to receive the Corresponding
+Source of your version by providing access to the Corresponding Source
+from a network server at no charge, through some standard or customary
+means of facilitating copying of software.  This Corresponding Source
+shall include the Corresponding Source for any work covered by version 3
+of the GNU General Public License that is incorporated pursuant to the
+following paragraph.
+
+  Notwithstanding any other provision of this License, you have
+permission to link or combine any covered work with a work licensed
+under version 3 of the GNU General Public License into a single
+combined work, and to convey the resulting work.  The terms of this
+License will continue to apply to the part which is the covered work,
+but the work with which it is combined will remain governed by version
+3 of the GNU General Public License.
+
+  14. Revised Versions of this License.
+
+  The Free Software Foundation may publish revised and/or new versions of
+the GNU Affero General Public License from time to time.  Such new versions
+will be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+  Each version is given a distinguishing version number.  If the
+Program specifies that a certain numbered version of the GNU Affero General
+Public License "or any later version" applies to it, you have the
+option of following the terms and conditions either of that numbered
+version or of any later version published by the Free Software
+Foundation.  If the Program does not specify a version number of the
+GNU Affero General Public License, you may choose any version ever published
+by the Free Software Foundation.
+
+  If the Program specifies that a proxy can decide which future
+versions of the GNU Affero General Public License can be used, that proxy's
+public statement of acceptance of a version permanently authorizes you
+to choose that version for the Program.
+
+  Later license versions may give you additional or different
+permissions.  However, no additional obligations are imposed on any
+author or copyright holder as a result of your choosing to follow a
+later version.
+
+  15. Disclaimer of Warranty.
+
+  THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
+APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
+HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
+OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
+THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
+IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
+ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+  16. Limitation of Liability.
+
+  IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
+THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
+GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
+USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
+DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
+PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
+EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
+SUCH DAMAGES.
+
+  17. Interpretation of Sections 15 and 16.
+
+  If the disclaimer of warranty and limitation of liability provided
+above cannot be given local legal effect according to their terms,
+reviewing courts shall apply local law that most closely approximates
+an absolute waiver of all civil liability in connection with the
+Program, unless a warranty or assumption of liability accompanies a
+copy of the Program in return for a fee.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+state the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program is free software: you can redistribute it and/or modify
+    it under the terms of the GNU Affero General Public License as published by
+    the Free Software Foundation, either version 3 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Affero General Public License for more details.
+
+    You should have received a copy of the GNU Affero General Public License
+    along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+Also add information on how to contact you by electronic and paper mail.
+
+  If your software can interact with users remotely through a computer
+network, you should also make sure that it provides a way for users to
+get its source.  For example, if your program is a web application, its
+interface could display a "Source" link that leads users to an archive
+of the code.  There are many ways you could offer source, and different
+solutions will be better for different programs; see section 13 for the
+specific requirements.
+
+  You should also get your employer (if you work as a programmer) or school,
+if any, to sign a "copyright disclaimer" for the program, if necessary.
+For more information on this, and how to apply and follow the GNU AGPL, see
+<https://www.gnu.org/licenses/>.

README.md

@@ -1,10 +1,9 @@
-[![Publish Docker Image](https://github.com/sudolulo/winnow/actions/workflows/docker-publish.yml/badge.svg)](https://github.com/sudolulo/winnow/actions/workflows/docker-publish.yml) [![Release](https://github.com/sudolulo/winnow/actions/workflows/release.yml/badge.svg)](https://github.com/sudolulo/winnow/actions/workflows/release.yml) [![Lint](https://github.com/sudolulo/winnow/actions/workflows/lint.yml/badge.svg)](https://github.com/sudolulo/winnow/actions/workflows/lint.yml) [![Test](https://github.com/sudolulo/winnow/actions/workflows/test.yml/badge.svg)](https://github.com/sudolulo/winnow/actions/workflows/test.yml)
-[![Immich](https://img.shields.io/badge/Immich-v1.106%2B-violet?style=for-the-badge)](https://immich.app) [![Frigate](https://img.shields.io/badge/Frigate-Ready-green?style=for-the-badge)](https://frigate.video)
-
-**Docs:** [Setup Guide](docs/setup.md) · [Troubleshooting](docs/troubleshooting.md) · [FAQ](docs/faq.md)
-
 # winnow
 
+[![Docker](https://github.com/sudolulo/winnow/actions/workflows/docker-publish.yml/badge.svg)](https://github.com/sudolulo/winnow/actions/workflows/docker-publish.yml) [![Test](https://github.com/sudolulo/winnow/actions/workflows/test.yml/badge.svg)](https://github.com/sudolulo/winnow/actions/workflows/test.yml) [![Immich](https://img.shields.io/badge/Immich-v1.106%2B-blueviolet)](https://immich.app) [![Frigate](https://img.shields.io/badge/Frigate-Ready-brightgreen)](https://frigate.video)
+
+**Docs:** [Setup](https://github.com/sudolulo/winnow/wiki/Setup) · [Troubleshooting](https://github.com/sudolulo/winnow/wiki/Troubleshooting) · [FAQ](https://github.com/sudolulo/winnow/wiki/FAQ)
+
 `winnow` pulls photos of people and objects from your [Immich](https://immich.app) library, selects the most diverse and highest-quality subset using AI embeddings, and delivers them as training data for [Frigate](https://frigate.video)'s face recognition and object classification models.
 
 It runs fully headless in Docker, is configured entirely through environment variables, and can run on a schedule — no interactive prompts, no manual steps.
@@ -112,17 +111,23 @@ 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
       - FRIGATE_URL=http://192.168.1.10:5000
-      - AUTO_MODE=true
       - CRON_SCHEDULE=0 3 * * 0   # Every Sunday at 3 AM
     volumes:
       - /path/to/models:/models
@@ -137,11 +142,21 @@ services:
               capabilities: [gpu]
 ```
 
+> **CPU users (`:cpu` tag):** remove the `deploy.resources` block — no NVIDIA runtime needed. Add `mem_limit: 2g` to the service to prevent an OOM restart loop on large libraries.
+
 See [compose.yml](compose.yml) for the full annotated example.
 
 ### Scheduling Behaviour
 
-On startup the container always runs once immediately. If `CRON_SCHEDULE` is set, it then starts a scheduler that fires on the defined interval, keeping the process (and loaded models) alive between runs. Without `CRON_SCHEDULE` the container exits after the first run.
+`CRON_SCHEDULE` controls container lifetime:
+
+| `CRON_SCHEDULE` value | Behaviour |
+| :-- | :-- |
+| *(unset)* | Run once on startup, then exit |
+| *(empty string)* | Stay alive, run nothing — trigger manually with `docker exec -it winnow winnow` |
+| Cron expression | Run on startup, then repeat on schedule |
+
+In scheduled mode the process (and loaded models) stays resident between runs. In manual mode the container idles indefinitely with `sleep infinity` — useful when you want to trigger runs interactively on demand without pulling a new container each time.
 
 The first run after a fresh install downloads the embedding models (~1-2 GB). Subsequent runs use the cached models from the mounted volume and start immediately.
 
@@ -153,7 +168,8 @@ The first run after a fresh install downloads the embedding models (~1-2 GB). Su
 
 | Variable | Default | Description |
 | :--- | :--- | :--- |
-| `AUTO_MODE` | `false` | Run without interactive prompts — required for Docker/cron use |
+| `AUTO_MODE` | *(auto)* | Force non-interactive mode even in a terminal; auto-detected otherwise (no TTY = auto) |
+| `VERBOSE` | `false` | Set to `true` to enable DEBUG-level console output (the log file is always DEBUG) |
 | `TRAINING_MODE` | `face` | `face` — upload crops to Frigate API; `object` — save crops to disk |
 | `STRATEGY` | `auto` | `auto` (adaptive), `standard` (30 images), `broad` (100 images) |
 | `LIMIT` | *(unset)* | Exact image count — overrides `STRATEGY` |
@@ -193,7 +209,7 @@ The first run after a fresh install downloads the embedding models (~1-2 GB). Su
 | Variable | Default | Description |
 | :--- | :--- | :--- |
 | `FORCE_CPU` | `false` | Disable GPU — fall back to CPU for embedding computation |
-| `ENABLE_CACHE` | `false` | Cache computed embeddings to disk (speeds up re-runs on the same library) |
+| `ENABLE_CACHE` | `true` | Cache computed embeddings to disk (speeds up re-runs on the same library) |
 | `CACHE_DIR` | `.if_cache` | Path for embedding cache and upload tracker files |
 | `HF_HOME` | *(system)* | HuggingFace model cache location (SigLIP) |
 | `INSIGHTFACE_HOME` | *(system)* | InsightFace model cache location (Buffalo_L) |
@@ -210,7 +226,7 @@ The first run after a fresh install downloads the embedding models (~1-2 GB). Su
 
 | Variable | Default | Description |
 | :--- | :--- | :--- |
-| `CRON_SCHEDULE` | *(unset)* | Cron expression for recurring runs — unset exits after first run |
+| `CRON_SCHEDULE` | *(unset)* | Unset = run once and exit; empty = stay alive for manual `docker exec`; cron expression = scheduled |
 
 ---
 
@@ -223,7 +239,7 @@ uv sync
 uv run winnow
 ```
 
-Requires Python 3.12+ and [uv](https://astral.sh/uv/). An NVIDIA GPU is strongly recommended — CPU mode works but embedding computation is significantly slower.
+Requires Python 3.13+ and [uv](https://astral.sh/uv/). An NVIDIA GPU is strongly recommended — CPU mode works but embedding computation is slower (typically tens of seconds per person vs under a second on GPU).
 
 ---
 
@@ -232,7 +248,7 @@ Requires Python 3.12+ and [uv](https://astral.sh/uv/). An NVIDIA GPU is strongly
 - **Immich** v1.106+
 - **Frigate** v0.16+ (face mode only — object mode has no Frigate API dependency)
 - **NVIDIA GPU** recommended (CUDA 12.x)
-- **Python 3.12+**
+- **Python 3.13+**
 
 ---
 

compose.yml

@@ -9,7 +9,10 @@ services:
       - FRIGATE_URL=${FRIGATE_URL}
 
       # ── Mode & Strategy ───────────────────────────────────────────────────
-      - AUTO_MODE=true
+      # Auto mode is active by default when no TTY is present (Docker/cron).
+      # Set AUTO_MODE=true to force auto mode in an interactive terminal.
+      # To run interactively: docker exec -it winnow winnow
+      # - VERBOSE=true                # Enable DEBUG-level console output
       # TRAINING_MODE: face = upload to Frigate face recognition API
       #                object = save crops to output dir for manual Frigate placement
       - TRAINING_MODE=face
@@ -34,8 +37,8 @@ services:
       # - MAX_AUTO_IMAGES=80          # Hard cap on auto-diversity selection (default: 80)
 
       # ── Caching & Models ──────────────────────────────────────────────────
-      - FORCE_CPU=false
+      # - FORCE_CPU=true              # Disable GPU, fall back to CPU
-      - ENABLE_CACHE=true
+      # - ENABLE_CACHE=false          # Disable embedding cache (default: true)
       - CACHE_DIR=/app/.if_cache
       - HF_HOME=/models/huggingface
       - INSIGHTFACE_HOME=/models/.insightface
@@ -46,18 +49,19 @@ services:
       # - RESET_PERSON=John           # Clear uploaded+rejected history for one person
 
       # ── Scheduling ────────────────────────────────────────────────────────
-      # Cron expression (unset = run once and exit)
+      # CRON_SCHEDULE controls container lifetime:
-      # Every Sunday at 3 AM:
+      #   unset          — run once on startup, then exit
-      - CRON_SCHEDULE=0 3 * * 0
+      #   empty string   — stay alive, run nothing; trigger manually with:
-      # - CRON_SCHEDULE=0 3 1 * *
+      #                    docker exec -it winnow winnow
-      # - CRON_SCHEDULE=*/30 * * * *
+      #   cron expression — run on startup, then on schedule
+      # - CRON_SCHEDULE=                # Manual mode (keep alive, no auto-run)
+      # - CRON_SCHEDULE=0 3 * * 0      # Every Sunday at 3 AM
+      # - CRON_SCHEDULE=0 3 1 * *      # First of every month
     volumes:
       # Replace with absolute paths on your host, e.g. /opt/winnow/models
       - /path/to/winnow/models:/models
       - /path/to/winnow/cache:/app/.if_cache
       - /path/to/winnow/output:/app/frigate_train
-    stdin_open: true
-    tty: true
     restart: unless-stopped
     deploy:
       resources:

entrypoint.sh

@@ -2,11 +2,19 @@
 set -e
 export PYTHONUNBUFFERED=1
 
-# 1. Run the job immediately on startup
+# CRON_SCHEDULE controls container lifetime:
+#   unset          — run once and exit
+#   empty string   — stay alive, run nothing (use: docker exec -it winnow winnow)
+#   cron expression — run immediately, then on schedule
+
+if [ "${CRON_SCHEDULE+isset}" = "isset" ] && [ -z "$CRON_SCHEDULE" ]; then
+    echo "▶ CRON_SCHEDULE is empty — manual mode. Use 'docker exec -it winnow winnow' to run."
+    exec sleep infinity
+fi
+
 echo "▶ Running on startup..."
-/app/.venv/bin/python -m winnow.cli
+/app/.venv/bin/winnow
 
-# 2. If a schedule exists, start the scheduler
 if [ -n "${CRON_SCHEDULE:-}" ]; then
     echo "▶ CRON_SCHEDULE set to: $CRON_SCHEDULE"
     echo "▶ Switching to scheduled mode..."
@@ -14,4 +22,3 @@ if [ -n "${CRON_SCHEDULE:-}" ]; then
 else
     echo "▶ No schedule set, exiting."
 fi
-

pyproject-cpu.toml

@@ -0,0 +1,93 @@
+[project]
+name = "winnow"
+version = "0.2.11"
+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"

pyproject.toml

@@ -1,15 +1,15 @@
 [project]
 name = "winnow"
-version = "0.2.6"
+version = "0.2.11"
 description = "Immich to Frigate training sets"
-license = "MIT"
+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 :: MIT License",
+    "License :: OSI Approved :: GNU Affero General Public License v3 or later (AGPLv3+)",
     "Programming Language :: Python :: 3.13",
     "Topic :: Scientific/Engineering :: Image Recognition",
 ]
@@ -18,7 +18,9 @@ dependencies = [
     "insightface>=0.7.3",
     "nvidia-cudnn-cu12>=9.0.0",
     "numpy>=2.2.6",
-    "onnxruntime-gpu>=1.23.2",
+    "onnxruntime-gpu>=1.23.2; sys_platform == 'linux' and platform_machine == 'x86_64'",
+    "onnxruntime>=1.23.2; sys_platform == 'linux' and platform_machine != 'x86_64'",
+    "onnxruntime>=1.23.2; sys_platform != 'linux'",
     "opencv-python-headless>=4.12.0.88",
     "pillow>=12.1.0",
     "python-dotenv>=1.2.1",
@@ -37,7 +39,16 @@ winnow = "winnow.cli:main"
 Repository = "https://github.com/sudolulo/winnow"
 
 [tool.uv]
-override-dependencies = ["onnxruntime-gpu>=1.23.2"]
+conflicts = [
+    [
+        { package = "onnxruntime" },
+        { package = "onnxruntime-gpu" },
+    ],
+]
+required-environments = [
+    "sys_platform == 'linux' and platform_machine == 'x86_64'",
+    "sys_platform == 'linux' and platform_machine == 'aarch64'",
+]
 
 [tool.uv.sources]
 torch = [

scheduler.py

@@ -1,7 +1,6 @@
 #!/usr/bin/env python3
 import logging
 import os
-import subprocess
 import sys
 import time
 from pathlib import Path
@@ -9,33 +8,27 @@ from pathlib import Path
 try:
     from croniter import croniter
 except ImportError:
-    print("❌ croniter not installed. Run: uv add croniter")
+    print("croniter not installed. Run: uv add croniter")
     sys.exit(1)
 
+# Imported at module level so models loaded during the first run stay
+# resident in memory across all subsequent scheduled runs.
+from winnow.cli import main
+
 SCHEDULE = os.environ["CRON_SCHEDULE"]
 MODELS_DIR = os.environ.get("HF_HOME", "/models/huggingface")
-INSIGHTFACE_BASE = os.environ.get("INSIGHTFACE_HOME", "/models")
+INSIGHTFACE_HOME = os.environ.get("INSIGHTFACE_HOME", "/models/.insightface")
-
-RUN_ENV = {**os.environ, "PYTHONUNBUFFERED": "1"}
 
 logger = logging.getLogger(__name__)
 
 
-def check_models():
+def check_models() -> None:
-    """Log model status before each run."""
+    buffalo = Path(INSIGHTFACE_HOME) / "models" / "buffalo_l"
-    print("📦 Checking models...", flush=True)
-    buffalo = Path(INSIGHTFACE_BASE) / ".insightface" / "models" / "buffalo_l"
-    if buffalo.exists():
-        print("  ✅ InsightFace Buffalo_L: present", flush=True)
-    else:
-        print("  ⬇️  InsightFace Buffalo_L: not found — will download", flush=True)
-
     hf_hub = Path(MODELS_DIR) / "hub"
-    if hf_hub.exists() and any(hf_hub.iterdir()):
+    if not buffalo.exists():
-        print("  ✅ HuggingFace models: present", flush=True)
+        print("  InsightFace Buffalo_L not found — will download on first run", flush=True)
-    else:
+    if not (hf_hub.exists() and any(hf_hub.iterdir())):
-        print("  ⬇️  HuggingFace models: not found — will download", flush=True)
+        print("  HuggingFace models not found — will download on first run", flush=True)
-    print("🚀 Starting winnow...", flush=True)
 
 
 NOW = time.time()
@@ -45,14 +38,15 @@ next_run = cron.get_next(float)
 while True:
     now = time.time()
     if now >= next_run:
-        print(f"\n▶ [{time.strftime('%Y-%m-%d %H:%M:%S')}] Starting winnow...", flush=True)
+        print(f"\n[{time.strftime('%Y-%m-%d %H:%M:%S')}] Starting winnow run...", flush=True)
         check_models()
-        result = subprocess.run(["uv", "run", "winnow"], env=RUN_ENV)
+        try:
-        if result.returncode != 0:
+            main()
-            logger.error(f"winnow exited with code {result.returncode}")
+            print("winnow run complete", flush=True)
-            print(f"❌ winnow failed with exit code {result.returncode}", flush=True)
+        except KeyboardInterrupt:
-        else:
+            raise
-            print("✅ winnow completed successfully", flush=True)
+        except Exception as e:
+            logger.error(f"winnow run failed: {e}", exc_info=True)
+            print(f"winnow run failed: {e}", flush=True)
         next_run = cron.get_next(float)
-    time.sleep(60)
+    time.sleep(max(1, next_run - time.time()))
-

tests/test_config.py

@@ -25,7 +25,7 @@ def test_config_loads_defaults(monkeypatch):
     assert cfg.FACE_MARGIN == 0.15
     assert cfg.USE_FULL_RESOLUTION is True
     assert cfg.ENABLE_FACE_ALIGNMENT is True
-    assert cfg.ENABLE_CACHE is False
+    assert cfg.ENABLE_CACHE is True
 
     _Config.reset()
 

tests/test_quality.py

@@ -0,0 +1,151 @@
+"""Tests for image quality filtering functions."""
+
+import numpy as np
+from PIL import Image
+
+
+def _rgb_image(r, g, b, size=(100, 100)) -> Image.Image:
+    arr = np.full((*size, 3), [r, g, b], dtype=np.uint8)
+    return Image.fromarray(arr, "RGB")
+
+
+def _noisy_color_image(size=(100, 100)) -> Image.Image:
+    """Noisy image with a strong red channel so grayscale check passes."""
+    rng = np.random.default_rng(0)
+    arr = rng.integers(0, 256, (*size, 3), dtype=np.uint8)
+    arr[:, :, 0] = np.clip(arr[:, :, 0].astype(int) + 80, 0, 255).astype(np.uint8)
+    arr[:, :, 2] = np.clip(arr[:, :, 2].astype(int) - 80, 0, 255).astype(np.uint8)
+    return Image.fromarray(arr, "RGB")
+
+
+# ── check_blur ────────────────────────────────────────────────────────────────
+
+def test_blur_rejects_flat_image():
+    from winnow.quality import check_blur
+    flat = np.full((100, 100, 3), 128, dtype=np.uint8)
+    passed, reason = check_blur(flat, threshold=100.0)
+    assert not passed
+    assert "Blurry" in reason
+
+
+def test_blur_passes_noisy_color_image():
+    from winnow.quality import check_blur
+    img = _noisy_color_image()
+    passed, _ = check_blur(np.asarray(img), threshold=100.0)
+    assert passed
+
+
+# ── check_grayscale ───────────────────────────────────────────────────────────
+
+def test_grayscale_rejects_ir_image():
+    from winnow.quality import check_grayscale
+    gray = np.full((100, 100, 3), 128, dtype=np.uint8)
+    passed, reason = check_grayscale(gray)
+    assert not passed
+    assert "Grayscale" in reason
+
+
+def test_grayscale_passes_color_image():
+    from winnow.quality import check_grayscale
+    color = np.zeros((100, 100, 3), dtype=np.uint8)
+    color[:, :, 0] = 200  # strong red channel
+    passed, _ = check_grayscale(color)
+    assert passed
+
+
+def test_grayscale_rejects_single_channel():
+    from winnow.quality import check_grayscale
+    single = np.full((100, 100, 1), 128, dtype=np.uint8)
+    passed, reason = check_grayscale(single)
+    assert not passed
+
+
+# ── check_exposure ────────────────────────────────────────────────────────────
+
+def test_exposure_rejects_black_image():
+    from winnow.quality import check_exposure
+    black = np.zeros((100, 100, 3), dtype=np.uint8)
+    passed, reason = check_exposure(black)
+    assert not passed
+    assert "Underexposed" in reason
+
+
+def test_exposure_rejects_white_image():
+    from winnow.quality import check_exposure
+    white = np.full((100, 100, 3), 255, dtype=np.uint8)
+    passed, reason = check_exposure(white)
+    assert not passed
+    assert "Overexposed" in reason
+
+
+def test_exposure_passes_normal_image():
+    from winnow.quality import check_exposure
+    mid = np.full((100, 100, 3), 128, dtype=np.uint8)
+    passed, _ = check_exposure(mid)
+    assert passed
+
+
+# ── check_face_size ───────────────────────────────────────────────────────────
+
+def test_face_size_rejects_small_face():
+    from winnow.quality import check_face_size
+    passed, reason = check_face_size(30, 30, min_px=50)
+    assert not passed
+    assert "small" in reason
+
+
+def test_face_size_passes_adequate_face():
+    from winnow.quality import check_face_size
+    passed, _ = check_face_size(100, 100, min_px=50)
+    assert passed
+
+
+def test_face_size_rejects_if_either_dimension_small():
+    from winnow.quality import check_face_size
+    passed, _ = check_face_size(100, 30, min_px=50)
+    assert not passed
+
+
+# ── check_confidence ──────────────────────────────────────────────────────────
+
+def test_confidence_rejects_low_score():
+    from winnow.quality import check_confidence
+    passed, reason = check_confidence(0.5, min_conf=0.7)
+    assert not passed
+    assert "confidence" in reason.lower()
+
+
+def test_confidence_passes_high_score():
+    from winnow.quality import check_confidence
+    passed, _ = check_confidence(0.95, min_conf=0.7)
+    assert passed
+
+
+def test_confidence_passes_none_score():
+    from winnow.quality import check_confidence
+    passed, _ = check_confidence(None, min_conf=0.7)
+    assert passed
+
+
+# ── assess_quality (integration) ─────────────────────────────────────────────
+
+def test_assess_quality_passes_good_image():
+    from winnow.quality import assess_quality
+    img = _noisy_color_image()
+    result = assess_quality(img, face_bbox=(10, 10, 110, 110), confidence=0.9)
+    assert result.passed
+
+
+def test_assess_quality_collects_multiple_failures():
+    from winnow.quality import assess_quality
+    black = _rgb_image(0, 0, 0)
+    result = assess_quality(black, face_bbox=(0, 0, 10, 10), confidence=0.3)
+    assert not result.passed
+    assert len(result.reasons) >= 2
+
+
+def test_assess_quality_skips_face_size_without_bbox():
+    from winnow.quality import assess_quality
+    img = _noisy_color_image()
+    result = assess_quality(img, face_bbox=None, confidence=0.9)
+    assert result.passed

uv.lock

@@ -2,20 +2,25 @@ version = 1
 revision = 3
 requires-python = ">=3.13"
 resolution-markers = [
-    "platform_machine == 'x86_64' and sys_platform == 'linux'",
     "platform_machine == 'aarch64' and sys_platform == 'linux'",
+    "platform_machine != 'aarch64' and platform_machine != 's390x' and platform_machine != 'x86_64' and sys_platform == 'linux'",
+    "platform_machine == 's390x' and sys_platform == 'linux'",
     "platform_machine != 's390x' and sys_platform == 'win32'",
     "platform_machine == 's390x' and sys_platform == 'win32'",
     "platform_machine != 's390x' and sys_platform != 'darwin' and sys_platform != 'linux' and sys_platform != 'win32'",
     "platform_machine == 's390x' and sys_platform != 'darwin' and sys_platform != 'linux' and sys_platform != 'win32'",
     "platform_machine != 's390x' and sys_platform == 'darwin'",
     "platform_machine == 's390x' and sys_platform == 'darwin'",
-    "platform_machine != 'aarch64' and platform_machine != 's390x' and platform_machine != 'x86_64' and sys_platform == 'linux'",
+    "platform_machine == 'x86_64' and sys_platform == 'linux'",
-    "platform_machine == 's390x' and sys_platform == 'linux'",
 ]
-
+required-markers = [
-[manifest]
+    "platform_machine == 'x86_64' and sys_platform == 'linux'",
-overrides = [{ name = "onnxruntime-gpu", specifier = ">=1.23.2" }]
+    "platform_machine == 'aarch64' and sys_platform == 'linux'",
+]
+conflicts = [[
+    { package = "onnxruntime" },
+    { package = "onnxruntime-gpu" },
+]]
 
 [[package]]
 name = "annotated-doc"
@@ -109,7 +114,7 @@ name = "click"
 version = "8.4.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "colorama", marker = "sys_platform == 'win32'" },
+    { name = "colorama", marker = "sys_platform == 'win32' or (extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/9b/98/518d8e5081007684232226f475082b30087d0f585e8457db087298259f49/click-8.4.1.tar.gz", hash = "sha256:918b5633eddf6b41c32d4f454bf0de810065c74e3f7dbf8ee5452f8be88d3e96", size = 353007, upload-time = "2026-05-22T04:08:37.769Z" }
 wheels = [
@@ -200,13 +205,21 @@ resolution-markers = [
     "platform_machine == 'x86_64' and sys_platform == 'linux'",
 ]
 dependencies = [
-    { name = "cuda-pathfinder", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "cuda-pathfinder", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 wheels = [
+    { url = "https://files.pythonhosted.org/packages/eb/7b/f1575e41e1a17dc2f2a408b2e8e864c9324e41e3e23f6401e5efc54c152a/cuda_bindings-12.9.7-cp313-cp313-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:266379e4942051f544a8e7ea1a30ead8d7e8199b6b30fcdc8917cae2bf614e61", size = 6978549, upload-time = "2026-05-27T18:44:18.839Z" },
     { url = "https://files.pythonhosted.org/packages/9d/dc/62d62eb4f91eb721bcf46da51b13e9872ccd8fa7e60eb8ba7b7baeac72c6/cuda_bindings-12.9.7-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:59cf4a37b0d662ba15037c9ceebe1a306ebf2c01a8235a09be13cd07094fdb74", size = 7457675, upload-time = "2026-05-27T18:44:20.637Z" },
+    { url = "https://files.pythonhosted.org/packages/43/b2/753fe88151001d0dc23f56a8e119fe06b991b0d1a885fa02f9852b12f523/cuda_bindings-12.9.7-cp313-cp313-win_amd64.whl", hash = "sha256:5bd89dcb78475a6d8a4620ea94b74edf0cbbeacee6d1622d8f94452c1e8d3f15", size = 7360097, upload-time = "2026-05-27T18:44:22.405Z" },
+    { url = "https://files.pythonhosted.org/packages/f9/77/94d9b85f26add6fe9c9cb7c4ec3b96bc598f7ea5cfbd7490cc0a36adf5be/cuda_bindings-12.9.7-cp313-cp313t-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:2dbcd4801954eb3508f4dc2fa0d0c8eb93eb3f45326fd61be2731418c371e7a0", size = 6870886, upload-time = "2026-05-27T18:44:24.164Z" },
     { url = "https://files.pythonhosted.org/packages/04/dd/3ec34b569e1b990b11276feba306bf8f446656cc38e8ed0f49b5facfeffa/cuda_bindings-12.9.7-cp313-cp313t-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:3747ea132642416786a8e31bf229032df3a7856911ae5426a7be53d032df183d", size = 7345663, upload-time = "2026-05-27T18:44:26.333Z" },
+    { url = "https://files.pythonhosted.org/packages/b8/c8/d79a20ba396e7ab2dfdd4b72b62356972b25b88aee2ded49a70c797ddea1/cuda_bindings-12.9.7-cp313-cp313t-win_amd64.whl", hash = "sha256:64f7ade7a7a3b69001489753acc21706d9dbda32db8deb68a767a0a0aab30b68", size = 7780136, upload-time = "2026-05-27T18:44:28.121Z" },
+    { url = "https://files.pythonhosted.org/packages/68/e4/075052d42872cf8162da53f14447a4b8abc004c3750e4b724ee502428da0/cuda_bindings-12.9.7-cp314-cp314-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:775960ac9e530717f3b48e165cc6f68684fa9a4141764fd923e4c1a9820acc73", size = 7060090, upload-time = "2026-05-27T18:44:30.281Z" },
     { url = "https://files.pythonhosted.org/packages/ec/cd/3289c810a4d45e5364a3387a74b4c9b6f6f57ee96ae0e5b537cc61dec242/cuda_bindings-12.9.7-cp314-cp314-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:3c47ec1a7a441d91aab32339951df7a1be53451121a12c094bba51467717a35a", size = 7504419, upload-time = "2026-05-27T18:44:31.992Z" },
+    { url = "https://files.pythonhosted.org/packages/5b/a0/c429fdcfa5aae181415504c5085ea5944f782b417dd16a7f2a14be0da80d/cuda_bindings-12.9.7-cp314-cp314-win_amd64.whl", hash = "sha256:1e2a4f2ec5b67408c04bb4fbed45d214b66de1f00ee2e972865cacb8708d4e1e", size = 7493876, upload-time = "2026-05-27T18:44:33.618Z" },
+    { url = "https://files.pythonhosted.org/packages/11/43/472a6281c3d94e71687e27c657a8f60718d3579b4d94c41deea503165f8a/cuda_bindings-12.9.7-cp314-cp314t-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:00a833d399b31071fab4cf3de2929840ae462dc4848116eeff033d09219e7116", size = 6899146, upload-time = "2026-05-27T18:44:35.556Z" },
     { url = "https://files.pythonhosted.org/packages/2b/13/10c1d0b32a9da65142d213e0733d748457fb3fd066aee4317335266f15c6/cuda_bindings-12.9.7-cp314-cp314t-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:11aeafa2b33995f890086b3fb0f062075176d956e9b6a6fe1a699dddc413f6ad", size = 7369087, upload-time = "2026-05-27T18:44:37.359Z" },
+    { url = "https://files.pythonhosted.org/packages/33/10/c71a07cd2a1d4db119bada1848b4752a874ccfe4927d419bfdd05f250920/cuda_bindings-12.9.7-cp314-cp314t-win_amd64.whl", hash = "sha256:ece8dfbc22e6de96a26940ab9887eb3cfe1fc1bc3966169391cdb866bb82bb64", size = 8208198, upload-time = "2026-05-27T18:44:39.053Z" },
 ]
 
 [[package]]
@@ -218,15 +231,18 @@ resolution-markers = [
     "platform_machine == 's390x' and sys_platform == 'linux'",
 ]
 dependencies = [
-    { name = "cuda-pathfinder", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "cuda-pathfinder", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/cc/6e/2394f8163360f8391f8f1b7e72d300a82724edb81a7b7084c799fbd4c91f/cuda_bindings-13.3.1-cp313-cp313-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:9efb21c1ee64981e184b9e0ba5eb3179e5ba3d4b51665a6cb52b8ef3d01a7cbf", size = 5920504, upload-time = "2026-05-29T23:11:56.883Z" },
     { url = "https://files.pythonhosted.org/packages/34/c2/ef9b6a63f7dc432712a462c816662e662e00d38caa9b861c8c2588195d03/cuda_bindings-13.3.1-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:2732904099e0a4d4db774a5fc6d91ee95fae065b4d2ecabb4968c5fe2406c9d7", size = 6476660, upload-time = "2026-05-29T23:11:59.188Z" },
+    { url = "https://files.pythonhosted.org/packages/0c/2f/6a0dd496550c6fafbf6aeb1bf40242eeabb2fd138a43892aabb4be8224c2/cuda_bindings-13.3.1-cp313-cp313-win_amd64.whl", hash = "sha256:18c8c167c8907b8f02531ca810534315c458dabef31f7965095619bf647b9202", size = 5830027, upload-time = "2026-05-29T23:12:01.205Z" },
     { url = "https://files.pythonhosted.org/packages/b1/81/bff68ce829999c1e4209c761bbf903b1c06ec570416ddb25020864ad5907/cuda_bindings-13.3.1-cp314-cp314-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:1ab2f74ed65bfef4163ba07a8db16f1085e0729291db12a2423aff84ee8278b8", size = 6013639, upload-time = "2026-05-29T23:12:03.509Z" },
     { url = "https://files.pythonhosted.org/packages/d4/e0/c8a1f0c8f9ffdea4f5fe6dbab89b326cef4d85caf489dad39e209da89416/cuda_bindings-13.3.1-cp314-cp314-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:efd4c814d311ec08c981f6dded1dbe7d4b371067ee4f6c14cccec4bde9590f80", size = 6534419, upload-time = "2026-05-29T23:12:05.633Z" },
+    { url = "https://files.pythonhosted.org/packages/48/45/2734be44dbc80ac082ec23a86b41c8294992dcb90033645ed1bc50aafe4c/cuda_bindings-13.3.1-cp314-cp314-win_amd64.whl", hash = "sha256:8de12ef60bf40756852cb62bbb40460609269f6ece522903d1cc93d73a3ececb", size = 5961055, upload-time = "2026-05-29T23:12:07.971Z" },
     { url = "https://files.pythonhosted.org/packages/52/b8/83b1f563925b290f2d11a01a77a84013ba56052fe3653a5bef3ccfbb43d6/cuda_bindings-13.3.1-cp314-cp314t-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c3c772dfff49681541d59630c90f858e173ac926b9c593a2b7123f2a1043cc76", size = 5809771, upload-time = "2026-05-29T23:12:10.422Z" },
     { url = "https://files.pythonhosted.org/packages/12/20/e79b4bfe98f075195afb6343d41c498f9dbd2d161d7021d4d28bceb83581/cuda_bindings-13.3.1-cp314-cp314t-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:36febb7c1079d68a981dbbd8d5a67235b399802b82075c9388624719607e52b9", size = 6358584, upload-time = "2026-05-29T23:12:12.767Z" },
+    { url = "https://files.pythonhosted.org/packages/27/2a/b59bcac016ab9985d6b48a5d05b0d698461a159ca03ee11c4abd54da2ac4/cuda_bindings-13.3.1-cp314-cp314t-win_amd64.whl", hash = "sha256:61120b5e4f4a63f67efd7e7396914cb9ef871bb1f0021e990fb70277be240a4d", size = 6740329, upload-time = "2026-05-29T23:12:15.153Z" },
 ]
 
 [[package]]
@@ -250,37 +266,37 @@ wheels = [
 
 [package.optional-dependencies]
 cublas = [
-    { name = "nvidia-cublas-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cublas-cu12", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 cudart = [
-    { name = "nvidia-cuda-runtime-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cuda-runtime-cu12", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 cufft = [
-    { name = "nvidia-cufft-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cufft-cu12", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 cufile = [
-    { name = "nvidia-cufile-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cufile-cu12", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 cupti = [
-    { name = "nvidia-cuda-cupti-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cuda-cupti-cu12", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 curand = [
-    { name = "nvidia-curand-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-curand-cu12", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 cusolver = [
-    { name = "nvidia-cusolver-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cusolver-cu12", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 cusparse = [
-    { name = "nvidia-cusparse-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cusparse-cu12", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 nvjitlink = [
-    { name = "nvidia-nvjitlink-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 nvrtc = [
-    { name = "nvidia-cuda-nvrtc-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cuda-nvrtc-cu12", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 nvtx = [
-    { name = "nvidia-nvtx-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-nvtx-cu12", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 
 [[package]]
@@ -297,34 +313,34 @@ wheels = [
 
 [package.optional-dependencies]
 cudart = [
-    { name = "nvidia-cuda-runtime", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cuda-runtime", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 cufft = [
-    { name = "nvidia-cufft", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cufft", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 cufile = [
-    { name = "nvidia-cufile", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cufile", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 cupti = [
-    { name = "nvidia-cuda-cupti", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cuda-cupti", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 curand = [
-    { name = "nvidia-curand", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-curand", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 cusolver = [
-    { name = "nvidia-cusolver", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cusolver", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 cusparse = [
-    { name = "nvidia-cusparse", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cusparse", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 nvjitlink = [
-    { name = "nvidia-nvjitlink", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-nvjitlink", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 nvrtc = [
-    { name = "nvidia-cuda-nvrtc", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cuda-nvrtc", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 nvtx = [
-    { name = "nvidia-nvtx", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-nvtx", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 
 [[package]]
@@ -472,7 +488,7 @@ dependencies = [
     { name = "click" },
     { name = "filelock" },
     { name = "fsspec" },
-    { name = "hf-xet", marker = "platform_machine == 'AMD64' or platform_machine == 'aarch64' or platform_machine == 'amd64' or platform_machine == 'arm64' or platform_machine == 'x86_64'" },
+    { name = "hf-xet", marker = "platform_machine == 'AMD64' or platform_machine == 'aarch64' or platform_machine == 'amd64' or platform_machine == 'arm64' or platform_machine == 'x86_64' or (extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
     { name = "httpx" },
     { name = "packaging" },
     { name = "pyyaml" },
@@ -850,11 +866,12 @@ name = "nvidia-cublas"
 version = "13.1.1.3"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-cuda-nvrtc", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cuda-nvrtc", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/a7/a1/0bd24ee8c8d03adac032fd2909426a00c88f8c57961b1277ded97f91119f/nvidia_cublas-13.1.1.3-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:b7a210458267ac818974c53038fbec2e969d5c99f305ab15c72522fa9f001dd5", size = 542848918, upload-time = "2026-04-08T18:46:22.985Z" },
     { url = "https://files.pythonhosted.org/packages/3b/cd/154ca20c38269e05eff77c1464e6c1da89f50a6390b565e9d82e06bc11e1/nvidia_cublas-13.1.1.3-py3-none-manylinux_2_27_x86_64.whl", hash = "sha256:37936a16db8fe4ac1f065c2139360608a543a09275cb1a1af612e08cfa065436", size = 423138758, upload-time = "2026-04-08T18:46:58.655Z" },
+    { url = "https://files.pythonhosted.org/packages/45/9e/2f562daf80eb8f7a685fb7bea4fda71f6048e4f359d6fdd1b6e70206cb2f/nvidia_cublas-13.1.1.3-py3-none-win_amd64.whl", hash = "sha256:b6cdce694e47ff6aadf0a69df1cab6628d696f5ff56e8d16af50309d855fa20f", size = 404358158, upload-time = "2026-04-08T18:47:26.987Z" },
 ]
 
 [[package]]
@@ -874,6 +891,7 @@ source = { registry = "https://pypi.org/simple" }
 wheels = [
     { url = "https://files.pythonhosted.org/packages/2a/2a/80353b103fc20ce05ef51e928daed4b6015db4aaa9162ed0997090fe2250/nvidia_cuda_cupti-13.0.85-py3-none-manylinux_2_25_aarch64.whl", hash = "sha256:796bd679890ee55fb14a94629b698b6db54bcfd833d391d5e94017dd9d7d3151", size = 10310827, upload-time = "2025-09-04T08:26:42.012Z" },
     { url = "https://files.pythonhosted.org/packages/33/6d/737d164b4837a9bbd202f5ae3078975f0525a55730fe871d8ed4e3b952b0/nvidia_cuda_cupti-13.0.85-py3-none-manylinux_2_25_x86_64.whl", hash = "sha256:4eb01c08e859bf924d222250d2e8f8b8ff6d3db4721288cf35d14252a4d933c8", size = 10715597, upload-time = "2025-09-04T08:26:51.312Z" },
+    { url = "https://files.pythonhosted.org/packages/ad/df/b74b10025c1205695c5676373f2edd3e87a7202cc62ead0dfbc373b0f6ea/nvidia_cuda_cupti-13.0.85-py3-none-win_amd64.whl", hash = "sha256:683f58d301548deeefcb8f6fac1b8d907691b9d8b18eccab417f51e362102f00", size = 7736776, upload-time = "2025-09-04T08:38:08.38Z" },
 ]
 
 [[package]]
@@ -881,8 +899,11 @@ name = "nvidia-cuda-cupti-cu12"
 version = "12.6.80"
 source = { registry = "https://pypi.org/simple" }
 wheels = [
+    { url = "https://files.pythonhosted.org/packages/e6/8b/2f6230cb715646c3a9425636e513227ce5c93c4d65823a734f4bb86d43c3/nvidia_cuda_cupti_cu12-12.6.80-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:166ee35a3ff1587f2490364f90eeeb8da06cd867bd5b701bf7f9a02b78bc63fc", size = 8236764, upload-time = "2024-11-20T17:35:41.03Z" },
+    { url = "https://files.pythonhosted.org/packages/25/0f/acb326ac8fd26e13c799e0b4f3b2751543e1834f04d62e729485872198d4/nvidia_cuda_cupti_cu12-12.6.80-py3-none-manylinux2014_aarch64.whl", hash = "sha256:358b4a1d35370353d52e12f0a7d1769fc01ff74a191689d3870b2123156184c4", size = 8236756, upload-time = "2024-10-01T16:57:45.507Z" },
     { url = "https://files.pythonhosted.org/packages/49/60/7b6497946d74bcf1de852a21824d63baad12cd417db4195fc1bfe59db953/nvidia_cuda_cupti_cu12-12.6.80-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:6768bad6cab4f19e8292125e5f1ac8aa7d1718704012a0e3272a6f61c4bce132", size = 8917980, upload-time = "2024-11-20T17:36:04.019Z" },
     { url = "https://files.pythonhosted.org/packages/a5/24/120ee57b218d9952c379d1e026c4479c9ece9997a4fb46303611ee48f038/nvidia_cuda_cupti_cu12-12.6.80-py3-none-manylinux2014_x86_64.whl", hash = "sha256:a3eff6cdfcc6a4c35db968a06fcadb061cbc7d6dde548609a941ff8701b98b73", size = 8917972, upload-time = "2024-10-01T16:58:06.036Z" },
+    { url = "https://files.pythonhosted.org/packages/1c/81/7796f096afaf726796b1b648f3bc80cafc61fe7f77f44a483c89e6c5ef34/nvidia_cuda_cupti_cu12-12.6.80-py3-none-win_amd64.whl", hash = "sha256:bbe6ae76e83ce5251b56e8c8e61a964f757175682bbad058b170b136266ab00a", size = 5724175, upload-time = "2024-10-01T17:09:47.955Z" },
 ]
 
 [[package]]
@@ -892,6 +913,7 @@ source = { registry = "https://pypi.org/simple" }
 wheels = [
     { url = "https://files.pythonhosted.org/packages/c3/68/483a78f5e8f31b08fb1bb671559968c0ca3a065ac7acabfc7cee55214fd6/nvidia_cuda_nvrtc-13.0.88-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:ad9b6d2ead2435f11cbb6868809d2adeeee302e9bb94bcf0539c7a40d80e8575", size = 90215200, upload-time = "2025-09-04T08:28:44.204Z" },
     { url = "https://files.pythonhosted.org/packages/b7/dc/6bb80850e0b7edd6588d560758f17e0550893a1feaf436807d64d2da040f/nvidia_cuda_nvrtc-13.0.88-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:d27f20a0ca67a4bb34268a5e951033496c5b74870b868bacd046b1b8e0c3267b", size = 43015449, upload-time = "2025-09-04T08:28:20.239Z" },
+    { url = "https://files.pythonhosted.org/packages/4a/af/345fedb9f4c76c84ab4fa445b36bd4048a4d9db60e6bc76b4f913ff4b852/nvidia_cuda_nvrtc-13.0.88-py3-none-win_amd64.whl", hash = "sha256:6bcd4e7f8e205cbe644f5a98f2f799bef9556fefc89dd786e79a16312ce49872", size = 76807835, upload-time = "2025-09-04T08:39:15.274Z" },
 ]
 
 [[package]]
@@ -900,6 +922,8 @@ version = "12.6.85"
 source = { registry = "https://pypi.org/simple" }
 wheels = [
     { url = "https://files.pythonhosted.org/packages/f5/31/ffb400c5ae99daf09687aa6c42831c5d824f71c4851363ed2a4a1ac52bab/nvidia_cuda_nvrtc_cu12-12.6.85-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:800927308ccc5dd6246d3f61f7fcef2ed7ec4e59e199090d360d3293f78bd5a2", size = 23649944, upload-time = "2024-11-20T17:38:06.511Z" },
+    { url = "https://files.pythonhosted.org/packages/48/ab/476146f59ff5ef5bd6e62c187097d859ea78b5752d19c6c3f9be5f90dafc/nvidia_cuda_nvrtc_cu12-12.6.85-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:3f3134f50963882373063901657554f230bedf6039d30b09f6be55c64c993a37", size = 23162872, upload-time = "2024-11-20T17:37:42.967Z" },
+    { url = "https://files.pythonhosted.org/packages/0c/f7/472414aee887d626373d0b2140a59ac4308e3eaed815060e5410fc83305a/nvidia_cuda_nvrtc_cu12-12.6.85-py3-none-win_amd64.whl", hash = "sha256:a419e2c95e75b88b602f8bb66f82a6c5651e8475a509841c958486b1b71510bf", size = 39026436, upload-time = "2024-11-20T17:49:13.633Z" },
 ]
 
 [[package]]
@@ -909,6 +933,7 @@ source = { registry = "https://pypi.org/simple" }
 wheels = [
     { url = "https://files.pythonhosted.org/packages/87/4f/17d7b9b8e285199c58ce28e31b5c5bbaa4d8271af06a89b6405258245de2/nvidia_cuda_runtime-13.0.96-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:ef9bcbe90493a2b9d810e43d249adb3d02e98dd30200d86607d8d02687c43f55", size = 2261060, upload-time = "2025-10-09T08:55:15.78Z" },
     { url = "https://files.pythonhosted.org/packages/2e/24/d1558f3b68b1d26e706813b1d10aa1d785e4698c425af8db8edc3dced472/nvidia_cuda_runtime-13.0.96-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:7f82250d7782aa23b6cfe765ecc7db554bd3c2870c43f3d1821f1d18aebf0548", size = 2243632, upload-time = "2025-10-09T08:55:36.117Z" },
+    { url = "https://files.pythonhosted.org/packages/b7/94/6b867483bec07da24ffa32736c79fabb94ef3a7af4d787a9d4a974868576/nvidia_cuda_runtime-13.0.96-py3-none-win_amd64.whl", hash = "sha256:f79298c8a098cec150a597c8eba58ecdab96e3bdc4b9bc4f9983635031740492", size = 2927037, upload-time = "2025-10-09T09:04:23.782Z" },
 ]
 
 [[package]]
@@ -916,8 +941,11 @@ name = "nvidia-cuda-runtime-cu12"
 version = "12.6.77"
 source = { registry = "https://pypi.org/simple" }
 wheels = [
+    { url = "https://files.pythonhosted.org/packages/8f/ea/590b2ac00d772a8abd1c387a92b46486d2679ca6622fd25c18ff76265663/nvidia_cuda_runtime_cu12-12.6.77-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:6116fad3e049e04791c0256a9778c16237837c08b27ed8c8401e2e45de8d60cd", size = 908052, upload-time = "2024-11-20T17:35:19.905Z" },
+    { url = "https://files.pythonhosted.org/packages/b7/3d/159023799677126e20c8fd580cca09eeb28d5c5a624adc7f793b9aa8bbfa/nvidia_cuda_runtime_cu12-12.6.77-py3-none-manylinux2014_aarch64.whl", hash = "sha256:d461264ecb429c84c8879a7153499ddc7b19b5f8d84c204307491989a365588e", size = 908040, upload-time = "2024-10-01T16:57:22.221Z" },
     { url = "https://files.pythonhosted.org/packages/e1/23/e717c5ac26d26cf39a27fbc076240fad2e3b817e5889d671b67f4f9f49c5/nvidia_cuda_runtime_cu12-12.6.77-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:ba3b56a4f896141e25e19ab287cd71e52a6a0f4b29d0d31609f60e3b4d5219b7", size = 897690, upload-time = "2024-11-20T17:35:30.697Z" },
     { url = "https://files.pythonhosted.org/packages/f0/62/65c05e161eeddbafeca24dc461f47de550d9fa8a7e04eb213e32b55cfd99/nvidia_cuda_runtime_cu12-12.6.77-py3-none-manylinux2014_x86_64.whl", hash = "sha256:a84d15d5e1da416dd4774cb42edf5e954a3e60cc945698dc1d5be02321c44dc8", size = 897678, upload-time = "2024-10-01T16:57:33.821Z" },
+    { url = "https://files.pythonhosted.org/packages/fa/76/4c80fa138333cc975743fd0687a745fccb30d167f906f13c1c7f9a85e5ea/nvidia_cuda_runtime_cu12-12.6.77-py3-none-win_amd64.whl", hash = "sha256:86c58044c824bf3c173c49a2dbc7a6c8b53cb4e4dca50068be0bf64e9dab3f7f", size = 891773, upload-time = "2024-10-01T17:09:26.362Z" },
 ]
 
 [[package]]
@@ -928,10 +956,12 @@ resolution-markers = [
     "platform_machine == 'x86_64' and sys_platform == 'linux'",
 ]
 dependencies = [
-    { name = "nvidia-cublas-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cublas-cu12", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 wheels = [
+    { url = "https://files.pythonhosted.org/packages/fa/41/e79269ce215c857c935fd86bcfe91a451a584dfc27f1e068f568b9ad1ab7/nvidia_cudnn_cu12-9.10.2.21-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:c9132cc3f8958447b4910a1720036d9eff5928cc3179b0a51fb6d167c6cc87d8", size = 705026878, upload-time = "2025-06-06T21:52:51.348Z" },
     { url = "https://files.pythonhosted.org/packages/ba/51/e123d997aa098c61d029f76663dedbfb9bc8dcf8c60cbd6adbe42f76d049/nvidia_cudnn_cu12-9.10.2.21-py3-none-manylinux_2_27_x86_64.whl", hash = "sha256:949452be657fa16687d0930933f032835951ef0892b37d2d53824d1a84dc97a8", size = 706758467, upload-time = "2025-06-06T21:54:08.597Z" },
+    { url = "https://files.pythonhosted.org/packages/3d/90/0bd6e586701b3a890fd38aa71c387dab4883d619d6e5ad912ccbd05bfd67/nvidia_cudnn_cu12-9.10.2.21-py3-none-win_amd64.whl", hash = "sha256:c6288de7d63e6cf62988f0923f96dc339cea362decb1bf5b3141883392a7d65e", size = 692992268, upload-time = "2025-06-06T21:55:18.114Z" },
 ]
 
 [[package]]
@@ -940,17 +970,17 @@ version = "9.23.1.3"
 source = { registry = "https://pypi.org/simple" }
 resolution-markers = [
     "platform_machine == 'aarch64' and sys_platform == 'linux'",
+    "platform_machine != 'aarch64' and platform_machine != 's390x' and platform_machine != 'x86_64' and sys_platform == 'linux'",
+    "platform_machine == 's390x' and sys_platform == 'linux'",
     "platform_machine != 's390x' and sys_platform == 'win32'",
     "platform_machine == 's390x' and sys_platform == 'win32'",
     "platform_machine != 's390x' and sys_platform != 'darwin' and sys_platform != 'linux' and sys_platform != 'win32'",
     "platform_machine == 's390x' and sys_platform != 'darwin' and sys_platform != 'linux' and sys_platform != 'win32'",
     "platform_machine != 's390x' and sys_platform == 'darwin'",
     "platform_machine == 's390x' and sys_platform == 'darwin'",
-    "platform_machine != 'aarch64' and platform_machine != 's390x' and platform_machine != 'x86_64' and sys_platform == 'linux'",
-    "platform_machine == 's390x' and sys_platform == 'linux'",
 ]
 dependencies = [
-    { name = "nvidia-cublas-cu12", marker = "platform_machine != 'x86_64' or sys_platform != 'linux'" },
+    { name = "nvidia-cublas-cu12", marker = "platform_machine != 'x86_64' or sys_platform != 'linux' or (extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/10/30/ecca1c8194c8077c4b57a3d96b56d96f15852551b01b919bae6429d92218/nvidia_cudnn_cu12-9.23.1.3-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:6dbc18f05aab2a323a4ffd43d985410608f7db7db9a8596e189cddbd3e527441", size = 778220760, upload-time = "2026-06-09T19:38:19.281Z" },
@@ -963,11 +993,12 @@ name = "nvidia-cudnn-cu13"
 version = "9.20.0.48"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-cublas", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cublas", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/56/c5/83384d846b2fd17c44bd499b36c75a45ed4f095fbbb2252294e89cea5c5c/nvidia_cudnn_cu13-9.20.0.48-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:e31454ae00094b0c55319d9d15b6fa2fc50a9e1c0f5c8c80fb75258234e731e1", size = 444574296, upload-time = "2026-03-09T19:28:27.751Z" },
     { url = "https://files.pythonhosted.org/packages/6e/5e/edb9c0ae051602c3ccaffe424256463636d639e27d7f302dde9975ef9e7a/nvidia_cudnn_cu13-9.20.0.48-py3-none-manylinux_2_27_x86_64.whl", hash = "sha256:0c45dd8eeb50b603f07995b1b300c62ffe6a1980482b82b3bcf94a4ca9d49304", size = 366173588, upload-time = "2026-03-09T19:29:34.474Z" },
+    { url = "https://files.pythonhosted.org/packages/78/39/21507455b1bca8b5702a9e9fc6ce73735f216f558dac2c9ede58e4d456b8/nvidia_cudnn_cu13-9.20.0.48-py3-none-win_amd64.whl", hash = "sha256:af8139732b99c0118be65ea5aac97f0d46018f8c552889e49d2fb0c6261a4a24", size = 350712614, upload-time = "2026-03-09T19:31:11.398Z" },
 ]
 
 [[package]]
@@ -975,11 +1006,12 @@ name = "nvidia-cufft"
 version = "12.0.0.61"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-nvjitlink", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-nvjitlink", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/8b/ae/f417a75c0259e85c1d2f83ca4e960289a5f814ed0cea74d18c353d3e989d/nvidia_cufft-12.0.0.61-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:2708c852ef8cd89d1d2068bdbece0aa188813a0c934db3779b9b1faa8442e5f5", size = 214053554, upload-time = "2025-09-04T08:31:38.196Z" },
     { url = "https://files.pythonhosted.org/packages/a8/2f/7b57e29836ea8714f81e9898409196f47d772d5ddedddf1592eadb8ab743/nvidia_cufft-12.0.0.61-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:6c44f692dce8fd5ffd3e3df134b6cdb9c2f72d99cf40b62c32dde45eea9ddad3", size = 214085489, upload-time = "2025-09-04T08:31:56.044Z" },
+    { url = "https://files.pythonhosted.org/packages/85/b2/f8af21a2ed1beed337a6a02c5a28aeb85441f4d578ec3d529543c775ea4b/nvidia_cufft-12.0.0.61-py3-none-win_amd64.whl", hash = "sha256:2abce5b39d2f5ae12730fb7e5db6696533e36c26e2d3e8fd1750bdd2853364eb", size = 213342123, upload-time = "2025-09-04T08:40:51.145Z" },
 ]
 
 [[package]]
@@ -987,11 +1019,14 @@ name = "nvidia-cufft-cu12"
 version = "11.3.0.4"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-nvjitlink-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 wheels = [
+    { url = "https://files.pythonhosted.org/packages/1f/37/c50d2b2f2c07e146776389e3080f4faf70bcc4fa6e19d65bb54ca174ebc3/nvidia_cufft_cu12-11.3.0.4-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:d16079550df460376455cba121db6564089176d9bac9e4f360493ca4741b22a6", size = 200164144, upload-time = "2024-11-20T17:40:58.288Z" },
+    { url = "https://files.pythonhosted.org/packages/ce/f5/188566814b7339e893f8d210d3a5332352b1409815908dad6a363dcceac1/nvidia_cufft_cu12-11.3.0.4-py3-none-manylinux2014_aarch64.whl", hash = "sha256:8510990de9f96c803a051822618d42bf6cb8f069ff3f48d93a8486efdacb48fb", size = 200164135, upload-time = "2024-10-01T17:03:24.212Z" },
     { url = "https://files.pythonhosted.org/packages/8f/16/73727675941ab8e6ffd86ca3a4b7b47065edcca7a997920b831f8147c99d/nvidia_cufft_cu12-11.3.0.4-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:ccba62eb9cef5559abd5e0d54ceed2d9934030f51163df018532142a8ec533e5", size = 200221632, upload-time = "2024-11-20T17:41:32.357Z" },
     { url = "https://files.pythonhosted.org/packages/60/de/99ec247a07ea40c969d904fc14f3a356b3e2a704121675b75c366b694ee1/nvidia_cufft_cu12-11.3.0.4-py3-none-manylinux2014_x86_64.whl", hash = "sha256:768160ac89f6f7b459bee747e8d175dbf53619cfe74b2a5636264163138013ca", size = 200221622, upload-time = "2024-10-01T17:03:58.79Z" },
+    { url = "https://files.pythonhosted.org/packages/b4/38/36fd800cec8f6e89b7c1576edaaf8076e69ec631644cdbc1b5f2e2b5a9df/nvidia_cufft_cu12-11.3.0.4-py3-none-win_amd64.whl", hash = "sha256:6048ebddfb90d09d2707efb1fd78d4e3a77cb3ae4dc60e19aab6be0ece2ae464", size = 199356881, upload-time = "2024-10-01T17:13:01.861Z" },
 ]
 
 [[package]]
@@ -1009,6 +1044,7 @@ version = "1.11.1.6"
 source = { registry = "https://pypi.org/simple" }
 wheels = [
     { url = "https://files.pythonhosted.org/packages/b2/66/cc9876340ac68ae71b15c743ddb13f8b30d5244af344ec8322b449e35426/nvidia_cufile_cu12-1.11.1.6-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:cc23469d1c7e52ce6c1d55253273d32c565dd22068647f3aa59b3c6b005bf159", size = 1142103, upload-time = "2024-11-20T17:42:11.83Z" },
+    { url = "https://files.pythonhosted.org/packages/17/bf/cc834147263b929229ce4aadd62869f0b195e98569d4c28b23edc72b85d9/nvidia_cufile_cu12-1.11.1.6-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:8f57a0051dcf2543f6dc2b98a98cb2719c37d3cee1baba8965d57f3bbc90d4db", size = 1066155, upload-time = "2024-11-20T17:41:49.376Z" },
 ]
 
 [[package]]
@@ -1018,6 +1054,7 @@ source = { registry = "https://pypi.org/simple" }
 wheels = [
     { url = "https://files.pythonhosted.org/packages/1e/72/7c2ae24fb6b63a32e6ae5d241cc65263ea18d08802aaae087d9f013335a2/nvidia_curand-10.4.0.35-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:133df5a7509c3e292aaa2b477afd0194f06ce4ea24d714d616ff36439cee349a", size = 61962106, upload-time = "2025-08-04T10:21:41.128Z" },
     { url = "https://files.pythonhosted.org/packages/a5/9f/be0a41ca4a4917abf5cb9ae0daff1a6060cc5de950aec0396de9f3b52bc5/nvidia_curand-10.4.0.35-py3-none-manylinux_2_27_x86_64.whl", hash = "sha256:1aee33a5da6e1db083fe2b90082def8915f30f3248d5896bcec36a579d941bfc", size = 59544258, upload-time = "2025-08-04T10:22:03.992Z" },
+    { url = "https://files.pythonhosted.org/packages/99/27/72103153b1ffc00e09fdc40ac970235343dcd1ea8bd762e84d2d73219ffa/nvidia_curand-10.4.0.35-py3-none-win_amd64.whl", hash = "sha256:65b1710aa6961d326b411e314b374290904c5ddf41dc3f766ebc3f1d7d4ca69f", size = 55242481, upload-time = "2025-08-04T10:30:41.831Z" },
 ]
 
 [[package]]
@@ -1025,8 +1062,11 @@ name = "nvidia-curand-cu12"
 version = "10.3.7.77"
 source = { registry = "https://pypi.org/simple" }
 wheels = [
+    { url = "https://files.pythonhosted.org/packages/42/ac/36543605358a355632f1a6faa3e2d5dfb91eab1e4bc7d552040e0383c335/nvidia_curand_cu12-10.3.7.77-py3-none-manylinux2014_aarch64.whl", hash = "sha256:6e82df077060ea28e37f48a3ec442a8f47690c7499bff392a5938614b56c98d8", size = 56289881, upload-time = "2024-10-01T17:04:18.981Z" },
     { url = "https://files.pythonhosted.org/packages/73/1b/44a01c4e70933637c93e6e1a8063d1e998b50213a6b65ac5a9169c47e98e/nvidia_curand_cu12-10.3.7.77-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:a42cd1344297f70b9e39a1e4f467a4e1c10f1da54ff7a85c12197f6c652c8bdf", size = 56279010, upload-time = "2024-11-20T17:42:50.958Z" },
     { url = "https://files.pythonhosted.org/packages/4a/aa/2c7ff0b5ee02eaef890c0ce7d4f74bc30901871c5e45dee1ae6d0083cd80/nvidia_curand_cu12-10.3.7.77-py3-none-manylinux2014_x86_64.whl", hash = "sha256:99f1a32f1ac2bd134897fc7a203f779303261268a65762a623bf30cc9fe79117", size = 56279000, upload-time = "2024-10-01T17:04:45.274Z" },
+    { url = "https://files.pythonhosted.org/packages/a6/02/5362a9396f23f7de1dd8a64369e87c85ffff8216fc8194ace0fa45ba27a5/nvidia_curand_cu12-10.3.7.77-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:7b2ed8e95595c3591d984ea3603dd66fe6ce6812b886d59049988a712ed06b6e", size = 56289882, upload-time = "2024-11-20T17:42:25.222Z" },
+    { url = "https://files.pythonhosted.org/packages/a9/a8/0cd0cec757bd4b4b4ef150fca62ec064db7d08a291dced835a0be7d2c147/nvidia_curand_cu12-10.3.7.77-py3-none-win_amd64.whl", hash = "sha256:6d6d935ffba0f3d439b7cd968192ff068fafd9018dbf1b85b37261b13cfc9905", size = 55783873, upload-time = "2024-10-01T17:13:30.377Z" },
 ]
 
 [[package]]
@@ -1034,13 +1074,14 @@ name = "nvidia-cusolver"
 version = "12.0.4.66"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-cublas", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cublas", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "nvidia-cusparse", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cusparse", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "nvidia-nvjitlink", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-nvjitlink", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/c8/c3/b30c9e935fc01e3da443ec0116ed1b2a009bb867f5324d3f2d7e533e776b/nvidia_cusolver-12.0.4.66-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:02c2457eaa9e39de20f880f4bd8820e6a1cfb9f9a34f820eb12a155aa5bc92d2", size = 223467760, upload-time = "2025-09-04T08:33:04.222Z" },
     { url = "https://files.pythonhosted.org/packages/5f/67/cba3777620cdacb99102da4042883709c41c709f4b6323c10781a9c3aa34/nvidia_cusolver-12.0.4.66-py3-none-manylinux_2_27_x86_64.whl", hash = "sha256:0a759da5dea5c0ea10fd307de75cdeb59e7ea4fcb8add0924859b944babf1112", size = 200941980, upload-time = "2025-09-04T08:33:22.767Z" },
+    { url = "https://files.pythonhosted.org/packages/99/ef/332a0101260ca78a1daef046bf0b06199e8ed4dac1d2aa698289c358169c/nvidia_cusolver-12.0.4.66-py3-none-win_amd64.whl", hash = "sha256:16515bd33a8e76bb54d024cfa068fa68d30e80fc34b9e1090813ea9362e0cb65", size = 193551444, upload-time = "2025-09-04T08:41:46.813Z" },
 ]
 
 [[package]]
@@ -1048,13 +1089,16 @@ name = "nvidia-cusolver-cu12"
 version = "11.7.1.2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-cublas-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cublas-cu12", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "nvidia-cusparse-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cusparse-cu12", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "nvidia-nvjitlink-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 wheels = [
+    { url = "https://files.pythonhosted.org/packages/93/17/dbe1aa865e4fdc7b6d4d0dd308fdd5aaab60f939abfc0ea1954eac4fb113/nvidia_cusolver_cu12-11.7.1.2-py3-none-manylinux2014_aarch64.whl", hash = "sha256:0ce237ef60acde1efc457335a2ddadfd7610b892d94efee7b776c64bb1cac9e0", size = 157833628, upload-time = "2024-10-01T17:05:05.591Z" },
     { url = "https://files.pythonhosted.org/packages/f0/6e/c2cf12c9ff8b872e92b4a5740701e51ff17689c4d726fca91875b07f655d/nvidia_cusolver_cu12-11.7.1.2-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:e9e49843a7707e42022babb9bcfa33c29857a93b88020c4e4434656a655b698c", size = 158229790, upload-time = "2024-11-20T17:43:43.211Z" },
     { url = "https://files.pythonhosted.org/packages/9f/81/baba53585da791d043c10084cf9553e074548408e04ae884cfe9193bd484/nvidia_cusolver_cu12-11.7.1.2-py3-none-manylinux2014_x86_64.whl", hash = "sha256:6cf28f17f64107a0c4d7802be5ff5537b2130bfc112f25d5a30df227058ca0e6", size = 158229780, upload-time = "2024-10-01T17:05:39.875Z" },
+    { url = "https://files.pythonhosted.org/packages/7c/5f/07d0ba3b7f19be5a5ec32a8679fc9384cfd9fc6c869825e93be9f28d6690/nvidia_cusolver_cu12-11.7.1.2-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:dbbe4fc38ec1289c7e5230e16248365e375c3673c9c8bac5796e2e20db07f56e", size = 157833630, upload-time = "2024-11-20T17:43:16.77Z" },
+    { url = "https://files.pythonhosted.org/packages/d4/53/fff50a0808df7113d77e3bbc7c2b7eaed6f57d5eb80fbe93ead2aea1e09a/nvidia_cusolver_cu12-11.7.1.2-py3-none-win_amd64.whl", hash = "sha256:6813f9d8073f555444a8705f3ab0296d3e1cb37a16d694c5fc8b862a0d8706d7", size = 149287877, upload-time = "2024-10-01T17:13:49.804Z" },
 ]
 
 [[package]]
@@ -1062,11 +1106,12 @@ name = "nvidia-cusparse"
 version = "12.6.3.3"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-nvjitlink", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-nvjitlink", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/f8/94/5c26f33738ae35276672f12615a64bd008ed5be6d1ebcb23579285d960a9/nvidia_cusparse-12.6.3.3-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:80bcc4662f23f1054ee334a15c72b8940402975e0eab63178fc7e670aa59472c", size = 162155568, upload-time = "2025-09-04T08:33:42.864Z" },
     { url = "https://files.pythonhosted.org/packages/fa/18/623c77619c31d62efd55302939756966f3ecc8d724a14dab2b75f1508850/nvidia_cusparse-12.6.3.3-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:2b3c89c88d01ee0e477cb7f82ef60a11a4bcd57b6b87c33f789350b59759360b", size = 145942937, upload-time = "2025-09-04T08:33:58.029Z" },
+    { url = "https://files.pythonhosted.org/packages/02/b0/b043d6f3480f102f885cf87fc3ffd3edcb5e23b855025a50e2ef4d059185/nvidia_cusparse-12.6.3.3-py3-none-win_amd64.whl", hash = "sha256:cbcf42feb737bd7ec15b4c0a63e62351886bd3f975027b8815d7f720a2b5ea79", size = 143783033, upload-time = "2025-09-04T08:42:12.391Z" },
 ]
 
 [[package]]
@@ -1074,11 +1119,14 @@ name = "nvidia-cusparse-cu12"
 version = "12.5.4.2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-nvjitlink-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 wheels = [
+    { url = "https://files.pythonhosted.org/packages/eb/eb/6681efd0aa7df96b4f8067b3ce7246833dd36830bb4cec8896182773db7d/nvidia_cusparse_cu12-12.5.4.2-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:d25b62fb18751758fe3c93a4a08eff08effedfe4edf1c6bb5afd0890fe88f887", size = 216451147, upload-time = "2024-11-20T17:44:18.055Z" },
+    { url = "https://files.pythonhosted.org/packages/d3/56/3af21e43014eb40134dea004e8d0f1ef19d9596a39e4d497d5a7de01669f/nvidia_cusparse_cu12-12.5.4.2-py3-none-manylinux2014_aarch64.whl", hash = "sha256:7aa32fa5470cf754f72d1116c7cbc300b4e638d3ae5304cfa4a638a5b87161b1", size = 216451135, upload-time = "2024-10-01T17:06:03.826Z" },
     { url = "https://files.pythonhosted.org/packages/06/1e/b8b7c2f4099a37b96af5c9bb158632ea9e5d9d27d7391d7eb8fc45236674/nvidia_cusparse_cu12-12.5.4.2-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:7556d9eca156e18184b94947ade0fba5bb47d69cec46bf8660fd2c71a4b48b73", size = 216561367, upload-time = "2024-11-20T17:44:54.824Z" },
     { url = "https://files.pythonhosted.org/packages/43/ac/64c4316ba163e8217a99680c7605f779accffc6a4bcd0c778c12948d3707/nvidia_cusparse_cu12-12.5.4.2-py3-none-manylinux2014_x86_64.whl", hash = "sha256:23749a6571191a215cb74d1cdbff4a86e7b19f1200c071b3fcf844a5bea23a2f", size = 216561357, upload-time = "2024-10-01T17:06:29.861Z" },
+    { url = "https://files.pythonhosted.org/packages/45/ef/876ad8e4260e1128e6d4aac803d9d51baf3791ebdb4a9b8d9b8db032b4b0/nvidia_cusparse_cu12-12.5.4.2-py3-none-win_amd64.whl", hash = "sha256:4acb8c08855a26d737398cba8fb6f8f5045d93f82612b4cfd84645a2332ccf20", size = 213712630, upload-time = "2024-10-01T17:14:23.779Z" },
 ]
 
 [[package]]
@@ -1086,7 +1134,9 @@ name = "nvidia-cusparselt-cu12"
 version = "0.7.1"
 source = { registry = "https://pypi.org/simple" }
 wheels = [
+    { url = "https://files.pythonhosted.org/packages/73/b9/598f6ff36faaece4b3c50d26f50e38661499ff34346f00e057760b35cc9d/nvidia_cusparselt_cu12-0.7.1-py3-none-manylinux2014_aarch64.whl", hash = "sha256:8878dce784d0fac90131b6817b607e803c36e629ba34dc5b433471382196b6a5", size = 283835557, upload-time = "2025-02-26T00:16:54.265Z" },
     { url = "https://files.pythonhosted.org/packages/56/79/12978b96bd44274fe38b5dde5cfb660b1d114f70a65ef962bcbbed99b549/nvidia_cusparselt_cu12-0.7.1-py3-none-manylinux2014_x86_64.whl", hash = "sha256:f1bb701d6b930d5a7cea44c19ceb973311500847f81b634d802b7b539dc55623", size = 287193691, upload-time = "2025-02-26T00:15:44.104Z" },
+    { url = "https://files.pythonhosted.org/packages/2f/d8/a6b0d0d0c2435e9310f3e2bb0d9c9dd4c33daef86aa5f30b3681defd37ea/nvidia_cusparselt_cu12-0.7.1-py3-none-win_amd64.whl", hash = "sha256:f67fbb5831940ec829c9117b7f33807db9f9678dc2a617fbe781cac17b4e1075", size = 271020911, upload-time = "2025-02-26T00:14:47.204Z" },
 ]
 
 [[package]]
@@ -1096,6 +1146,7 @@ source = { registry = "https://pypi.org/simple" }
 wheels = [
     { url = "https://files.pythonhosted.org/packages/46/e1/cdc1797eadf82d3a9a575a19b33fdc871a97edbec42c00b5b5e914f4aff4/nvidia_cusparselt_cu13-0.8.1-py3-none-manylinux2014_aarch64.whl", hash = "sha256:4dca476c50bf4780d46cd0bfbd82e2bc10a08e4fef7950917ce8d7578d22a23f", size = 221051344, upload-time = "2025-09-05T18:49:51.289Z" },
     { url = "https://files.pythonhosted.org/packages/34/7d/2661f2fb3ac4302f3a246f5fc030213ac60c1fe0bce84f9783dbd831dbb7/nvidia_cusparselt_cu13-0.8.1-py3-none-manylinux2014_x86_64.whl", hash = "sha256:786ce87568c303fadb5afcc7102d454cd3040d75f6f8626f5db460d1871f4dd0", size = 170148586, upload-time = "2025-09-05T18:50:50.248Z" },
+    { url = "https://files.pythonhosted.org/packages/31/83/f3647ce26916c94a6ca4ff1810623e2c405cff2dea6e78d29516b2514df9/nvidia_cusparselt_cu13-0.8.1-py3-none-win_amd64.whl", hash = "sha256:dccbd362f91a7b9024d1f55ee9f548ac065027ff15d8c8b0db889ab3a8f31215", size = 156885108, upload-time = "2025-09-05T18:51:35.958Z" },
 ]
 
 [[package]]
@@ -1112,6 +1163,7 @@ name = "nvidia-nccl-cu12"
 version = "2.29.3"
 source = { registry = "https://pypi.org/simple" }
 wheels = [
+    { url = "https://files.pythonhosted.org/packages/28/cf/bcf8bb0c0030b1b9a345331f6281c37d2a8669758521eb93c382f6f87c8f/nvidia_nccl_cu12-2.29.3-py3-none-manylinux_2_18_aarch64.whl", hash = "sha256:6351b79dc7d2cc3d654ea1523616b9eeded71fe9c8da66b71eef9a5d1b2adad4", size = 289708535, upload-time = "2026-02-03T21:10:58.804Z" },
     { url = "https://files.pythonhosted.org/packages/31/5a/cac7d231f322b66caa16fd4b136ebc8e4b18b2805811c2d58dc47210cdea/nvidia_nccl_cu12-2.29.3-py3-none-manylinux_2_18_x86_64.whl", hash = "sha256:35ad42e7d5d722a83c36a3a478e281c20a5646383deaf1b9ed1a9ab7d61bed53", size = 289760316, upload-time = "2026-02-03T21:11:37.899Z" },
 ]
 
@@ -1131,6 +1183,7 @@ source = { registry = "https://pypi.org/simple" }
 wheels = [
     { url = "https://files.pythonhosted.org/packages/56/7a/123e033aaff487c77107195fa5a2b8686795ca537935a24efae476c41f05/nvidia_nvjitlink-13.0.88-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:13a74f429e23b921c1109976abefacc69835f2f433ebd323d3946e11d804e47b", size = 40713933, upload-time = "2025-09-04T08:35:43.553Z" },
     { url = "https://files.pythonhosted.org/packages/ab/2c/93c5250e64df4f894f1cbb397c6fd71f79813f9fd79d7cd61de3f97b3c2d/nvidia_nvjitlink-13.0.88-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:e931536ccc7d467a98ba1d8b89ff7fa7f1fa3b13f2b0069118cd7f47bff07d0c", size = 38768748, upload-time = "2025-09-04T08:35:20.008Z" },
+    { url = "https://files.pythonhosted.org/packages/e4/01/07530b0e37546231052e30234540289c42eaffa486f1a34a87fed340157b/nvidia_nvjitlink-13.0.88-py3-none-win_amd64.whl", hash = "sha256:634e96e3da9ef845ae744097a1f289238ecf946ce0b82e93cdce14b9782e682f", size = 36035115, upload-time = "2025-09-04T08:43:03.001Z" },
 ]
 
 [[package]]
@@ -1139,6 +1192,8 @@ version = "12.6.85"
 source = { registry = "https://pypi.org/simple" }
 wheels = [
     { url = "https://files.pythonhosted.org/packages/9d/d7/c5383e47c7e9bf1c99d5bd2a8c935af2b6d705ad831a7ec5c97db4d82f4f/nvidia_nvjitlink_cu12-12.6.85-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:eedc36df9e88b682efe4309aa16b5b4e78c2407eac59e8c10a6a47535164369a", size = 19744971, upload-time = "2024-11-20T17:46:53.366Z" },
+    { url = "https://files.pythonhosted.org/packages/31/db/dc71113d441f208cdfe7ae10d4983884e13f464a6252450693365e166dcf/nvidia_nvjitlink_cu12-12.6.85-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:cf4eaa7d4b6b543ffd69d6abfb11efdeb2db48270d94dfd3a452c24150829e41", size = 19270338, upload-time = "2024-11-20T17:46:29.758Z" },
+    { url = "https://files.pythonhosted.org/packages/89/76/93c1467b1387387440a4d25102d86b7794535449b689f8e2dc22c1c8ff7f/nvidia_nvjitlink_cu12-12.6.85-py3-none-win_amd64.whl", hash = "sha256:e61120e52ed675747825cdd16febc6a0730537451d867ee58bee3853b1b13d1c", size = 161908572, upload-time = "2024-11-20T17:52:40.124Z" },
 ]
 
 [[package]]
@@ -1146,6 +1201,7 @@ name = "nvidia-nvshmem-cu12"
 version = "3.4.5"
 source = { registry = "https://pypi.org/simple" }
 wheels = [
+    { url = "https://files.pythonhosted.org/packages/1d/6a/03aa43cc9bd3ad91553a88b5f6fb25ed6a3752ae86ce2180221962bc2aa5/nvidia_nvshmem_cu12-3.4.5-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:0b48363fc6964dede448029434c6abed6c5e37f823cb43c3bcde7ecfc0457e15", size = 138936938, upload-time = "2025-09-06T00:32:05.589Z" },
     { url = "https://files.pythonhosted.org/packages/b5/09/6ea3ea725f82e1e76684f0708bbedd871fc96da89945adeba65c3835a64c/nvidia_nvshmem_cu12-3.4.5-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:042f2500f24c021db8a06c5eec2539027d57460e1c1a762055a6554f72c369bd", size = 139103095, upload-time = "2025-09-06T00:32:31.266Z" },
 ]
 
@@ -1165,6 +1221,7 @@ source = { registry = "https://pypi.org/simple" }
 wheels = [
     { url = "https://files.pythonhosted.org/packages/c2/f3/d86c845465a2723ad7e1e5c36dcd75ddb82898b3f53be47ebd429fb2fa5d/nvidia_nvtx-13.0.85-py3-none-manylinux1_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:4936d1d6780fbe68db454f5e72a42ff64d1fd6397df9f363ae786930fd5c1cd4", size = 148047, upload-time = "2025-09-04T08:29:01.761Z" },
     { url = "https://files.pythonhosted.org/packages/a8/64/3708a90d1ebe202ffdeb7185f878a3c84d15c2b2c31858da2ce0583e2def/nvidia_nvtx-13.0.85-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:cb7780edb6b14107373c835bf8b72e7a178bac7367e23da7acb108f973f157a6", size = 148878, upload-time = "2025-09-04T08:28:53.627Z" },
+    { url = "https://files.pythonhosted.org/packages/d2/50/0e2220f8620a177de994211186ffc5bfa9f2ce1e1282797f8f90096f9f88/nvidia_nvtx-13.0.85-py3-none-win_amd64.whl", hash = "sha256:d66ea44254dd3c6eacc300047af6e1288d2269dd072b417e0adffbf479e18519", size = 137066, upload-time = "2025-09-04T08:39:25.649Z" },
 ]
 
 [[package]]
@@ -1172,8 +1229,11 @@ name = "nvidia-nvtx-cu12"
 version = "12.6.77"
 source = { registry = "https://pypi.org/simple" }
 wheels = [
+    { url = "https://files.pythonhosted.org/packages/b9/93/80f8a520375af9d7ee44571a6544653a176e53c2b8ccce85b97b83c2491b/nvidia_nvtx_cu12-12.6.77-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:f44f8d86bb7d5629988d61c8d3ae61dddb2015dee142740536bc7481b022fe4b", size = 90549, upload-time = "2024-11-20T17:38:17.387Z" },
+    { url = "https://files.pythonhosted.org/packages/2b/53/36e2fd6c7068997169b49ffc8c12d5af5e5ff209df6e1a2c4d373b3a638f/nvidia_nvtx_cu12-12.6.77-py3-none-manylinux2014_aarch64.whl", hash = "sha256:adcaabb9d436c9761fca2b13959a2d237c5f9fd406c8e4b723c695409ff88059", size = 90539, upload-time = "2024-10-01T17:00:27.179Z" },
     { url = "https://files.pythonhosted.org/packages/56/9a/fff8376f8e3d084cd1530e1ef7b879bb7d6d265620c95c1b322725c694f4/nvidia_nvtx_cu12-12.6.77-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:b90bed3df379fa79afbd21be8e04a0314336b8ae16768b58f2d34cb1d04cd7d2", size = 89276, upload-time = "2024-11-20T17:38:27.621Z" },
     { url = "https://files.pythonhosted.org/packages/9e/4e/0d0c945463719429b7bd21dece907ad0bde437a2ff12b9b12fee94722ab0/nvidia_nvtx_cu12-12.6.77-py3-none-manylinux2014_x86_64.whl", hash = "sha256:6574241a3ec5fdc9334353ab8c479fe75841dbe8f4532a8fc97ce63503330ba1", size = 89265, upload-time = "2024-10-01T17:00:38.172Z" },
+    { url = "https://files.pythonhosted.org/packages/f7/cd/98a447919d4ed14d407ac82b14b0a0c9c1dbfe81099934b1fc3bfd1e6316/nvidia_nvtx_cu12-12.6.77-py3-none-win_amd64.whl", hash = "sha256:2fb11a4af04a5e6c84073e6404d26588a34afd35379f0855a99797897efa75c0", size = 56434, upload-time = "2024-10-01T17:11:13.124Z" },
 ]
 
 [[package]]
@@ -1238,10 +1298,10 @@ name = "onnxruntime-gpu"
 version = "1.26.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "flatbuffers" },
+    { name = "flatbuffers", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "numpy" },
+    { name = "numpy", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "packaging" },
+    { name = "packaging", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "protobuf" },
+    { name = "protobuf", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/dd/97/fe8979f44b9275654b42f7bb556e30789b71a1b22998c83b540df2b1b774/onnxruntime_gpu-1.26.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:cfda2fad535595bfc3e570eb588092717711dcb2957656d814695e0c9ceb1508", size = 276974871, upload-time = "2026-05-08T19:15:58.052Z" },
@@ -1458,7 +1518,7 @@ name = "pytest"
 version = "9.0.3"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "colorama", marker = "sys_platform == 'win32'" },
+    { name = "colorama", marker = "sys_platform == 'win32' or (extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
     { name = "iniconfig" },
     { name = "packaging" },
     { name = "pluggy" },
@@ -1861,13 +1921,13 @@ resolution-markers = [
     "platform_machine != 's390x' and sys_platform == 'darwin'",
 ]
 dependencies = [
-    { name = "filelock", marker = "platform_machine != 's390x' and sys_platform == 'darwin'" },
+    { name = "filelock", marker = "(platform_machine != 's390x' and sys_platform == 'darwin') or (platform_machine == 's390x' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'darwin' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "fsspec", marker = "platform_machine != 's390x' and sys_platform == 'darwin'" },
+    { name = "fsspec", marker = "(platform_machine != 's390x' and sys_platform == 'darwin') or (platform_machine == 's390x' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'darwin' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "jinja2", marker = "platform_machine != 's390x' and sys_platform == 'darwin'" },
+    { name = "jinja2", marker = "(platform_machine != 's390x' and sys_platform == 'darwin') or (platform_machine == 's390x' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'darwin' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "networkx", marker = "platform_machine != 's390x' and sys_platform == 'darwin'" },
+    { name = "networkx", marker = "(platform_machine != 's390x' and sys_platform == 'darwin') or (platform_machine == 's390x' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'darwin' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "setuptools", marker = "platform_machine != 's390x' and sys_platform == 'darwin'" },
+    { name = "setuptools", marker = "(platform_machine != 's390x' and sys_platform == 'darwin') or (platform_machine == 's390x' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'darwin' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "sympy", marker = "platform_machine != 's390x' and sys_platform == 'darwin'" },
+    { name = "sympy", marker = "(platform_machine != 's390x' and sys_platform == 'darwin') or (platform_machine == 's390x' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'darwin' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "typing-extensions", marker = "platform_machine != 's390x' and sys_platform == 'darwin'" },
+    { name = "typing-extensions", marker = "(platform_machine != 's390x' and sys_platform == 'darwin') or (platform_machine == 's390x' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'darwin' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 wheels = [
     { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.12.0-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:90dd587a5f61bfe1307148b581e2084fc5bc4a06e2b90a20e9a36b81087ff16b", upload-time = "2026-05-12T16:20:17Z" },
@@ -1885,31 +1945,39 @@ resolution-markers = [
     "platform_machine == 's390x' and sys_platform == 'linux'",
 ]
 dependencies = [
-    { name = "cuda-bindings", version = "13.3.1", source = { registry = "https://pypi.org/simple" }, marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "cuda-bindings", version = "13.3.1", source = { registry = "https://pypi.org/simple" }, marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "cuda-toolkit", version = "13.0.2", source = { registry = "https://pypi.org/simple" }, extra = ["cudart", "cufft", "cufile", "cupti", "curand", "cusolver", "cusparse", "nvjitlink", "nvrtc", "nvtx"], marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "cuda-toolkit", version = "13.0.2", source = { registry = "https://pypi.org/simple" }, extra = ["cudart", "cufft", "cufile", "cupti", "curand", "cusolver", "cusparse", "nvjitlink", "nvrtc", "nvtx"], marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "filelock", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "filelock", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "fsspec", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "fsspec", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "jinja2", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "jinja2", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "networkx", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "networkx", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "nvidia-cublas", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cublas", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "nvidia-cudnn-cu13", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cudnn-cu13", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "nvidia-cusparselt-cu13", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cusparselt-cu13", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "nvidia-nccl-cu13", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-nccl-cu13", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "nvidia-nvshmem-cu13", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-nvshmem-cu13", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "setuptools", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "setuptools", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "sympy", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "sympy", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "triton", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "triton", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "typing-extensions", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "typing-extensions", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 wheels = [
+    { url = "https://files.pythonhosted.org/packages/86/ca/01896c80ba921676aa45886b2c5b8d774912de2a1f719de48169c6f755cd/torch-2.12.0-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:90dd587a5f61bfe1307148b581e2084fc5bc4a06e2b90a20e9a36b81087ff16b", size = 88009511, upload-time = "2026-05-13T14:54:47.411Z" },
     { url = "https://files.pythonhosted.org/packages/a5/04/52bdaf4787eab6ac7d7f5851dff934e4def0bc8ead9c8fd2b69b3e529699/torch-2.12.0-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:864392c73b7654f4d2b3ae712f607937d0dbb1101c4555fbb41848106b297f39", size = 426383231, upload-time = "2026-05-13T14:53:32.129Z" },
     { url = "https://files.pythonhosted.org/packages/49/8a/94bdecd13f5aaa90d45920b89789d9fe7c6f4af8c3cdd7ce01fcb59908fc/torch-2.12.0-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:5d6b560dfa7d56291c07d615c3bb73e8d9943d9b6d87f76cd0d9d570c4797fa6", size = 532269288, upload-time = "2026-05-13T14:53:49.423Z" },
+    { url = "https://files.pythonhosted.org/packages/3e/2f/bdbaaa267de519ef1b73054bf590d8c93c37a266c9a4e24a01bd38b6918f/torch-2.12.0-cp313-cp313-win_amd64.whl", hash = "sha256:3fee918902090ade827643e758e98363278815de583c75d111fdd665ebffde9f", size = 122987706, upload-time = "2026-05-13T14:54:00.335Z" },
+    { url = "https://files.pythonhosted.org/packages/9b/ad/e95e822f3538171e22640a7fbe839a1fdb666600bf6487025de2ff03b11a/torch-2.12.0-cp313-cp313t-macosx_14_0_arm64.whl", hash = "sha256:10ee1448a9f304d3b987eb4656f664ba6e4d7b410ca7a5a7c642199777a2cf88", size = 88319556, upload-time = "2026-05-13T14:54:05.574Z" },
     { url = "https://files.pythonhosted.org/packages/b7/07/055d06d985b445d67422d25b033c11cf55bbb81785d4c4e68e28bca5820e/torch-2.12.0-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:af68dbf403439cae9ceaeaaf92f8352b460787dcd27b92aa05c40dd4a19c0f1e", size = 426397656, upload-time = "2026-05-13T14:52:38.84Z" },
     { url = "https://files.pythonhosted.org/packages/43/94/b0b4fdc3014122e0a7302fb90086d352aa48f2576f0b252561ebb38c01a8/torch-2.12.0-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:a6a2eebb237d3b1d9ad3b378e86d9b9e0782afdea8b1e0eba6a13646b9b49c07", size = 532183124, upload-time = "2026-05-13T14:53:16.178Z" },
+    { url = "https://files.pythonhosted.org/packages/d8/c8/052405e6ad05d3237bfe5a4df78f917773956f8e17813a2d44c059068b74/torch-2.12.0-cp313-cp313t-win_amd64.whl", hash = "sha256:2140e373e9a51a3e22ef62e8d14366d0b470d18f0adf19fdc757368077133a34", size = 123232462, upload-time = "2026-05-13T14:52:27.26Z" },
+    { url = "https://files.pythonhosted.org/packages/67/dc/ac069f8d6e8be701535921141055293b0d4819d3d7f224a4612cf157c7f9/torch-2.12.0-cp314-cp314-macosx_14_0_arm64.whl", hash = "sha256:f7dfae4a519197dfa050e98d8e36378a0fb5899625a875c2b54445005a2e404e", size = 88027282, upload-time = "2026-05-13T14:53:05.258Z" },
     { url = "https://files.pythonhosted.org/packages/33/c3/1c1eb00e34555b536dddf792676026a988d710ed36981aa00499b36b0620/torch-2.12.0-cp314-cp314-manylinux_2_28_aarch64.whl", hash = "sha256:891c769072637c74e9a5a77a3bc782894696d8ffec83b938df8536dee7f0ba78", size = 426386961, upload-time = "2026-05-13T14:51:28.406Z" },
     { url = "https://files.pythonhosted.org/packages/cd/d4/7e730dba0c7032a4154dc9056b76cf9625515e030e269cfbf8098fcfee7d/torch-2.12.0-cp314-cp314-manylinux_2_28_x86_64.whl", hash = "sha256:e2ad3eb85d39c3cab62dfa93ed5a73516e6a53c6713cb97d004004fe089f0f1f", size = 532272265, upload-time = "2026-05-13T14:51:59.308Z" },
+    { url = "https://files.pythonhosted.org/packages/f1/b4/92c80d1bbfee1c0036c06d1d2155a3065bd2423134c83bf8a47e65cd6b9b/torch-2.12.0-cp314-cp314-win_amd64.whl", hash = "sha256:c66696857e987efb8bc1777a37357ec4f60ab5e8af6250b83d6034437fa2d8f3", size = 122987138, upload-time = "2026-05-13T14:51:45.942Z" },
+    { url = "https://files.pythonhosted.org/packages/7b/78/2e12b37ce50a19a037d7bc62d652a5a8f27385a7b05859d6bc9204f20cfe/torch-2.12.0-cp314-cp314t-macosx_14_0_arm64.whl", hash = "sha256:b4556715c8572758625d62b6e0ae3b1f76c440221913a6fb5e100f321fb4fb02", size = 88320100, upload-time = "2026-05-13T14:51:39.955Z" },
     { url = "https://files.pythonhosted.org/packages/56/5e/83c450ec7b0bb40a7b74611c1b5440f9260e33c54c90d556fd4a1f0fd955/torch-2.12.0-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:a43ac605a5e13116c72b64c359644cce0229f213dde48d2ae0ae5eb5becf7feb", size = 426391871, upload-time = "2026-05-13T14:52:14.989Z" },
     { url = "https://files.pythonhosted.org/packages/c9/e9/1a0b575d98d0afedd8f157d23fa3d2759421483660448e60d0a4b10b6daa/torch-2.12.0-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:6a7512adfdd7f6732e40de1c620831e3c75b39b98cef60b11d0c5f0a76473ec5", size = 532192241, upload-time = "2026-05-13T14:51:07.795Z" },
+    { url = "https://files.pythonhosted.org/packages/88/21/afadd25ecd81b3cea1e11c73cf1ab41a983a50271548c3ec7ec3b9efc3e9/torch-2.12.0-cp314-cp314t-win_amd64.whl", hash = "sha256:5f96b63f8287f66a005dd1b5a6abba2920f11156c5e5c4d815f3e2050fd1aa16", size = 123231092, upload-time = "2026-05-13T14:51:18.854Z" },
 ]
 
 [[package]]
@@ -1925,23 +1993,31 @@ resolution-markers = [
     "platform_machine == 's390x' and sys_platform == 'darwin'",
 ]
 dependencies = [
-    { name = "filelock", marker = "(platform_machine == 's390x' and sys_platform == 'darwin') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "filelock", marker = "(platform_machine == 's390x' and sys_platform == 'darwin') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux') or (sys_platform == 'darwin' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform == 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "fsspec", marker = "(platform_machine == 's390x' and sys_platform == 'darwin') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "fsspec", marker = "(platform_machine == 's390x' and sys_platform == 'darwin') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux') or (sys_platform == 'darwin' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform == 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "jinja2", marker = "(platform_machine == 's390x' and sys_platform == 'darwin') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "jinja2", marker = "(platform_machine == 's390x' and sys_platform == 'darwin') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux') or (sys_platform == 'darwin' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform == 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "networkx", marker = "(platform_machine == 's390x' and sys_platform == 'darwin') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "networkx", marker = "(platform_machine == 's390x' and sys_platform == 'darwin') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux') or (sys_platform == 'darwin' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform == 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "setuptools", marker = "(platform_machine == 's390x' and sys_platform == 'darwin') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "setuptools", marker = "(platform_machine == 's390x' and sys_platform == 'darwin') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux') or (sys_platform == 'darwin' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform == 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "sympy", marker = "(platform_machine == 's390x' and sys_platform == 'darwin') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "sympy", marker = "(platform_machine == 's390x' and sys_platform == 'darwin') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux') or (sys_platform == 'darwin' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform == 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "typing-extensions", marker = "(platform_machine == 's390x' and sys_platform == 'darwin') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "typing-extensions", marker = "(platform_machine == 's390x' and sys_platform == 'darwin') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux') or (sys_platform == 'darwin' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform == 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 wheels = [
+    { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.12.0%2Bcpu-cp313-cp313-linux_s390x.whl", hash = "sha256:5e0da19e1c3bfdc9b92638c552579eac678354485d61fc8921b0461fd6c40449", upload-time = "2026-05-12T23:17:05Z" },
     { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.12.0%2Bcpu-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:68b7ddd4db4603a03e106e74c7098c8d8c8943d33c1e5ada009ca4cd885759c3", upload-time = "2026-05-12T23:17:12Z" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.12.0%2Bcpu-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:ada78018bdfa30d1c766596cd32d910dbf5b03424cd859231b6d2a00533de922", upload-time = "2026-05-12T23:17:20Z" },
     { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.12.0%2Bcpu-cp313-cp313-win_amd64.whl", hash = "sha256:59bc266826e683899d49ee0af9829f3eafd0a16e15b5db9dc591c8d955003b66", upload-time = "2026-05-12T23:17:27Z" },
     { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.12.0%2Bcpu-cp313-cp313-win_arm64.whl", hash = "sha256:97a5160abf3ca9d59a2cd7b4b4de89d9dfe290d36a1ac720262a55fbcee10b6c", upload-time = "2026-05-12T23:17:31Z" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.12.0%2Bcpu-cp313-cp313t-linux_s390x.whl", hash = "sha256:32b9b7a0974cd6149cb98def0a28a49d92d7c14a384273d5539da9624239e950", upload-time = "2026-05-12T23:17:36Z" },
     { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.12.0%2Bcpu-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:93ed8dc52c113580daf6124982b3232629045dccc5cd83a8f5ed478f7bac7340", upload-time = "2026-05-12T23:17:43Z" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.12.0%2Bcpu-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:6a1c86abd4ed15a0736cf2663ad69642ae5d1288c99e30346070e6241018a0a9", upload-time = "2026-05-12T23:17:54Z" },
     { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.12.0%2Bcpu-cp313-cp313t-win_amd64.whl", hash = "sha256:768dce4b7b3353795f667d1cb0dd7dfba06f570cd39539576097335e05bb71fe", upload-time = "2026-05-12T23:18:02Z" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.12.0%2Bcpu-cp314-cp314-linux_s390x.whl", hash = "sha256:ee1f329acfd0c2a1ccaa3393bcaf9857ea58759549bb2d67e271a6eab42382b3", upload-time = "2026-05-12T23:18:08Z" },
     { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.12.0%2Bcpu-cp314-cp314-manylinux_2_28_aarch64.whl", hash = "sha256:797c066367792c92eb97cafba7fd0caa8d7455e6078a4ee880630077378dc372", upload-time = "2026-05-12T23:18:15Z" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.12.0%2Bcpu-cp314-cp314-manylinux_2_28_x86_64.whl", hash = "sha256:a8f419ce3f25388d36e67153ec63b3a1b17059c49f5a7759a7e91ac4843660d3", upload-time = "2026-05-12T23:18:22Z" },
     { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.12.0%2Bcpu-cp314-cp314-win_amd64.whl", hash = "sha256:1dd196c43e74e7b3b526ff434e7efbdef3f3792a2efbecfc983d7dce501840d2", upload-time = "2026-05-12T23:18:30Z" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.12.0%2Bcpu-cp314-cp314t-linux_s390x.whl", hash = "sha256:d0d2080cb13c94ebc0c884d237e404490743d0f40192c8a180abf3b6b6f334cf", upload-time = "2026-05-12T23:18:35Z" },
     { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.12.0%2Bcpu-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:f7bc15972acad257723775237cdd120024cca844b8bc64701822fa596bcb7e14", upload-time = "2026-05-12T23:18:42Z" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.12.0%2Bcpu-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:4d79f961250d1763487ecbc90af019a80009f9e87cadc5366b3ec4ba5671fea6", upload-time = "2026-05-12T23:18:50Z" },
     { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.12.0%2Bcpu-cp314-cp314t-win_amd64.whl", hash = "sha256:46b8f4c41ac36bb5d5b47f5437b3de5541b313275e59c1d2aefd3bef32b0f531", upload-time = "2026-05-12T23:18:58Z" },
 ]
 
@@ -1953,26 +2029,34 @@ resolution-markers = [
     "platform_machine == 'x86_64' and sys_platform == 'linux'",
 ]
 dependencies = [
-    { name = "cuda-bindings", version = "12.9.7", source = { registry = "https://pypi.org/simple" }, marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "cuda-bindings", version = "12.9.7", source = { registry = "https://pypi.org/simple" }, marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "cuda-toolkit", version = "12.6.3", source = { registry = "https://pypi.org/simple" }, extra = ["cublas", "cudart", "cufft", "cufile", "cupti", "curand", "cusolver", "cusparse", "nvjitlink", "nvrtc", "nvtx"], marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "cuda-toolkit", version = "12.6.3", source = { registry = "https://pypi.org/simple" }, extra = ["cublas", "cudart", "cufft", "cufile", "cupti", "curand", "cusolver", "cusparse", "nvjitlink", "nvrtc", "nvtx"], marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "filelock", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "filelock", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "fsspec", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "fsspec", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "jinja2", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "jinja2", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "networkx", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "networkx", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "nvidia-cudnn-cu12", version = "9.10.2.21", source = { registry = "https://pypi.org/simple" }, marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cudnn-cu12", version = "9.10.2.21", source = { registry = "https://pypi.org/simple" }, marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "nvidia-cusparselt-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cusparselt-cu12", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "nvidia-nccl-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-nccl-cu12", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "nvidia-nvshmem-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-nvshmem-cu12", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "setuptools", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "setuptools", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "sympy", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "sympy", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "triton", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "triton", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "typing-extensions", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "typing-extensions", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 wheels = [
+    { url = "https://download-r2.pytorch.org/whl/cu126/torch-2.12.0%2Bcu126-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:3cf6676d41d8d57350d45d738b35cbed7671e36242a836993cd69b0c18819177", upload-time = "2026-05-12T23:30:41Z" },
     { url = "https://download-r2.pytorch.org/whl/cu126/torch-2.12.0%2Bcu126-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:8727a3901c34bf9825069aaf82f0984dd28ff622e1a727d2534555cd778fc5dc", upload-time = "2026-05-12T23:31:17Z" },
+    { url = "https://download-r2.pytorch.org/whl/cu126/torch-2.12.0%2Bcu126-cp313-cp313-win_amd64.whl", hash = "sha256:163a5020765016b11de7580e61d2d94e9595b8a8d0e5641c10b469fc34360e47", upload-time = "2026-05-12T23:32:53Z" },
+    { url = "https://download-r2.pytorch.org/whl/cu126/torch-2.12.0%2Bcu126-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:debd0815f6a2383c2a69cc2a40b4b3566ab339677f2a0cf8faff23daaa9ae03d", upload-time = "2026-05-12T23:34:19Z" },
     { url = "https://download-r2.pytorch.org/whl/cu126/torch-2.12.0%2Bcu126-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:1719b4ed6cbe5ff750e5636b2625bade85caeea937436d8b235f5e49e471875d", upload-time = "2026-05-12T23:34:46Z" },
+    { url = "https://download-r2.pytorch.org/whl/cu126/torch-2.12.0%2Bcu126-cp313-cp313t-win_amd64.whl", hash = "sha256:13558cc2c4432c96deab6e5c4a8b3367d98a3ae5ec15123607529ff2f0f12ed3", upload-time = "2026-05-12T23:36:14Z" },
+    { url = "https://download-r2.pytorch.org/whl/cu126/torch-2.12.0%2Bcu126-cp314-cp314-manylinux_2_28_aarch64.whl", hash = "sha256:e9be67e6c64b980cfd75f8cf09463d7aea84dd75cddd9a90c6b2363be221a6b5", upload-time = "2026-05-12T23:37:39Z" },
     { url = "https://download-r2.pytorch.org/whl/cu126/torch-2.12.0%2Bcu126-cp314-cp314-manylinux_2_28_x86_64.whl", hash = "sha256:149a376813baf61f4a6d1fa2b3dd046a41c98b91d7d2c22a0989984642373f73", upload-time = "2026-05-12T23:38:07Z" },
+    { url = "https://download-r2.pytorch.org/whl/cu126/torch-2.12.0%2Bcu126-cp314-cp314-win_amd64.whl", hash = "sha256:4b05a1e104739100179ffb0d94daf17f1808b2f71cd895841729ccf06460b0d3", upload-time = "2026-05-12T23:39:31Z" },
+    { url = "https://download-r2.pytorch.org/whl/cu126/torch-2.12.0%2Bcu126-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:16f9187e12efffae37983c2edd7560cf7b1828bae84a30a3fd6733b3adcbdc6b", upload-time = "2026-05-12T23:40:51Z" },
     { url = "https://download-r2.pytorch.org/whl/cu126/torch-2.12.0%2Bcu126-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:6c1535d135828f839da6478bdfa94bcb4cf1dbd1bad06ca3d8ca07c94451348f", upload-time = "2026-05-12T23:41:20Z" },
+    { url = "https://download-r2.pytorch.org/whl/cu126/torch-2.12.0%2Bcu126-cp314-cp314t-win_amd64.whl", hash = "sha256:ec030dd30287eda9338ee401dcca722758862337bd0cdb904325b8eeba5c2694", upload-time = "2026-05-12T23:42:43Z" },
 ]
 
 [[package]]
@@ -1983,9 +2067,9 @@ resolution-markers = [
     "platform_machine != 's390x' and sys_platform == 'darwin'",
 ]
 dependencies = [
-    { name = "numpy", marker = "platform_machine != 's390x' and sys_platform == 'darwin'" },
+    { name = "numpy", marker = "(platform_machine != 's390x' and sys_platform == 'darwin') or (platform_machine == 's390x' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'darwin' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "pillow", marker = "platform_machine != 's390x' and sys_platform == 'darwin'" },
+    { name = "pillow", marker = "(platform_machine != 's390x' and sys_platform == 'darwin') or (platform_machine == 's390x' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'darwin' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "torch", version = "2.12.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "platform_machine != 's390x' and sys_platform == 'darwin'" },
+    { name = "torch", version = "2.12.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine != 's390x' and sys_platform == 'darwin') or (platform_machine == 's390x' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'darwin' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 wheels = [
     { url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.27.0-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:41d6dae73e1af09fa82ded597ae57f2a2314285acde54b25890a8f8e51b999d7", upload-time = "2026-05-12T16:20:37Z" },
@@ -2003,19 +2087,27 @@ resolution-markers = [
     "platform_machine == 's390x' and sys_platform == 'linux'",
 ]
 dependencies = [
-    { name = "numpy", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "numpy", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "pillow", marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "pillow", marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "torch", version = "2.12.0", source = { registry = "https://pypi.org/simple" }, marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "torch", version = "2.12.0", source = { registry = "https://pypi.org/simple" }, marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 wheels = [
+    { url = "https://files.pythonhosted.org/packages/d8/ae/36547812e6e047c1d80bcacd1b17a340612b08a6e876e0aabf3d0b9228b0/torchvision-0.27.0-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:41d6dae73e1af09fa82ded597ae57f2a2314285acde54b25890a8f8e51b999d7", size = 1758826, upload-time = "2026-05-13T14:57:05.262Z" },
     { url = "https://files.pythonhosted.org/packages/ae/30/32c4ea842738728a14e3df8c576c62dedcf5ae5cb6a5c984c6429ebe7524/torchvision-0.27.0-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:70f071c6f74b60d5fe8851636d8d4cd5f4fa29d57fd9348a87a6f17b990b95ba", size = 7789501, upload-time = "2026-05-13T14:56:57.786Z" },
     { url = "https://files.pythonhosted.org/packages/f6/24/4d0d48684251bd0673f87d633d5d88ab00227983b00591156eed2f86c8d5/torchvision-0.27.0-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:aaafa6962c9d91f42503de1957d6fa349907d028c06f335bd95da7a5bc57147d", size = 7579868, upload-time = "2026-05-13T14:56:41.618Z" },
+    { url = "https://files.pythonhosted.org/packages/ba/da/e6edd051d2ba25adf23b120fa97f458dff888d098c51e84724f17d2d1470/torchvision-0.27.0-cp313-cp313-win_amd64.whl", hash = "sha256:aee384a2782c89517c4ab9061d2720ba59fd2ffe5ef89d0a149cc2d43abdf521", size = 4092700, upload-time = "2026-05-13T14:57:09.729Z" },
+    { url = "https://files.pythonhosted.org/packages/fa/23/95dfa40431360f42ca949bf861434bed51164adfa8fb9801e05bf3194f50/torchvision-0.27.0-cp313-cp313t-macosx_14_0_arm64.whl", hash = "sha256:c5121f1b9ab09a7f73e837871deb8321551f7eaeb19d87aa00de9191968eae44", size = 1845008, upload-time = "2026-05-13T14:57:03.768Z" },
     { url = "https://files.pythonhosted.org/packages/23/b9/9dbdf76b2b49a75ba8088df6f7c755bdb520afb6c6dbac0102b46cde5e99/torchvision-0.27.0-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:1c01f0d1091ae22b9dfc082b0a0fe5faaf053686a29b4fb082ba7691375c73cf", size = 7791430, upload-time = "2026-05-13T14:56:56.206Z" },
     { url = "https://files.pythonhosted.org/packages/5c/6a/e4a16cf2f3310c2ea7760dc5d9054496844391e0f4c1fae87fefac2f3d9e/torchvision-0.27.0-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:dadea3c5ecfd05bbb2a3312ab0374f213c58bf6459cb059122e2f4dfe13d10ed", size = 7668441, upload-time = "2026-05-13T14:57:02.127Z" },
+    { url = "https://files.pythonhosted.org/packages/00/70/01b6461117a6a94b5af3f8ee166bb0f045056f3cf187750c110dabfdfffa/torchvision-0.27.0-cp313-cp313t-win_amd64.whl", hash = "sha256:a49e55055a39a8506fe7e59850522cab004efb2c3839f6057658889c1d69c815", size = 4141602, upload-time = "2026-05-13T14:56:53.449Z" },
+    { url = "https://files.pythonhosted.org/packages/92/22/c0633677b3b3f3e69554a21ac087bf705f829c40cd5e3783507b8c006681/torchvision-0.27.0-cp314-cp314-macosx_14_0_arm64.whl", hash = "sha256:c1fac0fc2a7adf29481fc1938a0e7845c57ba1147a986784109c4d98f434ea8c", size = 1758818, upload-time = "2026-05-13T14:56:54.988Z" },
     { url = "https://files.pythonhosted.org/packages/48/e8/55f9d9667b56dae470e69e31beac9b00d458ea393feec1aae95cc4f3f1c9/torchvision-0.27.0-cp314-cp314-manylinux_2_28_aarch64.whl", hash = "sha256:cbf89764fc76f3f17fbf80c12d5a89c691e91cb9d82c38412aaf0568655ffb19", size = 7789667, upload-time = "2026-05-13T14:56:48.858Z" },
     { url = "https://files.pythonhosted.org/packages/00/bc/6f8681daf3bbc4c315bb0005110f99d28e3ecd675bf9c8f2c0d393fbac7a/torchvision-0.27.0-cp314-cp314-manylinux_2_28_x86_64.whl", hash = "sha256:91f61b9865423037c327eb56afa207cc72de874e458c361840db9dcf5ce0c0eb", size = 7579848, upload-time = "2026-05-13T14:56:38.209Z" },
+    { url = "https://files.pythonhosted.org/packages/19/6c/8d8020e6bd1e46c53e487c9c4e9457a07f2ee28931028fb5d71e2da40adc/torchvision-0.27.0-cp314-cp314-win_amd64.whl", hash = "sha256:5bb82fc3c55daf1788621e504310b0a286f1069627a8742f692aebb075ef25a7", size = 4119284, upload-time = "2026-05-13T14:56:46.625Z" },
+    { url = "https://files.pythonhosted.org/packages/8d/7e/e78c48662a8d551606efdbe11c6b9c1d6d2391b92cd0e4591b9e6a2412b8/torchvision-0.27.0-cp314-cp314t-macosx_14_0_arm64.whl", hash = "sha256:2c4099a15150143b9b034730b404a56d572efe0b79489b4c765d929cb4eac7f3", size = 1758828, upload-time = "2026-05-13T14:56:52.293Z" },
     { url = "https://files.pythonhosted.org/packages/21/dd/d03ee9f9ee7bf11a8c7c776fb8e7fd6102f59c013791a2a4e5175bd6cba7/torchvision-0.27.0-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:b4c6bb0a670dcba017b3643e21902c9b8a1cc1c127d602f1488fa29ec3c6e865", size = 7790618, upload-time = "2026-05-13T14:56:44.721Z" },
     { url = "https://files.pythonhosted.org/packages/39/08/4002336a74742be70728603ec1769feb2b55e0d19c532c9ec9f92008de76/torchvision-0.27.0-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:1c2db4bde82bc48ebff73436a6adf34d4f809448268a70d9a1285f5c8f92313d", size = 7580217, upload-time = "2026-05-13T14:56:43.274Z" },
+    { url = "https://files.pythonhosted.org/packages/ed/cb/4dd4783eb3565f526ba6e64b6f6ca26c00eacc924cdfe60455db9d91b84b/torchvision-0.27.0-cp314-cp314t-win_amd64.whl", hash = "sha256:72bf547e58ddb948689734eed6f4b6a2031f979dba4fb08e3690688b392e929f", size = 4226392, upload-time = "2026-05-13T14:56:40.235Z" },
 ]
 
 [[package]]
@@ -2031,18 +2123,22 @@ resolution-markers = [
     "platform_machine == 's390x' and sys_platform == 'darwin'",
 ]
 dependencies = [
-    { name = "numpy", marker = "(platform_machine == 's390x' and sys_platform == 'darwin') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "numpy", marker = "(platform_machine == 's390x' and sys_platform == 'darwin') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux') or (sys_platform == 'darwin' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform == 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "pillow", marker = "(platform_machine == 's390x' and sys_platform == 'darwin') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "pillow", marker = "(platform_machine == 's390x' and sys_platform == 'darwin') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux') or (sys_platform == 'darwin' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform == 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "torch", version = "2.12.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine == 's390x' and sys_platform == 'darwin') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "torch", version = "2.12.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine == 's390x' and sys_platform == 'darwin') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux') or (sys_platform == 'darwin' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform == 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 wheels = [
     { url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.27.0%2Bcpu-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:69093b64b2762c43df17be2db2be163029963d90bc3f1801500fdeb723e54833", upload-time = "2026-05-12T16:20:36Z" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.27.0%2Bcpu-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:ba77816bbde883c0c2075a1e284cf2e6f324472d4523442f5e3ae0812a98ae1e", upload-time = "2026-05-12T16:20:36Z" },
     { url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.27.0%2Bcpu-cp313-cp313-win_amd64.whl", hash = "sha256:159c7d32de5256ed946b4188335b00d11e0c3f7838998f94eaa98384b0249600", upload-time = "2026-05-12T16:20:36Z" },
     { url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.27.0%2Bcpu-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:1777906f08c75be6daf9a11946894b63ef368951e7aa52da83f8bfc824856123", upload-time = "2026-05-12T16:20:36Z" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.27.0%2Bcpu-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:4388677d0903db4892587d5c87ab6f6cb31d19bac4838e083db022682036e152", upload-time = "2026-05-12T16:20:36Z" },
     { url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.27.0%2Bcpu-cp313-cp313t-win_amd64.whl", hash = "sha256:1d38651bd624dbbaf5ad77ccac93a60b16fc81f1ccacf2f5268bbc0dd2e7e1d7", upload-time = "2026-05-12T16:20:37Z" },
     { url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.27.0%2Bcpu-cp314-cp314-manylinux_2_28_aarch64.whl", hash = "sha256:c7e3c5662278ab5d64d150cc17694060e9ce5875b8739094dadf07a4ba45b90e", upload-time = "2026-05-12T16:20:37Z" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.27.0%2Bcpu-cp314-cp314-manylinux_2_28_x86_64.whl", hash = "sha256:1417b91354698b045a4127cf7108b1dc8af1351a3002ecc5661c3ca69df577d4", upload-time = "2026-05-12T16:20:37Z" },
     { url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.27.0%2Bcpu-cp314-cp314-win_amd64.whl", hash = "sha256:58759994610e69773b1d7b038dfb2c72e8bf237fb3ba765f2ab1d6af7835dd88", upload-time = "2026-05-12T16:20:37Z" },
     { url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.27.0%2Bcpu-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:4d2effc9740e711ea9b2db99e8874977eb6a3baa8b830b8a7416b2fde416de64", upload-time = "2026-05-12T16:20:37Z" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.27.0%2Bcpu-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:ae89bf1a81f3c7fdd222fbbddd8135a054d24ddd13f3b410e4f96d75f72952df", upload-time = "2026-05-12T16:20:37Z" },
     { url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.27.0%2Bcpu-cp314-cp314t-win_amd64.whl", hash = "sha256:c8b3c995d4294551b5ab33cbcf60d700819dc23d53b21a9c74936e521c88de33", upload-time = "2026-05-12T16:20:37Z" },
 ]
 
@@ -2054,15 +2150,23 @@ resolution-markers = [
     "platform_machine == 'x86_64' and sys_platform == 'linux'",
 ]
 dependencies = [
-    { name = "numpy", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "numpy", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "pillow", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "pillow", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "torch", version = "2.12.0+cu126", source = { registry = "https://download.pytorch.org/whl/cu126" }, marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "torch", version = "2.12.0+cu126", source = { registry = "https://download.pytorch.org/whl/cu126" }, marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 wheels = [
+    { url = "https://download-r2.pytorch.org/whl/cu126/torchvision-0.27.0%2Bcu126-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:313c8fbc1fa7b0e5192752601e91c3c9987f6f5ee1342691b465e0c33653a307", upload-time = "2026-05-12T16:20:42Z" },
     { url = "https://download-r2.pytorch.org/whl/cu126/torchvision-0.27.0%2Bcu126-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:56477bd091009afc733931724d66c56b21c9fa14ba2c3a1ec24c8ddce86b5cd8", upload-time = "2026-05-12T16:20:42Z" },
+    { url = "https://download-r2.pytorch.org/whl/cu126/torchvision-0.27.0%2Bcu126-cp313-cp313-win_amd64.whl", hash = "sha256:b92a80f74b638f6e8c29b1319eb69701ceea98c0ac3c166ac8ef3f45a0493400", upload-time = "2026-05-13T02:00:39Z" },
+    { url = "https://download-r2.pytorch.org/whl/cu126/torchvision-0.27.0%2Bcu126-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:af5367582f4189ec76b3ec0ef9b3503a55b03e57e05cdea62d44e12cacbf4b8a", upload-time = "2026-05-12T16:20:42Z" },
     { url = "https://download-r2.pytorch.org/whl/cu126/torchvision-0.27.0%2Bcu126-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:836e7bb5c54238cb810bc263529f63b4b6ed8d183d5c764d5368902fb1acab19", upload-time = "2026-05-12T16:20:42Z" },
+    { url = "https://download-r2.pytorch.org/whl/cu126/torchvision-0.27.0%2Bcu126-cp313-cp313t-win_amd64.whl", hash = "sha256:3335086359b4e210ebd6240cb383c63ad265345cb8f8041bf0fe876822a6ab4d", upload-time = "2026-05-13T02:00:40Z" },
+    { url = "https://download-r2.pytorch.org/whl/cu126/torchvision-0.27.0%2Bcu126-cp314-cp314-manylinux_2_28_aarch64.whl", hash = "sha256:0c12e5fdfb355eb1f20b3fca4235a427d568c7ff4fbca6208f5891f7400670c3", upload-time = "2026-05-12T16:20:42Z" },
     { url = "https://download-r2.pytorch.org/whl/cu126/torchvision-0.27.0%2Bcu126-cp314-cp314-manylinux_2_28_x86_64.whl", hash = "sha256:efa01b2bdb8982bb3ff72669d70ab1d608919bb082464a4134f4063834ed771f", upload-time = "2026-05-12T16:20:42Z" },
+    { url = "https://download-r2.pytorch.org/whl/cu126/torchvision-0.27.0%2Bcu126-cp314-cp314-win_amd64.whl", hash = "sha256:2d6e4300e5824d9711929fbda4edf57731d05808ae1706e44b477ade7aca9300", upload-time = "2026-05-13T02:00:41Z" },
+    { url = "https://download-r2.pytorch.org/whl/cu126/torchvision-0.27.0%2Bcu126-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:f095b22a16ef385855cd1117ac5aca45fd3eae7be6e79d79a594492b71728284", upload-time = "2026-05-12T16:20:42Z" },
     { url = "https://download-r2.pytorch.org/whl/cu126/torchvision-0.27.0%2Bcu126-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:60e070ef008c2e74724d2bf3949c7ec2a0fc25e34bafe1cee1d83b4e2782874c", upload-time = "2026-05-12T16:20:42Z" },
+    { url = "https://download-r2.pytorch.org/whl/cu126/torchvision-0.27.0%2Bcu126-cp314-cp314t-win_amd64.whl", hash = "sha256:9db7a154702b4404f1af0b48ac0098aa9ddcea3c80c8e9b8bf8f3fdd87e20946", upload-time = "2026-05-13T02:00:42Z" },
 ]
 
 [[package]]
@@ -2070,7 +2174,7 @@ name = "tqdm"
 version = "4.68.2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "colorama", marker = "sys_platform == 'win32'" },
+    { name = "colorama", marker = "sys_platform == 'win32' or (extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/85/05/0d5260f1f1ca784f4a4a0def9cbe6affe587f5b4025328d446c3d67765f4/tqdm-4.68.2.tar.gz", hash = "sha256:89c230e8dbc67c7615c142487111222f878c77427ea09549960f62389e258add", size = 171923, upload-time = "2026-06-09T13:26:42.539Z" }
 wheels = [
@@ -2151,14 +2255,14 @@ dependencies = [
     { name = "pyyaml" },
     { name = "requests" },
     { name = "scipy" },
-    { name = "torch", version = "2.12.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "platform_machine != 's390x' and sys_platform == 'darwin'" },
+    { name = "torch", version = "2.12.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine != 's390x' and sys_platform == 'darwin') or (platform_machine == 's390x' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'darwin' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "torch", version = "2.12.0", source = { registry = "https://pypi.org/simple" }, marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "torch", version = "2.12.0", source = { registry = "https://pypi.org/simple" }, marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "torch", version = "2.12.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine == 's390x' and sys_platform == 'darwin') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "torch", version = "2.12.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine == 's390x' and sys_platform == 'darwin') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux') or (sys_platform == 'darwin' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform == 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "torch", version = "2.12.0+cu126", source = { registry = "https://download.pytorch.org/whl/cu126" }, marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "torch", version = "2.12.0+cu126", source = { registry = "https://download.pytorch.org/whl/cu126" }, marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "torchvision", version = "0.27.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "platform_machine != 's390x' and sys_platform == 'darwin'" },
+    { name = "torchvision", version = "0.27.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine != 's390x' and sys_platform == 'darwin') or (platform_machine == 's390x' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'darwin' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "torchvision", version = "0.27.0", source = { registry = "https://pypi.org/simple" }, marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "torchvision", version = "0.27.0", source = { registry = "https://pypi.org/simple" }, marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "torchvision", version = "0.27.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine == 's390x' and sys_platform == 'darwin') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "torchvision", version = "0.27.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine == 's390x' and sys_platform == 'darwin') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux') or (sys_platform == 'darwin' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform == 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "torchvision", version = "0.27.0+cu126", source = { registry = "https://download.pytorch.org/whl/cu126" }, marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "torchvision", version = "0.27.0+cu126", source = { registry = "https://download.pytorch.org/whl/cu126" }, marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
     { name = "ultralytics-thop" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/5b/d6/7d95601a9078b614e87d14f93bf597a6bd75aa2bfe19cbe57e0016005c35/ultralytics-8.4.66.tar.gz", hash = "sha256:bb6e70e6b6de5399f9fc29a7c57495d6272529cc4896faf548372ddfa1c3365f", size = 1104120, upload-time = "2026-06-11T16:48:03.3Z" }
@@ -2172,10 +2276,10 @@ version = "2.0.20"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "numpy" },
-    { name = "torch", version = "2.12.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "platform_machine != 's390x' and sys_platform == 'darwin'" },
+    { name = "torch", version = "2.12.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine != 's390x' and sys_platform == 'darwin') or (platform_machine == 's390x' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'darwin' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "torch", version = "2.12.0", source = { registry = "https://pypi.org/simple" }, marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "torch", version = "2.12.0", source = { registry = "https://pypi.org/simple" }, marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "torch", version = "2.12.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine == 's390x' and sys_platform == 'darwin') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "torch", version = "2.12.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine == 's390x' and sys_platform == 'darwin') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux') or (sys_platform == 'darwin' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform == 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "torch", version = "2.12.0+cu126", source = { registry = "https://download.pytorch.org/whl/cu126" }, marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "torch", version = "2.12.0+cu126", source = { registry = "https://download.pytorch.org/whl/cu126" }, marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/98/c6/d25cb53e141242f74950744179c21b8798bb09b9e7161465ecda4f577ddf/ultralytics_thop-2.0.20.tar.gz", hash = "sha256:f3595e0d8c6fd0b9f62fc2cd9be921755e2649a05c34f1fabaea0bff7295d641", size = 34682, upload-time = "2026-06-06T11:42:42.184Z" }
 wheels = [
@@ -2193,28 +2297,29 @@ wheels = [
 
 [[package]]
 name = "winnow"
-version = "0.2.5"
+version = "0.2.11"
 source = { editable = "." }
 dependencies = [
     { name = "croniter" },
     { name = "insightface" },
     { name = "numpy" },
-    { name = "nvidia-cudnn-cu12", version = "9.10.2.21", source = { registry = "https://pypi.org/simple" }, marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cudnn-cu12", version = "9.10.2.21", source = { registry = "https://pypi.org/simple" }, marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "nvidia-cudnn-cu12", version = "9.23.1.3", source = { registry = "https://pypi.org/simple" }, marker = "platform_machine != 'x86_64' or sys_platform != 'linux'" },
+    { name = "nvidia-cudnn-cu12", version = "9.23.1.3", source = { registry = "https://pypi.org/simple" }, marker = "platform_machine != 'x86_64' or sys_platform != 'linux' or (extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "onnxruntime-gpu" },
+    { name = "onnxruntime", marker = "platform_machine != 'x86_64' or sys_platform != 'linux' or (extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
+    { name = "onnxruntime-gpu", marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
     { name = "opencv-python-headless" },
     { name = "pillow" },
     { name = "python-dotenv" },
     { name = "requests" },
     { name = "rich" },
-    { name = "torch", version = "2.12.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "platform_machine != 's390x' and sys_platform == 'darwin'" },
+    { name = "torch", version = "2.12.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine != 's390x' and sys_platform == 'darwin') or (platform_machine == 's390x' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'darwin' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "torch", version = "2.12.0", source = { registry = "https://pypi.org/simple" }, marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "torch", version = "2.12.0", source = { registry = "https://pypi.org/simple" }, marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "torch", version = "2.12.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine == 's390x' and sys_platform == 'darwin') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "torch", version = "2.12.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine == 's390x' and sys_platform == 'darwin') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux') or (sys_platform == 'darwin' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform == 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "torch", version = "2.12.0+cu126", source = { registry = "https://download.pytorch.org/whl/cu126" }, marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "torch", version = "2.12.0+cu126", source = { registry = "https://download.pytorch.org/whl/cu126" }, marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "torchvision", version = "0.27.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "platform_machine != 's390x' and sys_platform == 'darwin'" },
+    { name = "torchvision", version = "0.27.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine != 's390x' and sys_platform == 'darwin') or (platform_machine == 's390x' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'darwin' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "torchvision", version = "0.27.0", source = { registry = "https://pypi.org/simple" }, marker = "platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux'" },
+    { name = "torchvision", version = "0.27.0", source = { registry = "https://pypi.org/simple" }, marker = "(platform_machine != 'aarch64' and platform_machine != 'x86_64' and sys_platform == 'linux') or (platform_machine == 'aarch64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (platform_machine == 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "torchvision", version = "0.27.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine == 's390x' and sys_platform == 'darwin') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "torchvision", version = "0.27.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine == 's390x' and sys_platform == 'darwin') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux') or (sys_platform == 'darwin' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform == 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
-    { name = "torchvision", version = "0.27.0+cu126", source = { registry = "https://download.pytorch.org/whl/cu126" }, marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "torchvision", version = "0.27.0+cu126", source = { registry = "https://download.pytorch.org/whl/cu126" }, marker = "(platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine != 'x86_64' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu') or (sys_platform != 'linux' and extra == 'project-11-onnxruntime' and extra == 'project-15-onnxruntime-gpu')" },
     { name = "transformers" },
     { name = "ultralytics" },
 ]
@@ -2231,7 +2336,9 @@ requires-dist = [
     { name = "insightface", specifier = ">=0.7.3" },
     { name = "numpy", specifier = ">=2.2.6" },
     { name = "nvidia-cudnn-cu12", specifier = ">=9.0.0" },
-    { name = "onnxruntime-gpu", specifier = ">=1.23.2" },
+    { name = "onnxruntime", marker = "sys_platform != 'linux'", specifier = ">=1.23.2" },
+    { name = "onnxruntime", marker = "platform_machine != 'x86_64' and sys_platform == 'linux'", specifier = ">=1.23.2" },
+    { name = "onnxruntime-gpu", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'", specifier = ">=1.23.2" },
     { name = "opencv-python-headless", specifier = ">=4.12.0.88" },
     { name = "pillow", specifier = ">=12.1.0" },
     { name = "python-dotenv", specifier = ">=1.2.1" },

winnow/__init__.py

@@ -5,4 +5,9 @@ Immich library for Frigate's Face Recognition (ArcFace) and Object/State
 Classification models.
 """
 
-__version__ = "0.1.0"
+from importlib.metadata import PackageNotFoundError, version
+
+try:
+    __version__ = version("winnow")
+except PackageNotFoundError:
+    __version__ = "unknown"

winnow/cli.py

@@ -2,6 +2,7 @@
 
 import logging
 import os
+import sys
 
 from rich import print as rprint
 from rich.prompt import Confirm
@@ -10,7 +11,7 @@ from .config import Config, ConfigManager
 from .executor import execute_jobs, upload_to_frigate
 from .immich_api import get_people
 from .jobs import _show_preview, auto_configure, interactive_configure
-from .logging import console, setup_logging
+from .log_config import console, setup_logging
 from .upload_tracker import get_person_summary, reset_person
 
 logger = logging.getLogger(__name__)
@@ -19,7 +20,8 @@ logger = logging.getLogger(__name__)
 def main() -> None:
     """Entry point for winnow CLI."""
     try:
-        setup_logging(verbose=False)
+        verbose = os.environ.get("VERBOSE", "").lower() in ("true", "1", "yes")
+        setup_logging(verbose=verbose)
 
         console.print(r"""
     [bold blue]winnow[/bold blue]
@@ -63,17 +65,18 @@ def main() -> None:
             rprint("[bold red]Could not fetch people from Immich. Check URL/Key.[/bold red]")
             return
 
-        # Check for non-interactive mode
+        # Auto mode when no TTY (Docker, cron, pipes) — the primary use case.
-        auto_mode = os.environ.get("AUTO_MODE", "false").lower() == "true"
+        # A TTY means local interactive use; AUTO_MODE=true overrides that for scripting.
+        auto_mode = not sys.stdin.isatty() or os.environ.get("AUTO_MODE", "").lower() in ("true", "1", "yes")
         dry_run = os.environ.get("DRY_RUN", "false").lower() in ("true", "1", "yes")
 
         if dry_run:
             rprint("[bold yellow]DRY RUN — no images will be downloaded or uploaded[/bold yellow]")
 
         if auto_mode:
-            rprint("[bold cyan]Running in AUTO mode (non-interactive)[/bold cyan]")
             jobs = auto_configure(people)
         else:
+            rprint("[bold cyan]Interactive mode — set AUTO_MODE=true to skip prompts[/bold cyan]")
             jobs = interactive_configure(people)
 
         if jobs:

winnow/config.py

@@ -39,8 +39,7 @@ class _Config:
     USE_FULL_RESOLUTION: bool = True
     ENABLE_FACE_ALIGNMENT: bool = True
 
-    # Caching (opt-in to avoid unexpected files)
+    ENABLE_CACHE: bool = True
-    ENABLE_CACHE: bool = False
     CACHE_DIR: str = ".if_cache"
 
     def __new__(cls) -> "_Config":
@@ -64,7 +63,7 @@ class _Config:
         self.FACE_MARGIN = float(os.getenv("FACE_MARGIN", "0.15"))
         self.USE_FULL_RESOLUTION = os.getenv("USE_FULL_RESOLUTION", "true").lower() in ("true", "1", "yes")
         self.ENABLE_FACE_ALIGNMENT = os.getenv("ENABLE_FACE_ALIGNMENT", "true").lower() in ("true", "1", "yes")
-        self.ENABLE_CACHE = os.getenv("ENABLE_CACHE", "false").lower() in ("true", "1", "yes")
+        self.ENABLE_CACHE = os.getenv("ENABLE_CACHE", "true").lower() in ("true", "1", "yes")
         self.CACHE_DIR = os.getenv("CACHE_DIR", ".if_cache")
 
         # Fall back to config file for non-sensitive values (API_KEY not stored here)
@@ -161,7 +160,12 @@ class _ConfigAccessor:
 
 
 Config = _ConfigAccessor()
-ConfigManager = type("ConfigManager", (), {"get": staticmethod(lambda: _Config())})
+
+
+class ConfigManager:
+    @staticmethod
+    def get() -> _Config:
+        return _Config()
 
 
 def get_headers() -> dict[str, str]:

winnow/diversity.py

@@ -29,6 +29,7 @@ def select_diverse_assets(
     entity_name: str,
     selection_mode: str = "smart",
     entity_type: str = "face",
+    person_id: str | None = None,
     progress_callback=None,
 ) -> list:
     """
@@ -59,7 +60,7 @@ def select_diverse_assets(
         return _select_time_spread(assets, limit)
 
     try:
-        return _select_by_embedding(assets, limit, entity_type, progress_callback)
+        return _select_by_embedding(assets, limit, entity_type, person_id, progress_callback)
     except Exception as e:
         logger.error(f"Smart Diversity failed: {e}. Falling back to time spread.")
         return _select_time_spread(assets, limit)
@@ -80,9 +81,11 @@ def _fetch_thumbnail(asset_id: str, timeout: int = 10) -> Image.Image | None:
         return None
 
 
-def _get_face_bbox(asset: dict) -> tuple[float, float, float, float] | None:
+def _get_face_bbox(asset: dict, person_id: str | None = None) -> tuple[float, float, float, float] | None:
-    """Extract face bounding box from asset metadata if available."""
+    """Extract face bounding box from asset metadata for the given person."""
     for person in asset.get("people", []):
+        if person_id and person.get("id") != person_id:
+            continue
         faces = person.get("faces", [])
         if faces:
             f = faces[0]
@@ -95,12 +98,16 @@ def _get_face_bbox(asset: dict) -> tuple[float, float, float, float] | None:
     return None
 
 
-def _get_face_confidence(asset: dict) -> float | None:
+def _get_face_confidence(asset: dict, person_id: str | None = None) -> float | None:
-    """Extract face detection confidence from asset metadata if available."""
+    """Extract face detection confidence from asset metadata for the given person."""
     for person in asset.get("people", []):
+        if person_id and person.get("id") != person_id:
+            continue
         faces = person.get("faces", [])
         if faces:
-            return faces[0].get("score") or faces[0].get("confidence")
+            f = faces[0]
+            score = f.get("score")
+            return score if score is not None else f.get("confidence")
     return None
 
 
@@ -108,6 +115,7 @@ def _crop_face_from_thumbnail(
     img: Image.Image,
     asset: dict,
     margin: float = 0.25,
+    person_id: str | None = None,
 ) -> Image.Image | None:
     """Crop the face region from a thumbnail using Immich bbox metadata.
 
@@ -118,19 +126,22 @@ def _crop_face_from_thumbnail(
         img: Full preview thumbnail
         asset: Asset dict with people/faces metadata
         margin: Extra margin around the bbox (fraction, default 25%)
+        person_id: If provided, only crop from this person's face data.
 
     Returns:
         Cropped face PIL image, or None if no face metadata available
     """
-    bbox = _get_face_bbox(asset)
+    bbox = _get_face_bbox(asset, person_id=person_id)
     if bbox is None:
         return None
 
     x1, y1, x2, y2 = bbox
     img_w, img_h = img.size
 
-    # Get metadata dimensions to scale bbox
+    # Get metadata dimensions to scale bbox — must match the same person as _get_face_bbox
     for person in asset.get("people", []):
+        if person_id and person.get("id") != person_id:
+            continue
         faces = person.get("faces", [])
         if faces:
             meta_w = faces[0].get("imageWidth") or img_w
@@ -169,6 +180,7 @@ def _select_by_embedding(
     assets: list,
     limit: int | str,
     entity_type: str,
+    person_id: str | None = None,
     progress_callback=None,
 ) -> list:
     """Select assets using embedding-based cluster-aware FPS.
@@ -191,37 +203,48 @@ def _select_by_embedding(
     else:
         candidates = assets
 
-    # --- Phase 1: Concurrent thumbnail download ---
+    # --- Phases 1-4: Batched download → quality filter → crop → embed ---
+    # Process in bounded batches so at most _BATCH decoded images live in RAM
+    # at once. With 472 candidates each thumbnail is ~3-8 MB decoded; loading
+    # all at once easily exhausts a 4 GB container limit on CPU.
     from concurrent.futures import ThreadPoolExecutor, as_completed
 
-    thumbnail_map: dict[str, Image.Image] = {}
+    _BATCH = 32
-    with ThreadPoolExecutor(max_workers=8) as pool:
+    embeddings, valid_candidates, confidence_scores = [], [], []
-        futures = {pool.submit(_fetch_thumbnail, a["id"]): a for a in candidates}
+    quality_filtered = 0
-        for i, future in enumerate(as_completed(futures)):
+    processed = 0
-            if progress_callback:
+
-                progress_callback(i, len(candidates))
+    for batch_start in range(0, len(candidates), _BATCH):
+        batch = candidates[batch_start : batch_start + _BATCH]
+
+        # Download this batch concurrently
+        batch_images: dict[str, Image.Image] = {}
+        with ThreadPoolExecutor(max_workers=min(8, len(batch))) as pool:
+            futures = {pool.submit(_fetch_thumbnail, a["id"]): a for a in batch}
+            for future in as_completed(futures):
                 asset = futures[future]
                 try:
                     img = future.result()
                     if img is not None:
-                    thumbnail_map[asset["id"]] = img
+                        batch_images[asset["id"]] = img
-            except Exception:
+                except Exception as e:
+                    logger.debug(f"Failed to fetch thumbnail for {asset['id']}: {e}")
                     continue
 
-    # --- Phase 2-4: Quality filter → Crop → Embed ---
+        # Process each image; batch_images goes out of scope after this loop,
-    embeddings, valid_candidates, confidence_scores = [], [], []
+        # bounding peak thumbnail memory to _BATCH images per iteration.
-    quality_filtered = 0
+        for asset in batch:
-
+            img = batch_images.get(asset["id"])
-    for asset in candidates:
+            processed += 1
-        img = thumbnail_map.get(asset["id"])
+            if progress_callback:
+                progress_callback(processed, len(candidates))
             if img is None:
                 continue
 
-        confidence = _get_face_confidence(asset)
+            confidence = _get_face_confidence(asset, person_id=person_id)
 
-        # Quality gate: filter before expensive embedding computation
             if entity_type == "face":
-            face_bbox = _get_face_bbox(asset)
+                face_bbox = _get_face_bbox(asset, person_id=person_id)
                 quality = assess_quality(
                     img,
                     face_bbox=face_bbox,
@@ -235,8 +258,7 @@ def _select_by_embedding(
                     logger.debug(f"Quality filtered {asset['id']}: {quality.reason}")
                     continue
 
-            # Crop the target person's face before embedding
+                face_crop = _crop_face_from_thumbnail(img, asset, person_id=person_id)
-            face_crop = _crop_face_from_thumbnail(img, asset)
                 embed_img = face_crop if face_crop is not None else img
             else:
                 embed_img = img
@@ -247,9 +269,6 @@ def _select_by_embedding(
                 valid_candidates.append(asset)
                 confidence_scores.append(confidence)
 
-    if progress_callback:
-        progress_callback(len(candidates), len(candidates))
-
     if quality_filtered > 0:
         logger.info(f"Quality filtering removed {quality_filtered} images.")
 
@@ -360,7 +379,7 @@ def _compute_adaptive_threshold(emb_normed: np.ndarray, entity_type: str) -> flo
     fraction = 0.20 if entity_type == "face" else 0.10
     threshold = max(0.05, median_dist * fraction)
 
-    logger.info(
+    logger.debug(
         f"Adaptive threshold: {threshold:.4f} "
         f"(median_dist={median_dist:.4f}, fraction={fraction}, type={entity_type})"
     )
@@ -402,7 +421,7 @@ def _cluster_aware_selection(
 
     # --- Stage 1: K-Medoids clustering ---
     k = min(max(5, target // 4), n // 3, n)  # e.g., 5-20 clusters
-    logger.info(f"Clustering {n} embeddings into {k} groups (K-Medoids)...")
+    logger.debug(f"Clustering {n} embeddings into {k} groups (K-Medoids)...")
 
     # Compute full cosine distance matrix
     dist_matrix = 1 - emb_normed @ emb_normed.T
@@ -411,7 +430,7 @@ def _cluster_aware_selection(
     selected = list(medoid_indices)
     selected_set = set(selected)
 
-    logger.info(f"Selected {len(selected)} cluster medoids as initial picks.")
+    logger.debug(f"Selected {len(selected)} cluster medoids as initial picks.")
 
     # --- Stage 2: FPS with hard example weighting ---
     min_dists = np.full(n, np.inf)
@@ -436,8 +455,8 @@ def _cluster_aware_selection(
             break  # All points selected
 
         if limit == "auto" and best_dist < auto_threshold:
-            logger.info(
+            logger.debug(
-                f"Auto-stop: Next best image {best_dist:.3f} away " f"(adaptive threshold {auto_threshold:.4f})."
+                f"Auto-stop: next best image {best_dist:.3f} away (adaptive threshold {auto_threshold:.4f})."
             )
             break
 

winnow/embeddings.py

@@ -6,11 +6,13 @@ Unified embedding interface for faces and objects.
 - Caching: Disk-based cache avoids recomputation on reruns
 """
 
-import contextlib
 import importlib
 import logging
 import os
+import time
 import warnings
+from contextlib import contextmanager
+from pathlib import Path
 
 import cv2
 import numpy as np
@@ -20,6 +22,26 @@ from .cache import get_cache
 
 logger = logging.getLogger(__name__)
 
+
+@contextmanager
+def _suppress_output():
+    """Suppress stdout/stderr at the file-descriptor level, silencing C extension noise."""
+    devnull_fd = os.open(os.devnull, os.O_WRONLY)
+    saved_out, saved_err = os.dup(1), os.dup(2)
+    try:
+        os.dup2(devnull_fd, 1)
+        os.dup2(devnull_fd, 2)
+        yield
+    finally:
+        try:
+            os.dup2(saved_out, 1)
+        finally:
+            os.dup2(saved_err, 2)
+        os.close(devnull_fd)
+        os.close(saved_out)
+        os.close(saved_err)
+
+
 # Lazy-loaded singletons
 _insightface_app = None
 _insightface_loaded = False
@@ -37,18 +59,14 @@ def _preload_cuda_libs() -> None:
     """Preload CUDA/cuDNN DLLs so onnxruntime-gpu registers CUDAExecutionProvider.
 
     Starting with onnxruntime-gpu 1.19+, CUDA/cuDNN libraries are no longer
-    bundled inside the ORT package. They must be loaded from the nvidia-*
+    bundled inside the ORT package — they come from the nvidia-* pip packages.
-    pip packages (nvidia-cuda-runtime-cu12, nvidia-cudnn-cu12) before any
+    preload_dlls() locates them automatically via site-packages discovery.
-    InferenceSession is created.
-
-    Calling preload_dlls() with directory="" searches NVIDIA site-packages
-    directories automatically.
     """
     try:
         import onnxruntime
         if hasattr(onnxruntime, "preload_dlls"):
-            onnxruntime.preload_dlls(cuda=True, cudnn=True, directory="")
+            onnxruntime.preload_dlls(cuda=True, cudnn=True)
-            logger.info("Preloaded CUDA/cuDNN DLLs for onnxruntime-gpu")
+            logger.debug("Preloaded CUDA/cuDNN DLLs for onnxruntime-gpu")
         else:
             logger.debug("onnxruntime.preload_dlls() not available (ORT < 1.21)")
     except Exception as e:
@@ -70,32 +88,48 @@ def get_insightface_app():
     # Preload CUDA/cuDNN DLLs BEFORE any ORT InferenceSession is created
     _preload_cuda_libs()
 
+    ctx_id = -1
+    insightface_home = os.environ.get("INSIGHTFACE_HOME", os.path.expanduser("~/.insightface"))
     try:
         import onnxruntime as ort
         from insightface.app import FaceAnalysis
 
+        # Disk cache check — lets the user know whether a download is coming
+        buffalo_path = Path(insightface_home) / "models" / "buffalo_l"
+        if buffalo_path.exists() and any(buffalo_path.iterdir()):
+            logger.info("InsightFace Buffalo_L: found in model cache")
+        else:
+            logger.info("InsightFace Buffalo_L: not cached — downloading now (~300 MB)")
+
         # Get providers, excluding TensorRT to avoid noisy errors
         providers = [p for p in ort.get_available_providers() if p != "TensorrtExecutionProvider"]
-        logger.info(f"Available ONNX providers: {providers}")
+        logger.debug(f"ONNX providers available: {providers}")
 
-        # Determine device: 0 for GPU, -1 for CPU
         gpu_providers = {
             "CUDAExecutionProvider",
             "ROCmExecutionProvider",
             "MPSExecutionProvider",
             "CoreMLExecutionProvider",
         }
-        ctx_id = -1 if _is_force_cpu() else (0 if gpu_providers & set(providers) else -1)
+        has_gpu_provider = bool(gpu_providers & set(providers))
+        ctx_id = -1 if _is_force_cpu() else (0 if has_gpu_provider else -1)
+
+        if not has_gpu_provider and not _is_force_cpu():
+            logger.warning(
+                "No GPU execution provider found — running InsightFace on CPU. "
+                "If you have an NVIDIA GPU, ensure the NVIDIA Container Toolkit is "
+                "installed and the container has GPU access (deploy.resources in compose)."
+            )
 
         device_str = "GPU" if ctx_id >= 0 else "CPU"
-        logger.info(f"Loading InsightFace Buffalo_L on {device_str} (ctx_id={ctx_id})...")
+        logger.info(f"InsightFace Buffalo_L: loading into memory on {device_str}...")
 
-        # Suppress C-level output during model loading
+        t0 = time.time()
-        with open(os.devnull, "w") as devnull, contextlib.redirect_stdout(devnull), contextlib.redirect_stderr(devnull):
+        with _suppress_output():
-            insightface_home = os.environ.get("INSIGHTFACE_HOME", os.path.expanduser("~/.insightface"))
             _insightface_app = FaceAnalysis(name="buffalo_l", root=insightface_home, providers=providers)
             _insightface_app.prepare(ctx_id=ctx_id, det_size=(640, 640))
 
+        logger.info(f"InsightFace Buffalo_L: ready on {device_str} ({time.time() - t0:.1f}s)")
         return _insightface_app
 
     except ImportError:
@@ -103,17 +137,23 @@ def get_insightface_app():
         return None
     except Exception as e:
         logger.error(f"Failed to load InsightFace: {e}")
-        # Retry on CPU if GPU failed
         if ctx_id == 0:
-            logger.warning("Retrying InsightFace on CPU...")
+            logger.warning("InsightFace GPU load failed — retrying on CPU...")
             try:
                 from insightface.app import FaceAnalysis
 
-                _insightface_app = FaceAnalysis(name="buffalo_l", root=insightface_home)
+                t0 = time.time()
+                with _suppress_output():
+                    _insightface_app = FaceAnalysis(
+                        name="buffalo_l",
+                        root=insightface_home,
+                        providers=["CPUExecutionProvider"],
+                    )
                     _insightface_app.prepare(ctx_id=-1, det_size=(640, 640))
+                logger.info(f"InsightFace Buffalo_L: ready on CPU (fallback, {time.time() - t0:.1f}s)")
                 return _insightface_app
             except Exception as ex:
-                logger.error(f"CPU fallback failed: {ex}")
+                logger.error(f"InsightFace CPU fallback failed: {ex}")
         return None
 
 
@@ -162,7 +202,18 @@ def get_siglip_model():
         from transformers import AutoImageProcessor, SiglipVisionModel
 
         model_name = "google/siglip-base-patch16-224"
-        logger.info(f"Loading SigLIP model ({model_name})...")
+
+        # Disk cache check — path derived from model_name using HuggingFace's slug convention
+        hf_home = os.environ.get("HF_HOME", os.path.join(os.path.expanduser("~"), ".cache", "huggingface"))
+        cache_slug = "models--" + model_name.replace("/", "--")
+        model_cache = Path(hf_home) / "hub" / cache_slug
+        if model_cache.exists() and any(model_cache.iterdir()):
+            logger.info(f"SigLIP {model_name}: found in model cache")
+        else:
+            logger.info(f"SigLIP {model_name}: not cached — downloading now (~380 MB)")
+
+        logger.info(f"SigLIP {model_name}: loading into memory...")
+        t0 = time.time()
 
         with warnings.catch_warnings():
             warnings.filterwarnings("ignore", category=FutureWarning)
@@ -176,15 +227,16 @@ def get_siglip_model():
         if not _is_force_cpu():
             if torch.cuda.is_available():
                 _siglip_model = _siglip_model.cuda()
-                logger.info("SigLIP running on CUDA GPU")
+                device_name = "CUDA GPU"
             elif hasattr(torch.backends, "mps") and torch.backends.mps.is_available():
                 _siglip_model = _siglip_model.to("mps")
-                logger.info("SigLIP running on Apple MPS")
+                device_name = "Apple MPS"
             else:
-                logger.info("SigLIP running on CPU")
+                device_name = "CPU"
         else:
-            logger.info("FORCE_CPU set. SigLIP running on CPU")
+            device_name = "CPU (FORCE_CPU)"
 
+        logger.info(f"SigLIP {model_name}: ready on {device_name} ({time.time() - t0:.1f}s)")
         return _siglip_model, _siglip_processor
 
     except ImportError as e:
@@ -267,30 +319,31 @@ def get_embedding(
 
     use_cache = Config.ENABLE_CACHE and asset_id is not None
     cache = get_cache(Config.CACHE_DIR) if use_cache else None
-    model_key = "immich" if entity_type == "face" else "siglip"
+    # Use a single consistent cache key per model so lookups and stores always match.
+    # "immich" was previously used as the face key on the lookup path but "insightface"
+    # on the store path — meaning the cache was never hit for locally-computed embeddings.
+    cache_key = "insightface" if entity_type == "face" else "siglip"
 
     # 1. Use Immich embedding if provided
     if immich_embedding is not None:
         if cache:
-            cache.put(asset_id, immich_embedding, model_key)
+            cache.put(asset_id, immich_embedding, cache_key)
         return immich_embedding
 
     # 2. Check disk cache
     if cache:
-        cached = cache.get(asset_id, model_key)
+        cached = cache.get(asset_id, cache_key)
         if cached is not None:
             return cached
 
     # 3. Compute locally
     if entity_type == "face":
         emb = get_face_embedding(img_pil)
-        model_key = "insightface"
     else:
         emb = get_object_embedding(img_pil)
 
-    # Cache the result
     if emb is not None and cache:
-        cache.put(asset_id, emb, model_key)
+        cache.put(asset_id, emb, cache_key)
 
     return emb
 

winnow/executor.py

@@ -14,7 +14,7 @@ from rich.progress import BarColumn, Progress, SpinnerColumn, TaskProgressColumn
 from .config import Config, get_headers
 from .image_processing import process_face_mode, process_full_mode, process_object_mode
 from .immich_api import fetch_face_data, fetch_full_image
-from .logging import console
+from .log_config import console
 from .upload_tracker import mark_rejected, mark_uploaded
 
 logger = logging.getLogger(__name__)

winnow/frigate_api.py

@@ -21,8 +21,13 @@ def get_frigate_face_counts() -> dict[str, int] | None:
         resp = requests.get(f"{frigate_url}/api/faces", timeout=10)
         resp.raise_for_status()
         data = resp.json()
-        train = data.get("train", {})
+        # Response: {person_name: [file, ...], "train": [...], ...}
-        return {name: len(files) for name, files in train.items() if isinstance(files, list)}
+        # "train" is a flat pending list, not a person — skip it.
+        return {
+            name: len(files)
+            for name, files in data.items()
+            if name != "train" and isinstance(files, list)
+        }
     except Exception as e:
         logger.warning(f"Could not query Frigate face counts: {e}")
         return None

winnow/immich_api.py

@@ -35,10 +35,13 @@ def get_people() -> list[dict]:
             headers=get_headers(),
             timeout=10,
         )
+        if resp.status_code == 401:
+            logger.error("Immich API key is invalid or expired (401 Unauthorized). Update API_KEY.")
+            return []
         resp.raise_for_status()
         return resp.json().get("people", [])
     except (requests.RequestException, ValueError) as e:
-        logger.error(f"Failed to fetch people: {e}")
+        logger.error(f"Failed to fetch people from Immich: {e}")
         return []
 
 
@@ -49,7 +52,7 @@ def fetch_all_assets(person: dict) -> list[dict]:
     url = f"{Config.IMMICH_URL}/api/search/metadata"
     page_size = 1000
 
-    logger.info(f"Fetching assets for {name}...")
+    logger.debug(f"Fetching assets for {name}...")
 
     assets = []
     for page in range(1, MAX_PAGES + 1):
@@ -137,10 +140,11 @@ def fetch_face_data(asset_id: str, person_id: str | None = None) -> FaceData | N
             face.get("boundingBoxY2", 0),
         )
 
+        score = face.get("score")
         return FaceData(
             embedding=embedding,
             bbox=bbox,
-            confidence=face.get("score") or face.get("confidence"),
+            confidence=score if score is not None else face.get("confidence"),
             image_width=face.get("imageWidth", 0),
             image_height=face.get("imageHeight", 0),
         )
@@ -212,6 +216,6 @@ def filter_recent_assets(assets: list[dict], years: int | None = None) -> list[d
         except ValueError:
             continue
 
-    logger.info(f"Retained {len(recent)} assets (filtered {skipped} old assets).")
+    logger.debug(f"Retained {len(recent)} assets (filtered {skipped} old assets).")
     return recent
 

winnow/jobs.py

@@ -13,7 +13,7 @@ from .diversity import select_diverse_assets
 from .embeddings import is_embedding_available, load_embedding_model
 from .frigate_api import get_frigate_face_counts
 from .immich_api import fetch_all_assets, filter_recent_assets
-from .logging import console
+from .log_config import console
 from .upload_tracker import filter_already_uploaded, get_person_summary, update_frigate_count
 
 logger = logging.getLogger(__name__)
@@ -81,7 +81,9 @@ def _resolve_strategy(strategy: str, has_embedding: bool) -> tuple[int | str, st
     return strategy_map.get(strategy, ("auto", "smart"))
 
 
-def _perform_selection(assets: list, limit: int | str, name: str, selection_mode: str, entity_type: str) -> list:
+def _perform_selection(
+    assets: list, limit: int | str, name: str, selection_mode: str, entity_type: str, person_id: str | None = None
+) -> list:
     """Run diversity selection with progress display."""
     if selection_mode == "smart":
         model_display = "InsightFace (face embeddings)" if entity_type == "face" else "SigLIP (visual embeddings)"
@@ -104,6 +106,7 @@ def _perform_selection(assets: list, limit: int | str, name: str, selection_mode
                 name,
                 selection_mode=selection_mode,
                 entity_type=entity_type,
+                person_id=person_id,
                 progress_callback=lambda c, t: progress.update(task, completed=c, total=t),
             )
 
@@ -113,7 +116,9 @@ def _perform_selection(assets: list, limit: int | str, name: str, selection_mode
 
     rprint(f"\n[cyan]Using time-spread selection for {limit} images...[/cyan]")
     with console.status(f"[bold]Selecting {limit} images evenly distributed over time...[/bold]"):
-        selected = select_diverse_assets(assets, limit, name, selection_mode="time", entity_type=entity_type)
+        selected = select_diverse_assets(
+            assets, limit, name, selection_mode="time", entity_type=entity_type, person_id=person_id
+        )
     rprint(f"  [green]Selected {len(selected)} images using time spread.[/green]")
     return selected
 
@@ -145,8 +150,11 @@ def _configure_person(person: dict, people: list[dict]) -> dict | None:
 
     rprint(f"  Found [bold]{len(all_assets)}[/bold] total, [bold]{len(recent_assets)}[/bold] in range ({years} years).")
 
-    # Filter out assets already uploaded to Frigate
+    # Filter out assets already uploaded to Frigate.
-    retry_rejected = os.environ.get("RETRY_REJECTED", "false").lower() in ("true", "1", "yes")
+    # In interactive mode, ask — use the env var only as the default so it can
+    # still be pre-set (e.g. RETRY_REJECTED=true) without forcing the answer.
+    retry_env = os.environ.get("RETRY_REJECTED", "false").lower() in ("true", "1", "yes")
+    retry_rejected = Confirm.ask("Include previously rejected images?", default=retry_env)
     before_dedup = len(recent_assets)
     new_asset_ids = set(filter_already_uploaded([a["id"] for a in recent_assets], retry_rejected=retry_rejected))
     recent_assets = [a for a in recent_assets if a["id"] in new_asset_ids]
@@ -167,7 +175,9 @@ def _configure_person(person: dict, people: list[dict]) -> dict | None:
         return None
 
     # Perform selection
-    selected_assets = _perform_selection(recent_assets, limit, name, selection_mode, entity_type)
+    selected_assets = _perform_selection(
+        recent_assets, limit, name, selection_mode, entity_type, person_id=person["id"]
+    )
 
     rprint(f"  [green]Queued {len(selected_assets)} images for {name}.[/green]")
     return {"person": person, "assets": selected_assets, "limit": len(selected_assets), "config": config}
@@ -276,10 +286,8 @@ def auto_configure(people: list[dict]) -> list[dict]:
         if frigate_counts is not None:
             already_uploaded = frigate_counts.get(name, 0)
         else:
-            already_uploaded = (
+            fc = person_summary.get("frigate_count")
-                person_summary.get("frigate_count")
+            already_uploaded = fc if fc is not None else person_summary.get("uploaded", 0)
-                or person_summary.get("uploaded", 0)
-            )
         capacity = Config.MAX_AUTO_IMAGES - already_uploaded
         if capacity <= 0:
             rprint(
@@ -291,17 +299,24 @@ def auto_configure(people: list[dict]) -> list[dict]:
         has_embedding = is_embedding_available(entity_type)
         limit, selection_mode = _resolve_strategy(strategy, has_embedding)
 
-        # Cap selection to remaining capacity
+        # Cap selection to remaining capacity.
+        # For auto mode with partial training, keep "auto" so adaptive stopping
+        # still runs — just trim the result to the remaining capacity afterward.
+        auto_cap = None
         if limit == "auto":
             if already_uploaded > 0:
-                limit = capacity  # partially filled — select exactly what remains
+                auto_cap = capacity
         else:
             limit = min(limit, capacity)
 
         if selection_mode == "skip":
             continue
 
-        selected_assets = _perform_selection(recent_assets, limit, name, selection_mode, entity_type)
+        selected_assets = _perform_selection(
+            recent_assets, limit, name, selection_mode, entity_type, person_id=person["id"]
+        )
+        if auto_cap is not None:
+            selected_assets = selected_assets[:auto_cap]
 
         if selected_assets:
             rprint(f"  [green]Queued {len(selected_assets)} images for {name}.[/green]")

winnow/log_config.py

@@ -26,10 +26,12 @@ def setup_logging(verbose: bool = False) -> logging.Logger:
     """Configure logging with Rich console and file output."""
     level = logging.DEBUG if verbose else logging.INFO
 
-    # Configure root logger
+    # Configure root logger; close existing handlers before replacing them
     root = logging.getLogger()
     root.setLevel(level)
-    root.handlers.clear()
+    for h in root.handlers[:]:
+        h.close()
+        root.removeHandler(h)
 
     # Rich console handler - uses shared console to avoid breaking progress bars
     root.addHandler(RichHandler(rich_tracebacks=True, markup=True, console=console))
@@ -37,7 +39,7 @@ def setup_logging(verbose: bool = False) -> logging.Logger:
     # File handler (always debug level) — log file respects OUTPUT_DIR if set
     log_dir = os.environ.get("OUTPUT_DIR", ".")
     os.makedirs(log_dir, exist_ok=True)
-    log_path = os.path.join(log_dir, "immich_export.log")
+    log_path = os.path.join(log_dir, "winnow.log")
     file_handler = logging.FileHandler(log_path)
     file_handler.setLevel(logging.DEBUG)
     file_handler.setFormatter(logging.Formatter("%(asctime)s - %(name)s - %(levelname)s - %(message)s"))