VapourSynth-MLRT-OV

This package contains the OpenVINO backend implementation of the vs-mlrt plugin.

Installation

pip install vapoursynth-mlrt-ov

Building from source

Requirements

  • C++ Compiler: C++20 compatible (e.g. MSVC 2019+, GCC, Clang)
  • Dependencies:
    • OpenVINO SDK (including OpenVINO Runtime & TBB)
    • ONNX
    • Protobuf
  • CMake Options:
    • WIN32_SHARED_OPENVINO (defaults to ON): Build for Windows with a shared OpenVINO dynamic library. If enabled, copies OpenVINO Runtime and dependency DLLs (tbb12.dll, etc.) to the installation folder.

Compilation

uv build --package vapoursynth-mlrt-ov

Detailed parameter information from the parent project follows.

VapourSynth OpenVINO

The vs-openvino plugin provides optimized pure CPU runtime for some popular AI filters.

Building and Installation

To build, you will need OpenVINO and its dependencies. Only Model Optimizer and Inference Engine are required.

You can download official Intel releases:

Or, you can use our prebuilt Windows binary releases from AmusementClub, our release has the benefit of static linking support.

Sample cmake commands to build:

cmake -S . -B build -G Ninja -D CMAKE_BUILD_TYPE=Release
	-D CMAKE_MSVC_RUNTIME_LIBRARY=MultiThreaded
	-D InferenceEngine_DIR=openvino/runtime/cmake
	-D VAPOURSYNTH_INCLUDE_DIRECTORY="path/to/vapoursynth/include"
cmake --build build
cmake --install build --prefix install

You should find vsov.dll (or libvsov.so) under install/bin. You will also need Intel TBB (you can get tbb.dll from OpenVINO release). On windows, tbb.dll must be placed under vapoursynth/plugins/vsov/ directory for vsov.dll to find.

Usage

Prototype: core.ov.Model(clip[] clips, string network_path[, int[] overlap = None, int[] tilesize = None, string device = "CPU", bint builtin = 0, string builtindir="models", bint fp16 = False, function config = None, bint path_is_serialization = False])

Arguments:

  • clip[] clips: the input clips, only 32-bit floating point RGB or GRAY clips are supported. For model specific input requirements, please consult our wiki.
  • string network_path: the path to the network in ONNX format.
  • int[] overlap: some networks (e.g. CNN) support arbitrary input shape where other networks might only support fixed input shape and the input clip must be processed in tiles. The overlap argument specifies the overlapping (horizontal and vertical, or both, in pixels) between adjacent tiles to minimize boundary issues. Please refer to network specific docs on the recommended overlapping size.
  • int[] tilesize: Even for CNN where arbitrary input sizes could be supported, sometimes the network does not work well for the entire range of input dimensions, and you have to limit the size of each tile. This parameter specify the tile size (horizontal and vertical, or both, including the overlapping). Please refer to network specific docs on the recommended tile size.
  • string device: Specifies the device to run the inference on. Currently "CPU" and "GPU" are supported. "GPU" requires Intel graphics (Broadwell+ processors with Gen8+ integrated GPUs or Xe discrete GPUs) with compatible graphics driver and compute runtime.
  • bint builtin: whether to load the model from the VS plugins directory, see also builtindir.
  • string builtindir: the model directory under VS plugins directory for builtin models, default "models".
  • bint fp16: whether to quantize model to fp16 for faster and memory efficient computation.
  • function config: plugin configuration parameters. It must be a callable object (e.g. a function) with no positional arguments, and returns the configuration parameter in a dictionary dict. The dictionary must use string str for its key and int, float or str for its values. Supported parameters: CPU, GPU (the prefix KEY_ has to be removed). Example: config = lambda: dict(CPU_THROUGHPUT_STREAMS=2)
  • bint path_is_serialization: whether the network_path argument specifies an onnx serialization of type bytes.

When overlap and tilesize are not specified, the filter will internally try to resize the network to fit the input clips. This might not always work (for example, the network might require the width to be divisible by 8), and the filter will error out in this case.

The general rule is to either:

  1. left out overlap, tilesize at all and just process the input frame in one tile, or
  2. set all three so that the frame is processed in tilesize[0] x tilesize[1] tiles, and adjacent tiles will have an overlap of overlap[0] x overlap[1] pixels on each direction. The overlapped region will be throw out so that only internal output pixels are used.

Project links

Data verified by PyPI on Aug 29, 2026
Data provided by the project maintainers, verified at the time the release was uploaded to PyPI.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Latest release

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for Ichunjo from gravatar.com Ichunjo

Credits

Author: AmusementClub

Maintainer: Vardë

GitHub Statistics

Data verified by PyPI on Aug 29, 2026
The GitHub source repository was provided by the project maintainers and verified by PyPI at the time of upload. Stars, forks, and open issues/PRs are derived from that repository and have not been independently verified.

License expression

GPL-3.0-or-later
View SPDX License List

Requires

Python >=3.12

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

vapoursynth_mlrt_ov-16.1.tar.gz (675.0 kB view details)

Uploaded Source

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

vapoursynth_mlrt_ov-16.1-py3-none-win_amd64.whl (69.4 MB view details)

Uploaded Python 3Windows x86-64

vapoursynth_mlrt_ov-16.1-py3-none-manylinux_2_35_aarch64.whl (21.6 MB view details)

Uploaded Python 3manylinux: glibc 2.35+ ARM64

vapoursynth_mlrt_ov-16.1-py3-none-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (49.1 MB view details)

Uploaded Python 3manylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

vapoursynth_mlrt_ov-16.1-py3-none-macosx_15_0_x86_64.whl (31.4 MB view details)

Uploaded Python 3macOS 15.0+ x86-64

vapoursynth_mlrt_ov-16.1-py3-none-macosx_14_0_arm64.whl (23.5 MB view details)

Uploaded Python 3macOS 14.0+ ARM64

File details

Details for the file vapoursynth_mlrt_ov-16.1.tar.gz.

File metadata

  • Download URL: vapoursynth_mlrt_ov-16.1.tar.gz
  • Upload date:
  • Size: 675.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for vapoursynth_mlrt_ov-16.1.tar.gz
Algorithm Hash digest
SHA256 3f37306d7ea854783ca6ec85e958e77dfe82073dc8c37555cbee9a1aed55bace
MD5 f4535f583f6030467c195c4a684eca6c
BLAKE2b-256 e356c83381e8836fe89eca7b65fee902938531b810a59b38e9b92f202f2cde1d

See more details on using hashes here.

Provenance

The following attestation bundles were made for vapoursynth_mlrt_ov-16.1.tar.gz:

Publisher: cd-publish.yml on Jaded-Encoding-Thaumaturgy/vs-wheels

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file vapoursynth_mlrt_ov-16.1-py3-none-win_amd64.whl.

File metadata

File hashes

Hashes for vapoursynth_mlrt_ov-16.1-py3-none-win_amd64.whl
Algorithm Hash digest
SHA256 cd007b950741496bac814f284f07fa1e2f4d4d4a8bbc4cc9591a86882fcf89f8
MD5 51b4a625e1cb55c45b02ad1d70e91430
BLAKE2b-256 1de912127196bdf0b05273772c5a397d3288d71922dbf778642e6dd78d4c0842

See more details on using hashes here.

Provenance

The following attestation bundles were made for vapoursynth_mlrt_ov-16.1-py3-none-win_amd64.whl:

Publisher: cd-publish.yml on Jaded-Encoding-Thaumaturgy/vs-wheels

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file vapoursynth_mlrt_ov-16.1-py3-none-manylinux_2_35_aarch64.whl.

File metadata

File hashes

Hashes for vapoursynth_mlrt_ov-16.1-py3-none-manylinux_2_35_aarch64.whl
Algorithm Hash digest
SHA256 6969127048ddf8f884b465feff51955a5162f2a9580065031eb58c7c02b5a790
MD5 034c0ac5038c7809d1e666785891c00f
BLAKE2b-256 653d5cb054466282a1c9405c838595ccef09d944e70cb7330fb7110b901f8027

See more details on using hashes here.

Provenance

The following attestation bundles were made for vapoursynth_mlrt_ov-16.1-py3-none-manylinux_2_35_aarch64.whl:

Publisher: cd-publish.yml on Jaded-Encoding-Thaumaturgy/vs-wheels

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file vapoursynth_mlrt_ov-16.1-py3-none-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.

File metadata

File hashes

Hashes for vapoursynth_mlrt_ov-16.1-py3-none-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
Algorithm Hash digest
SHA256 a4b827687778ec15cef811d81d8abd32587b9735f0ada0f05dda7843eb54c8f5
MD5 6b910df2ecf2db97b519f316381f0b85
BLAKE2b-256 2a2f79cda1c7ac8cfa37eeda80e89965eca690655080163ddd770693f1398047

See more details on using hashes here.

Provenance

The following attestation bundles were made for vapoursynth_mlrt_ov-16.1-py3-none-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl:

Publisher: cd-publish.yml on Jaded-Encoding-Thaumaturgy/vs-wheels

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file vapoursynth_mlrt_ov-16.1-py3-none-macosx_15_0_x86_64.whl.

File metadata

File hashes

Hashes for vapoursynth_mlrt_ov-16.1-py3-none-macosx_15_0_x86_64.whl
Algorithm Hash digest
SHA256 d297d9078f0003670762288a7740bf1d530efc8d0d041843cb9702d27b4ee870
MD5 c44e26960e0be2d3960e3838efb15ff6
BLAKE2b-256 1f10b9fefa726fa9c2435d597b83be98e3faf2bb974ab178d77a5e598790b6e2

See more details on using hashes here.

Provenance

The following attestation bundles were made for vapoursynth_mlrt_ov-16.1-py3-none-macosx_15_0_x86_64.whl:

Publisher: cd-publish.yml on Jaded-Encoding-Thaumaturgy/vs-wheels

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file vapoursynth_mlrt_ov-16.1-py3-none-macosx_14_0_arm64.whl.

File metadata

File hashes

Hashes for vapoursynth_mlrt_ov-16.1-py3-none-macosx_14_0_arm64.whl
Algorithm Hash digest
SHA256 c68fa141f0d69740de4bef30132fa8786d9e407a886b6c5e2eaafa2bd1c49373
MD5 00fc1a2ba8cce3e15fd497f32fa8da6c
BLAKE2b-256 87ec870e81889a1dd81eae7848b6454e1a5cf6a15bb582f210e5ac670b1b48ca

See more details on using hashes here.

Provenance

The following attestation bundles were made for vapoursynth_mlrt_ov-16.1-py3-none-macosx_14_0_arm64.whl:

Publisher: cd-publish.yml on Jaded-Encoding-Thaumaturgy/vs-wheels

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

This release

16.1 This release

6 files

16.0

6 files

15.16

6 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page