Package, configure, and iterate on a model with Truss at whatever level of control your model needs.
Mmdeploy
MMDeploy provides a model deployment framework from the OpenMMLab project.
About Mmdeploy
MMDeploy is an open-source deep learning model deployment toolset from the OpenMMLab project. It converts and runs models built with OpenMMLab codebases, including mmpretrain, mmdet, mmseg, mmocr, mmpose, and mmaction2, across several inference backends.
The project publishes a device, platform, and backend support matrix covering Linux, Windows, macOS, Android, and several hardware targets. Support depends on the specific combination, and some combinations are not listed. Version 1.x is the maintained line for new features, and users should align MMDeploy's version with their OpenMMLab 2.0 codebases. The 0.x branch is slated for deprecation. Pricing is unknown, and the project is released under the Apache 2.0 license.
Key features
- Deployment support for models from multiple OpenMMLab codebases, including mmdet and mmseg
- Multiple inference backends, including ONNX Runtime, TensorRT, OpenVINO, and ncnn
- Device and platform matrix spanning Linux, Windows, macOS, Android, and embedded hardware
- Extensible C/C++ SDK with customizable Transform, Net, and Module components
- Guides for model conversion, configuration, profiling, and quantization
Best for: Developers who need to deploy OpenMMLab models to a range of inference backends and hardware targets.
Good for
- Released under the Apache 2.0 open-source license
- Part of the OpenMMLab project, with a published list of supported codebases and models
- Broad backend and hardware coverage listed in its support matrix
Watch out for
- Support varies by device, platform, and backend combination, and some combinations are not listed
- Version 1.x is aligned with OpenMMLab 2.0, so users must match versions
- The 0.x branch will be deprecated, and new features will only be added to 1.x
Mmdeploy at a glance
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
Mmdeploy alternatives
Tools and sites you could use instead, ranked by how closely they match.
Merlin supports machine learning model management, deployment, and serving in Kubernetes environments.
Open source
24 alternatives
Eurybia tracks model drift and validates data during machine learning model deployment.
Open source
24 alternatives
Model deployment for AI applications is supported by nndeploy, a framework described as easy to use and high performance.
Open source
24 alternatives
Cog packages machine learning models into containers to support deployment across environments.
Open source
24 alternatives
ONNX-MLIR compiles ONNX models using MLIR compiler infrastructure for model deployment workflows.
Open source
24 alternativesPopular in AI Infrastructure & MLOps
Well-known listings from the same topic.
Guild AIguild.aiFlow AIflow-ai.comsystemprompt.iosystemprompt.ioCoreWeavecoreweave.comKili Technologykili-technology.comAPI docsdocs.x.ai
Mmdeploy FAQ
Which OpenMMLab codebases does MMDeploy support?
The project lists support for mmpretrain, mmdet, mmseg, mmagic, mmocr, mmpose, mmdet3d, mmrotate, and mmaction2, with more planned.
What license is MMDeploy released under?
MMDeploy is released under the Apache 2.0 license.
Which version should new users use?
New features are only added to MMDeploy 1.x on the main branch, and the 0.x branch will be deprecated. Users should align the version with their OpenMMLab codebases.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.