open-mmlab/mmdeploy

Health v2 · maintenance only

Adoption not part of the score

3137 stars · 714 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

MMDeploy is the OpenMMLab model deployment framework that converts PyTorch-based OpenMMLab models (mmdetection, mmsegmentation, etc.) into deployable formats like ONNX, TensorRT, OpenVINO, and ncnn. It provides conversion tooling plus an inference SDK for running computer vision models across platforms.

Use cases

• convert mmdetection models to TensorRT
• export PyTorch vision models to ONNX
• deploy OpenMMLab models on edge devices with ncnn
• run object detection inference with a C++ SDK
• optimize segmentation models with OpenVINO
• deploy computer vision models to production

When to choose

• you use OpenMMLab 2.0 codebases and need production deployment
• you need multi-backend support (TensorRT, ONNX Runtime, OpenVINO, ncnn) from one tool
• you want a ready-made inference SDK for vision models

When to avoid

• your models are not from the OpenMMLab ecosystem
• you need general-purpose LLM or NLP model deployment
• you need a framework with frequent recent updates - development activity has slowed

Facets

framework · maturity maintenance

machine-learning deep-learning compiler sdk deployment computer-vision deep-learning machine-learning developer-tools python cross-platform model-conversion onnx tensorrt openvino ncnn inference-optimization openmmlab edge-deployment linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="open-mmlab/mmdeploy")