# open-mmlab/mmdeploy

OpenMMLab Model Deployment Framework

Repository: https://github.com/open-mmlab/mmdeploy
Canonical: https://ross.abutalabs.com/products/mmdeploy
Homepage: https://mmdeploy.readthedocs.io/en/latest/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: model-converter, sdk, deployment, tensorrt, ncnn, pplnn, openvino, onnxruntime, onnx, mmdetection, mmsegmentation, computer-vision, deep-learning, pytorch
Last push: 2024-09-30T02:34:18+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 1713, "days_push": 703, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3137, forks 714 (observed 2026-08-28T04:07:45.742716+00:00)

## What it is
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
- artifact type: framework
- maturity: maintenance
- function: machine-learning, deep-learning, compiler, sdk, deployment
- domain: computer-vision, deep-learning, machine-learning, developer-tools
- platform: python, cross-platform
- tags: model-conversion, onnx, tensorrt, openvino, ncnn, inference-optimization, openmmlab, edge-deployment, linux, gpu

## Member repositories
- open-mmlab/mmdeploy (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:45.742716+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:26:05.271243+00:00, confidence not recorded.
  - readme: https://github.com/open-mmlab/mmdeploy (fetched 2026-08-28T04:07:45.742716+00:00, sha bcefe13a3a14)
  - registry_pypi: https://pypi.org/pypi/mmdeploy/json (fetched 2026-08-29T09:41:18.586675+00:00, sha 616fd91c34a9)
- Data as of 2026-08-30T08:39:29.467469+00:00.