Tools

How to Run CNN Models on RK3576

Convert YOLO11n on an Ubuntu PC, deploy it to RK3576 over SSH/SCP, and verify C++ and Python inference on its built-in NPU.

How to Run CNN Models on RK3588

Convert YOLO11n on an Ubuntu PC, deploy it to RK3588 over SSH/SCP, and verify C++ and Python inference on its built-in NPU.

How to Run LLM Models on RK3576

Convert DeepSeek-R1-Distill-Qwen-1.5B to RKLLM on an Ubuntu x86_64 PC, deploy it to RK3576 over SSH/SCP, and run the official C++ example.

How to Run LLM Models on RK3588

Convert DeepSeek-R1-Distill-Qwen-1.5B to RKLLM on an Ubuntu x86_64 PC, deploy it to RK3588 over SSH/SCP, and run the official C++ example.

Docker-based LLM model Deploy Tool

Use a Docker container to deploy LLM model on the device.

Speed Test Tool

Performance testing for LLM models.

RK LLM Model Conversion

Docker-based VLM model Deploy Tool

Use a Docker container to deploy VLM model on the device.

Speed Test Tool

Performance testing for VLM models.

RK VLM Model Conversion

Run CNN and Transformer Models on RK182x with RKNN3

Convert, cross-compile, deploy, and run RKNN3 models on an RK182x M.2 accelerator connected to an RK3588 host.