ProductRKNN Toolkit

RKNN

An NPU inference format and toolchain introduced by Rockchip for vision-oriented models. It supports edge NPU-accelerated inference for computer vision tasks such as classification, detection, and OCR.

Timeline (last 90 days)

Oct 15

RKNN is Rockchip's NPU inference format for vision models, commonly used for tasks such as classification, detection, and OCR.

Unverified50%

Oct 15

The language model uses the W8A8 quantized version in RKLLM format; the vision encoder uses the RKNN format.

Unverified50%

All Facts (2)

Unverified

RKNN is Rockchip's NPU inference format for vision models, commonly used for tasks such as classification, detection, and OCR.

50%Unverified

The language model uses the W8A8 quantized version in RKLLM format; the vision encoder uses the RKNN format.

50%

Source Articles

2B Parameters Can See Images! Qwen 3.5 Runs on RK3588 in Local Deployment TestOct 15