Anguo

Edge AI & embedded vision on Rockchip. Building RK Edge Doctor (open source).，

Joined on Nov 1, 2026

Anguo

Nov 3

Pinning NPU cores on RK3588 buys you 5% — and costs the big model 10%

#rockchip #rknn #benchmark #edgeai

2 min read

Want to connect with Anguo?

Create an account to connect with Anguo. You can also sign in below to proceed if you already have an account.

Create Account

Already have an account? Sign in

Anguo

Nov 2

Deploying to 20 Rockchip boards by hand is a trap — so I built rk-deploy

#rockchip #embedded #devops #systemd

4 min read

Anguo

Nov 2

RK3588 INT8, measured: 1.96 on YOLOv8n, 1.4 on YOLO11n — plus OCR joins the bench

#rockchip #rknn #benchmark #edgeai

2 min read

Anguo

Nov 2

Your IP camera's clock is wrong — and that's why ONVIF authentication keeps failing

#onvif #python #opensource #iot

4 min read

Anguo

Nov 2

I verified 127 Rockchip projects by hand so this list wouldn't rot — awesome-rockchip is live

#rockchip #rk3588 #opensource #embedded

4 min read

Anguo

Nov 2

10 RKNN models benchmarked on RK3588 — and the fastest one is cheating onto the CPU

#rockchip #rknn #benchmark #edgeai

4 min read

Anguo

Nov 1

Before you convert that ONNX model to RKNN, check whether it can convert at all

#rockchip #rknn #opensource #embedded

2 min read

Anguo

Nov 1

Your IP camera connects fine. Is the stream actually healthy?

#rockchip #rtsp #opensource #embedded

2 min read

Anguo

Nov 1

Is your RKNN model secretly running on the CPU? I built a tool that tells you

#rockchip #rk3588 #opensource #embedded

3 min read

DEV Community

Anguo

Badges

Writing Debut

Pinning NPU cores on RK3588 buys you 5% — and costs the big model 10%

Want to connect with Anguo?

Deploying to 20 Rockchip boards by hand is a trap — so I built rk-deploy

RK3588 INT8, measured: 1.96 on YOLOv8n, 1.4 on YOLO11n — plus OCR joins the bench

Your IP camera's clock is wrong — and that's why ONVIF authentication keeps failing

I verified 127 Rockchip projects by hand so this list wouldn't rot — awesome-rockchip is live

10 RKNN models benchmarked on RK3588 — and the fastest one is cheating onto the CPU

Before you convert that ONNX model to RKNN, check whether it can convert at all

Your IP camera connects fine. Is the stream actually healthy?

Is your RKNN model secretly running on the CPU? I built a tool that tells you