There are 8 repositories under npu topic.
Efficient Inference of Transformer models
Free TPU for FPGA with compiler supporting Pytorch/Caffe/Darknet/NCNN. An AI processor for using Xilinx FPGA to solve image classification, detection, and segmentation problem.
Samples code for world class Artificial Intelligence SoCs for computer vision applications.
TinyVision - A Tiny Linux Board / IPC / Server / Router / And so on...
The Pipeline example based on AXear-Pi (AX620A) , AXera-Pi Pro (AX650N) and AXera-Pi Zero (AX620Q) shows the software development skills of ISP, Image Processing, NPU, Encoding, and Display modules, which is helpful for users to develop their own multimedia applications.
FREE TPU V3plus for FPGA is the free version of a commercial AI processor (EEP-TPU) for Deep Learning EDGE Inference
YoloV5 NPU for the RK3566/68/88
Simplified AI runtime integration for mobile app development
Advanced driver-assistance system with Google Coral Edge TPU Dev Board / USB Accelerator, Intel Movidius NCS (neural compute stick), Myriad 2/X VPU, Gyrfalcon 2801 Neural Accelerator, NVIDIA Jetson Nano and Khadas VIM3
hardware design of universal NPU(CNN accelerator) for various convolution neural network
Easier usage of LLMs in Rockchip's NPU on SBCs like Orange Pi 5 and Radxa Rock 5 series
Run your yolov7 object detection with Rockchip NPU platforms (RK3566, RK3568, RK3588, RK3588S, RV1103, RV1106, RK3562).
Kotlin bindings for Edgerunner
ONNXim is a fast cycle-level simulator that can model multi-core NPUs for DNN inference
Small Heterogeneous & AI Powered Computing SBC Based on V853
YoloV8 NPU for the RK3566/68/88
ROS 2 Inference sample for using Rockchip NPU.
Rock Pi 5 image with Ubuntu 22, OpenCV, deep learning frameworks and NPU drivers
YoloV8 segmentation NPU for the RK 3566/68/88
NPUsim: Full-system, Cycle-accurate, Value-aware NPU Simulator
Allows access via HTTP to LLM running on RK3588 NPU. Returns JSON response.
Radxa Zero 3W/E image with Ubuntu 22, OpenCV, deep learning frameworks and NPU drivers
Superresolution running on Rockchip NPU (RK3588, etc..)
EmbeddedLLM: API server for Embedded Device Deployment. Currently support IpexLLM/DirectML./CPU
Making Rockchip's RKNN-Toolkit-2 install easier for SBCs like Orange Pi 5 or Radxa Rock 5
Rock Pi 5 image with OpenCV, deep learning frameworks and NPU drivers
YoloV10 NPU for the RK3566/68/88
Prometheus exporter for Rockchip NPU load metrics, written in Rust.
Chisel implementation of Neural Processing Unit for System on the Chip
YoloV5 segmentation NPU for the RK 3566/68/88