Skip to content

Latest commit

 

History

History
179 lines (133 loc) · 6.49 KB

README.md

File metadata and controls

179 lines (133 loc) · 6.49 KB

AI - Edge Computing

OBJECT DETECTION WITH LLMs

Onnxruntime

YOLO -NAS

QUANTIZATION

YOLO - TENSORRT - POSE - DETECT - SEGMENT

YOLO - POSE - DETECT - SEGMENT - CLASSIFY

FIXED BUGS

DOCUMENT ONNXRUNTIME

ONNXRUNTIME compatibility (ONNX, OPSET, TensorRT, CUDA, CUDNN)

TENSORRT

FASTDEPLOY

DEEPSPARSE - SPARSEML

MCU

COMPRESSION

OPENCV

MACE

NCNN

COREML

CoreML - Stable Diffusion

Performance Tool

LIGHTWEIGHT DETECTOR

TVM

LLVM

ARM-NN

CMSIS-NN

RISC-V

ARM

OpenCL

Vulkan

Cuda

Metal

XNNPack

Samsung ONE (On-device Neural Engine)

COMPANY

To provide an AI-Driven Optimizer to make Deep Neural Networks:

  • faster,
  • smaller,
  • energy-efficient
  • from cloud to edge computing
  • without compromising accuracy

PAPER