fp16 topic

Stage 3 IEEE 754 half-precision floating-point ponyfill

petamoriken

Conversion to/from half-precision floating point formats

Maratyszcza

InsightFace REST API for easy deployment of face recognition services with TensorRT in Docker.

SthPhoenix

Round matrix elements to lower precision in MATLAB

higham

Deploy stable diffusion model with onnx/tenorrt + tritonserver

kamalkraj

Optimised Caffe with OpenCL supporting for less powerful devices such as mobile phones

jizhuoran

Pytorch implementation of DreamerV2: Mastering Atari with Discrete World Models, based on the original implementation

esteveste

CPP20 implementation of a 16-bit floating-point type mimicking most of the IEEE 754 behavior. Single file and header-only.

fengwang

👀 Apply YOLOv8 exported with ONNX or TensorRT(FP16, INT8) to the Real-time camera

the0807