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

Conversion to/from half-precision floating point formats

Deploy stable diffusion model with onnx/tenorrt + tritonserver

Stage 3 IEEE 754 half-precision floating-point ponyfill

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

Round matrix elements to lower precision in MATLAB

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

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

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

Let's train CIFAR 10 Pytorch with Half-Precision!

Export pytorch model to ONNX and convert ONNX from float32 to float 16

IEEE 754-style floating-point converter

A flexible utility for converting tensor precision in PyTorch models and safetensors files, enabling efficient deployment across various platforms.

Converts a floating-point number or hexadecimal representation of a floating-point numbers into various formats and displays them into binary/hexadecimal.

apextrainer is an open source toolbox for fp16 trainer based on Detectron2 and Apex

Just a bunch of hand crafted experiments to tinker with the capabilities of a really fast aarch64 based system.

Transformer implementation in pytorch trained on NVIDIA A100 in fp16

Simple Example of Pytorch -> TensorRT and Inference