A flexible utility for converting tensor precision in PyTorch models and safetensors files, enabling efficient deployment across various platforms.
-
Updated
Aug 24, 2023 - Python
A flexible utility for converting tensor precision in PyTorch models and safetensors files, enabling efficient deployment across various platforms.
IEEE 754-style floating-point converter
Simple Example of Pytorch -> TensorRT and Inference
Export pytorch model to ONNX and convert ONNX from float32 to float 16
Converts a floating-point number or hexadecimal representation of a floating-point numbers into various formats and displays them into binary/hexadecimal.
Optimised Caffe with OpenCL supporting for less powerful devices such as mobile phones
apextrainer is an open source toolbox for fp16 trainer based on Detectron2 and Apex
👀 Apply YOLOv8 exported with ONNX or TensorRT(FP16, INT8) to the Real-time camera
Pytorch implementation of DreamerV2: Mastering Atari with Discrete World Models, based on the original implementation
CPP20 implementation of a 16-bit floating-point type mimicking most of the IEEE 754 behavior. Single file and header-only.
Let's train CIFAR 10 Pytorch with Half-Precision!
Stage 3 IEEE 754 half-precision floating-point ponyfill
Round matrix elements to lower precision in MATLAB
Deploy stable diffusion model with onnx/tenorrt + tritonserver
Conversion to/from half-precision floating point formats
InsightFace REST API for easy deployment of face recognition services with TensorRT in Docker.
Add a description, image, and links to the fp16 topic page so that developers can more easily learn about it.
To associate your repository with the fp16 topic, visit your repo's landing page and select "manage topics."