bfloat16

oneAPI Deep Neural Network Library (oneDNN)

Up to 200x Faster Dot Products & Similarity Metrics — for Python, Rust, C, JS, and Swift, supporting f64, f32, f16 real & complex, i8, and bit vectors using SIMD for both AVX2, AVX-512, NEON, SVE, & SVE2 📐

Library for specialized dense and sparse matrix operations, and deep learning primitives.

Half-precision floating point types f16 and bf16 for Rust.

Julia implementation for the BFloat16 number type

Round matrix elements to lower precision in MATLAB

C++ template library for floating point operations

Floating-Point Arithmetic Library for Z80

A JAX implementation of stochastic addition.

A LLaMA2-7b chatbot with memory running on CPU, and optimized using smooth quantization, 4-bit quantization or Intel® Extension For PyTorch with bfloat16.

IEEE 754-style floating-point converter

Bfloat16 conversion utilities for Go/Golang

A Pytorch implementation of stochastic addition.

CUDA/HIP header-only library for writing vectorized and low-precision (16 bit, 8 bit) GPU kernels

Basic linear algebra routines implemented using the chop rounding function

Comparison of vector element sum using various data types.

Customizable floating point types, with all standard floating point operations implemented from scratch.

Comparison of PageRank algorithm using various datatypes.

A lightweight C++ implementation of the Brain Floating Point (bfloat16) format.

Hybridized On-Premise and Cloud (HOPC) Deployment Experimentation with Bfloat16