Intel® Tensor Processing Primitives extension for Pytorch*

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

TPP experimentation on MLIR for linear algebra

An experimental CPU backend for Triton

Reference implementation of Deep Neural Network primitives using LIBXSMM's Tensor Processing Primitives (TPP)

PArallelLOOPgEneratoR: Threaded Loops Code Generation Infrastructure targeting Tensor Contraction Applications such as GEMMs, Convolutions and Fused Deep Learning Primitives

An Intel FPGA AI NIC implementation that offloads All-Reduce in distributed training