SGLang is a fast serving framework for large language models and vision language models.

SYCL* Templates for Linear Algebra (SYCL*TLA) - SYCL based CUTLASS implementation for Intel GPUs

PyTorch native quantization and sparsity for training and inference

OpenAI Triton backend for Intel® GPUs

A high-throughput and memory-efficient inference and serving engine for LLMs

Stable Diffusion and Flux in pure C/C++

GEMM performance kernels for Intel GPUs, Nvidia GPUs, and Intel CPUs, written using SYCL joint matrix extension

Tensors and Dynamic neural networks in Python with strong GPU acceleration

oneAPI Deep Neural Network Library (oneDNN)

A Python package for extending the official PyTorch that can easily obtain performance on Intel platform

Port of Facebook's LLaMA model in C/C++

Representation and Reference Lowering of ONNX Models in MLIR Compiler Infrastructure

MLIR Sample dialect

a JIT assembler for x86(IA-32)/x64(AMD64, x86-64) MMX/SSE/SSE2/SSE3/SSSE3/SSE4/FPU/AVX/AVX2/AVX-512 by C++ header

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

Fast sparse deep learning on CPUs

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Intel staging area for llvm.org contribution. Home for Intel LLVM-based projects.

This fork of BVLC/Caffe is dedicated to improving performance of this deep learning framework when running on CPU, in particular Intel® Xeon processors.

Models and examples built with TensorFlow

profiling tools for pytorch

Transformer implemented in Keras

Example code for the guide

Phrase-Based & Neural Unsupervised Machine Translation