IntelLabs

A model library for exploring state-of-the-art deep learning topologies and techniques for optimizing Natural Language Processing neural networks

Efficient Retrieval Augmentation and Generation Framework

A fuzzer for full VM kernel/driver targets

Framework for enhancing LLMs for RAG tasks using fine-tuning.

Intel Homomorphic Encryption Acceleration Library accelerates modular arithmetic operations used in homomorphic encryption by leveraging AVX512 and IFM52 available on Intel's 3rd Generation Xeon...

Causal discovery algorithms and tools for implementing new ones

Accelerated kernel library for genomics

Computer Graphics Video Quality Metric

VDMS: Your Favorite Visual Data Management System

EquiTriton is a project that seeks to implement high-performance kernels for commonly used building blocks in equivariant neural networks, enabling compute efficient training and inference.

Intel’s HERACLES accelerator introduces a new set of fundamental instructions, the Polynomial Instructions Set Architecture (P-ISA) that operates directly on polynomials requiring a completely new...

Graph learning framework for long-term video understanding

research work on multimodal cognitive ai

Pre-Silicon Hardware Fuzzing Toolkit

This repository contains the official Implementation for "BAA-NGP: Bundle-Adjusting Accelerated Neural Graphics Primitives".

Intel lab's open sourced data science framework for accelerating digital biology

LLM Adversarial Robustness Toolkit, a toolkit for evaluating LLM robustness through adversarial testing.

Simple framework for training and evaluating math reasoning agents using local models, GRPO and vLLM.