SCUDA is a GPU over IP bridge allowing GPUs on remote machines to be attached to CPU-only machines.

C11 compiler with GNU extensions for x86-64 Linux, working towards C23

Toolkit to segment text into sentences or other semantic units in a robust, efficient and adaptable way.

SONAR, a new multilingual and multimodal fixed-size sentence embedding space, with a full suite of speech and text encoders and decoders.

Large Concept Models: Language modeling in a sentence representation space

The easiest library for creating GUIs in Python

Massive open Japanese speech corpus

Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama mode…

Official inference framework for 1-bit LLMs

全国の住所データAPI

Code repo for the paper "SpinQuant LLM quantization with learned rotations"

A programming framework for agentic AI 🤖 PyPi: autogen-agentchat Discord: https://aka.ms/autogen-discord Office Hour: https://aka.ms/autogen-officehour

An easy-to-use and fast library for task-based parallelism, utilizing coroutines.

AMD related optimizations for transformer models

A large-scale simulation framework for LLM inference

[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

High-resolution models for human tasks.

Code for "Training-free Graph Neural Networks and the Power of Labels as Features" (TMLR 2024)

Development repository for the Triton language and compiler

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

A lightweight library for portable low-level GPU computation using WebGPU.

Spatial Voice Conversion: Voice Conversion Preserving Spatial Information and Non-target Signals

LLM101n: Let's build a Storyteller

Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.

LLM training in simple, raw C/CUDA

Memory Mosaics are networks of associative memories working in concert to achieve a prediction task.

The robust text processing pipeline framework enabling customizable, efficient, and metric-logged text preprocessing.

The MinHash-based Code Relationship & Investigation Toolkit (MCRIT) is a framework created to simplify the application of the MinHash algorithm in the context of code similarity.