Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.

Multi-Joint dynamics with Contact. A general purpose physics simulator.

Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.

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

"Effective Whole-body Pose Estimation with Two-stages Distillation" (ICCV 2023, CV4Metaverse Workshop)

[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning

Perplexica is an AI-powered search engine. It is an Open source alternative to Perplexity AI

Scalable neural net training via automatic normalization in the modular norm.

T-GATE: Temporally Gating Attention to Accelerate Diffusion Model for Free!

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance. Accepted to ACL 2024.

[HPCA'21] SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning

run paligemma in real time

ERRor ANnotation Toolkit: Automatically extract and classify grammatical errors in parallel original and corrected sentences.

Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts) @ NAACL 2024

TensorRT Model Optimizer is a unified library of state-of-the-art model optimization techniques such as quantization and sparsity. It compresses deep learning models for downstream deployment frame…

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

aider is AI pair programming in your terminal

A large-scale information-rich web dataset, featuring millions of real clicked query-document labels

Code for the ACL 2017 paper "Get To The Point: Summarization with Pointer-Generator Networks"

Easy token price estimates for 400+ LLMs

Tile primitives for speedy kernels

[ICML 2024] CLLMs: Consistency Large Language Models

Code and data for "MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning" (ICLR 2024)

Granite Code Models: A Family of Open Foundation Models for Code Intelligence

The Free Software Media System

Microsoft SEAL is an easy-to-use and powerful homomorphic encryption library.

This package is designed to bypass puppeteer's bot-detecting captchas such as Cloudflare. It acts like a real browser and can be managed with puppeteer.

A multi-level tensor algebra superoptimizer