Flash Attention Triton kernel with support for second-order derivatives

Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation

PygmalionAI's large-scale inference engine

Go ahead and axolotl questions

Renderer for the harmony response format to be used with gpt-oss

VLLM Port of the Chatterbox TTS model

This repository contains implementations and illustrative code to accompany DeepMind publications

Fractal Graph-of-Thought. Rhizomatic Mind-Mapping for Ai-Agents, Web-Links, Notes, and Code.

Esoteric Language Models

utilities for decoding deep representations (like sentence embeddings) back to text

⚡ Supercharge your Perplexity.ai

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

Use the NVIDIA Audio2Face headless server and interact with it through a requests API. Generate animation sequences for Unreal Engine 5, Maya and MetaHumans

MLOS is a project to enable autotuning for systems.

Scalable data pre processing and curation toolkit for LLMs

A toolkit for processing speech data and creating speech datasets

Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.

Lightweight coding agent that runs in your terminal

A time traveling resource monitor for modern Linux systems

Convert Compute And Books Into Instruct-Tuning Datasets

A service to convert audio to facial blendshapes for lipsyncing and facial performances.

Run Claude Code on OpenAI models

A tool for an analysis of LLM generations.

🙌 OpenHands: Code Less, Make More

The fast, Pythonic way to build Model Context Protocol servers 🚀

A collection of LogitsProcessors to customize and enhance LLM behavior for specific tasks.