The repository provides code for running inference with the Meta Segment Anything Audio Model (SAM-Audio), links for downloading the trained model checkpoints, and example notebooks that show how t…

5Hz Deep-Compression Speech VAE for AR-Diffusion and CALMs

Achieve state of the art inference performance with modern accelerators on Kubernetes

GLM-TTS: Controllable & Emotion-Expressive Zero-shot TTS with Multi-Reward Reinforcement Learning

Helpful kernel tutorials and examples for tile-based GPU programming

NVIDIA cuTile learn

cuTile is a programming model for writing parallel kernels for NVIDIA GPUs

Sharing both practical insights and theoretical knowledge about LLM evaluation that we gathered while managing the Open LLM Leaderboard and designing lighteval!

senders/receivers implementation in rust

An invertible and differentiable implementation of the Constant-Q Transform (CQT).

A framework for efficient model inference with omni-modality models

Another Tutorial on std::execution

An neural full-band audio codec for general audio sampled at 48 kHz with 7.5 kps or 4.5 kbps.

flex-block-attn: an efficient block sparse attention computation library

Official implementation of the paper: "FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models"

Omnilingual ASR Open-Source Multilingual SpeechRecognition for 1600+ Languages

Fast and local neural text-to-speech engine

Public repository for fine-tuning Masked Diffusion Models toward provable self-correction.

Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"

dLLM: Simple Diffusion Language Modeling

Data transformation framework for AI. Ultra performant, with incremental processing. 🌟 Star if you like it!

Di♪♪Rhythm 2: Efficient And High Fidelity Song Generation Via Block Flow Matching

Official implementation of "Continuous Autoregressive Language Models"

This is the official repo for the paper "LongCat-Flash-Omni Technical Report"

Introduction to Machine Learning Systems

[NeurIPS 2025] Encoder-Decoder Diffusion Language Models for Efficient Training and Inference