LongMIT: Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets

Official PyTorch code for Deep Audio-Signal Holistic Embeddings

Target Speaker Extraction Toolkit

SOTA discrete acoustic codec models with 40 tokens per second for audio language modeling

⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。

A MLX port of FLUX based on the Huggingface Diffusers implementation.

Fast Matrix Multiplications for Lookup Table-Quantized LLMs

MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.

A Fusion Code Generator for NVIDIA GPUs (commonly known as "nvFuser")

NVIDIA Math Libraries for the Python Ecosystem

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

PyTorch native quantization and sparsity for training and inference

LLM101n: Let's build a Storyteller

An intelligent assistant serving the entire software development lifecycle, powered by a Multi-Agent Framework, working with DevOps Toolkits, Code&Doc Repo RAG, etc.

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

A generative speech model for daily dialogue.

Speech, Language, Audio, Music Processing with Large Language Model

[ACM MM 2024] This is the official code for "AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encoding"

Tile primitives for speedy kernels

Kolmogorov Arnold Networks

Instant voice cloning by MIT and MyShell.

整理各研究方向经典论文

A native PyTorch Library for large model training

The official Meta Llama 3 GitHub site

lightweight, standalone C++ inference engine for Google's Gemma models.

CUDA Core Compute Libraries

THIS REPOSITORY HAS MOVED TO github.com/nvidia/cub, WHICH IS AUTOMATICALLY MIRRORED HERE.

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable…