Learn CUDA with PyTorch

TTS model capable of streaming conversational audio in realtime.

MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.

"AI-Trader: Can AI Beat the Market?" Live Trading Bench: https://ai4trade.ai Tech Report Link: https://arxiv.org/abs/2512.10971

FlashInfer: Kernel Library for LLM Serving

LLM101n: Let's build a Storyteller

The best ChatGPT that $100 can buy.

Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

An open-source, real-time streaming Automatic Speech Recognition (ASR) model for Thai, optimized for low-latency CPU deployment.

Code and training scripts for FlexOlmo

Code release for NeX: Real-time View Synthesis with Neural Basis Expansion

Text-audio foundation model from Boson AI

Text-audio foundation model from Boson AI

Automatically cleaning, enhancing, segmenting, filtering, and formatting a dataset to fine tune or train a voice model.

A FastAPI wrapper for NVIDIA's new parakeet 0.6b v2 TTS 600-million-parameter model designed for high-quality English speech recognition

An open-source AI agent that brings the power of Gemini directly into your terminal.

Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.

Will write CUDA for 100 days

My submission for the GPUMODE/AMD fp8 mm challenge

The official Python SDK for Model Context Protocol servers and clients

Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

LLMPerf is a library for validating and benchmarking LLMs

Fastest kernels written from scratch

Fast CUDA matrix multiplication from scratch

CUDA/Metal accelerated language model inference

Inference Llama 2 in one file of pure C

Yet Another Language Model: LLM inference in C++/CUDA, no libraries except for I/O