INAV: Navigation-enabled flight control software

A new lightweight, hybrid routing mesh protocol for packet radios

ShotPlan: Cinematic Video Generation with Learnable Planning Token

Docker configuration for running VLLM on dual DGX Sparks

An open-source audio wake word (or phrase) detection framework with a focus on performance and simplicity.

Fast and memory-efficient exact attention

Efficient Triton Kernels for LLM Training

Accessible large language models via k-bit quantization for PyTorch.

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

Train transformer language models with reinforcement learning.

low cost software radio platform

PersonaPlex code for python 3.13