DFlash & TurboQuant in llama.cpp with up to 3x faster generation and 7.5x more KV cache in same VRAM

Unity MCP acts as a bridge between AI assistants and your Unity Editor. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.

An awesome repository & A comprehensive survey on interpretability of LLM attention heads.

Code release for "Git Re-Basin: Merging Models modulo Permutation Symmetries"

Shared cockpit for Microsoft Flight Simulator.

Provide with pre-build flash-attention 2 and 3 package wheels on Linux and Windows using GitHub Actions

An open infrastructure to democratize and decentralize the development of superintelligence for humanity.

🚀 Efficient implementations for emerging model architectures

Block Transformer: Global-to-Local Language Modeling for Fast Inference (NeurIPS 2024)

Win10OS kde is a light clean theme for KDE Plasma desktop.

A simple, lightweight PowerShell script that allows you to remove pre-installed apps, disable telemetry, as well as perform various other changes to declutter and customize your Windows experience.…

free finite-difference time-domain (FDTD) software for electromagnetic simulations

🗺 A JavaScript library to easily integrate one or more SVG world maps with all nations (countries) and second-level political subdivisions (countries, provinces, states).

Hyprlust: Minimal hyprland setup

Scaling laws for different architectures have different slopes

[EMNLP 2023] Adapting Language Models to Compress Long Contexts

Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice…

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

[ICLR 2025] General-purpose activation steering library

SpotEdit:Selective Region Editing in Diffusion Transformers

SDK for ComfyUI

Implementation of "Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length"

Model Compression Toolbox for Large Language Models and Diffusion Models

RoboTHOR Challenge

ThreeDWorld simulation environment

An open-source platform for Visual AI.

Code for the habitat challenge

A modular high-level library to train embodied AI agents across a variety of tasks and environments.

The repo for In-context Autoencoder