Fast fp16-fp8 mixed precision matmul on RDNA3/3.5 GPUs without native fp8

Lower Precision Floating Point Operations

FSampler is a training‑free, sampler‑agnostic acceleration layer for diffusion sampling.

Enable true multi gpu capability in Comfy UI using XDiT XFuser and FSDP managed by Ray

Adds customizable sliders for Custom (OpenAI-compatible) source of Chat Completion API.

Next-generation AI roleplay system

llama.cpp fork with additional SOTA quants and improved performance

An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs

Open-Sora: Democratizing Efficient Video Production for All

A fast inference library for running LLMs locally on modern consumer-class GPUs

Large Language Model Text Generation Inference

YaRN: Efficient Context Window Extension of Large Language Models

A single Gradio + React WebUI with extensions for ACE-Step, OmniVoice, Kimi Audio, Piper TTS, GPT-SoVITS, CosyVoice, XTTSv2, DIA, Kokoro, OpenVoice, ParlerTTS, Stable Audio, MMS, StyleTTS2, MAGNet,…

A webui for different audio related Neural Networks

Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private.

🚀 BARK INFINITY GUI CMD 🎶 Powered Up Bark Text-prompted Generative Audio Model

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

[OBSOLETE] Extensions API for SillyTavern.

Oobabooga extension for Bark TTS

Run GGUF models easily with a KoboldAI UI. One File. Zero Install.

Free Download Manager Add-On. Provides support for downloading videos from various sites.

4 bits quantization of LLaMa using GPTQ

A gradio web UI for running Large Language Models like GPT-J 6B, OPT, GALACTICA, LLaMA, and Pygmalion.

An extension to Oobabooga to add a simple memory function for chat

4 bits quantization of LLMs using GPTQ