A Datacenter Scale Distributed Inference Serving Framework
🎙️ 「大模型」从0训练0.1B能听能说能看的全模态Omni模型！A 0.1B Omni model trained from scratch, capable of listening, speaking, and seeing!
A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support and full compatibility with vLLM, SGLang, and Transformers.
A real-time interactive Omni Avatar built on LiveKit, which allows you to seamlessly integrate with any open source Avatar components (real-time model, visual, voice, memory, search, etc.).
🤗 Optimum Intel: Accelerate inference with Intel optimization tools
Parcelvoy: Open source multi-channel marketing automation platform. Send data-driven emails, sms, push notifications and more!
LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM
🎨 Omni for Visual Studio Code
A modern, mostly zero-allocation C++23 library for working with low-level Windows within user-space. Iteration over loaded modules via PEB, EAT iteration, lazy imports, syscalls, and more.
🔥An open-source survey of the latest video reasoning tasks, paradigms, and benchmarks.
(NIPS 2025) OpenOmni: Official implementation of Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-Time Self-Aware Emotional Speech Synthesis
🎨 Omni for Spicetify
Homelab setup based on Omni and Talos.
Omni Browser is a secure, open-source Android browser by RebelRoot. Built on Mozilla GeckoView, it features native WebExtension support, aggressive media stream interception, a private encrypted locker, and on-device machine learning tools.
Add a description, image, and links to the omni topic page so that developers can more easily learn about it.
To associate your repository with the omni topic, visit your repo's landing page and select "manage topics."