Omni Python Packages

auto-round

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.

ai-dynamo-runtime

A Datacenter Scale Distributed Inference Serving Framework

ai-dynamo

A Datacenter Scale Distributed Inference Serving Framework

auto-round-lib

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.

auto-round-nightly

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.

geospacelab

A python-based library to collect, manage, and visualize geospace data (e.g. OMNI, geomagnetic indices, EISCAT, DMSP, SWARM, TEC, AMPERE, etc.).

alpha-avatar-plugins-memory

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.).

alpha-avatar-plugins-persona

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.).

alpha-avatar-agents

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.).

alpha-avatar-plugins-deepresearch

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.).

alpha-avatar-plugins-character

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.).

alpha-avatar-plugins-rag

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.).

alpha-avatar-plugins-mcp

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.).

alpha-avatar-plugins-voice

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.).

alpha-avatar-channels-whatsapp

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.).

auto-round-hpu

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.

alpha-avatar-plugins-status

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.).

kvbm

A Datacenter Scale Distributed Inference Serving Framework

auto-round-kernel

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.

omni-pca

HACS integration + async Python client for HAI/Leviton Omni-Link II panels (Omni Pro II, IIe, LTe, Lumina)