Skip to content
@Luna-Inference

Luna Inference

Building the world's fastest & cheapest AI local inference device

Popular repositories Loading

  1. rkllm-server rkllm-server Public

    Forked from ThomasVuNguyen/rkllm-just-works

    A minimal OpenAI-compliant rkllm server, verified functional on rk3588, RKNPU v0.9.6, RKLLM v1.2.0

    Python 12 2

  2. agent-evaluation agent-evaluation Public

    Evaluation framework to synthetically generate data, fine-tune and evaluate small language models made for agents

    Python 1

  3. luna1-voice luna1-voice Public

    Forked from ThomasVuNguyen/paroli

    Streaming TTS based on Piper with optional RK3588 NPU support

    C++ 1

  4. .github .github Public

    Creating the fastest LLM inference layer, through innovations in hardware utilization & novel mathematical operations

  5. simple-llama.cpp simple-llama.cpp Public

    The simplest way to inference llama3.2 fast

    C++

  6. Luna-inference.github.io Luna-inference.github.io Public

    A website to display performance changes over time of Luna Inference

    HTML

Repositories

Showing 10 of 26 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…