npu repositories

Trending repositories tagged npu, ranked by trending score. Updated daily.

  1. 1
    AbrahamPaulJ/nightmare-mobile

    On-device, ComfyUI-style node graph for image/video diffusion on Android. Run MiniMax H3 and WAN 2.2 14B on the Qualcomm Hexagon NPU. SD1.5, SDXL, Flux, Z-Image, Anima, Qwen Image 2.1, Krea 2 & MOSS Image. Inpainting, outpainting, ControlNet, LoRA, IP-Adapter & LivePortrait. Fully offline, no server, no account.

    GitHub · Kotlin · 270 stars · 22 forks · +33 stars in 24 hours · Trending score 2.64

  2. 2
    lemonade-sdk/lemonade

    Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk

    GitHub · C++ · 6,253 stars · 571 forks · +8 stars in 24 hours · Trending score 2.23

  3. 3
    ROCm/FastFlowLM

    Run LLMs on AMD Ryzen™ AI NPUs in minutes; purpose-built and deeply optimized for the AMD NPUs.

    GitHub · C++ · 2,068 stars · 181 forks · +10 stars in 24 hours · Trending score 2.04

  4. 4
    ayanoby/hexanima

    Offline anime image generation on the Snapdragon 8 Gen 1 NPU (Hexagon V69), no root. Android app.

    GitHub · C++ · 29 stars · 6 forks · +4 stars in 24 hours · Trending score 1.45

  5. 5
    jia1217/vigenflow

    VigenFlow runs generative diffusion models fully on-device using the AMD Ryzen AI NPU.

    GitHub · C++ · 29 stars · 4 forks · +4 stars in 24 hours · Trending score 1.25

  6. 6
    jwkim04/tesseract-npu

    A full-stack, open-source NPU for LLM inference.

    GitHub · C++ · 25 stars · 3 forks · +2 stars in 24 hours · Trending score 1.24

  7. 7
    microsoft/ai-dev-gallery

    An open-source project for Windows developers to learn how to add AI with local models and APIs to Windows apps.

    GitHub · C# · 1,519 stars · 229 forks · +1 stars in 24 hours · Trending score 1.21

  8. 8
    ModelEngine-Group/unified-cache-management

    Persist and reuse KV Cache to speedup your LLM.

    GitHub · C++ · 360 stars · 138 forks · +2 stars in 24 hours · Trending score 1.18

  9. 9
    justADeni/intel-npu-llm

    A simple Python script for running LLMs on Intel's Neural Processing Units (NPUs)

    GitHub · Python · 52 stars · 5 forks · +4 stars in 24 hours · Trending score 1.15

  10. 10
    ModelCloud/GPTQModel

    LLM model quantization (compression) toolkit with HW acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU, Tenstorrent, Huawei Ascent NPU, and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.

    GitHub · Python · 1,294 stars · 220 forks · +2 stars in 24 hours · Trending score 1.11

  11. 11
    zmxhot/InstantCaption

    Free offline AI translator for Android: low-latency speech translation, live captions and floating subtitles powered by local LLMs. 免费离线 AI 同声传译 · 本地大模型 · 低延迟字幕。NPU integration in source; public APK uses CPU models.

    GitHub · Java · 28 stars · 1 forks · +1 stars in 24 hours · Trending score 0.86

  12. 12
    1bit-MONSTER/engine

    One binary to rule them all: model-agnostic local LLM inference for AMD Strix Halo (Ryzen AI MAX+ 395) on Linux. Radeon 8060S iGPU (gfx1151) via HRX + our HIP kernels, XDNA 2 NPU via our NPU runtime, inside Lemonade Server with an OpenAI-compatible API. Qwen3.8, ZAYA1, BitNet b1.58, any GGUF. Apache-2.0.

    GitHub · C++ · 10 stars · 2 forks · +1 stars in 24 hours · Trending score 0.69

  13. 13
    shen-shanshan/cs-self-learning

    This repo is used for archiving my notes, codes and materials of cs learning.

    GitHub · Jupyter Notebook · 103 stars · 6 forks · 0 stars in 24 hours · Trending score 0.68

  14. 14
    istitov/stuff

    Useful Gentoo overlay: curated ebuilds, AI, tools & science

    GitHub · Shell · 48 stars · 22 forks · +1 stars in 24 hours · Trending score 0.55

  15. 15
    oneclickvirt/oneclickvirt

    Universal Virtualization Management Platform 可扩展的通用虚拟化管理平台,支持 Proxmox VE / LXD (GPU) / Incus (GPU) / Docker / Podman / Containerd / Qemu / Kubevirt

    GitHub · Go · 384 stars · 61 forks · 0 stars in 24 hours · Trending score 0.40

  16. 16
    Xilinx/XRT

    Run Time for AIE and FPGA based platforms

    GitHub · C++ · 695 stars · 553 forks · 0 stars in 24 hours · Trending score 0.33

  17. 17
    Hal0ai/hal0

    Open-source self-hosted home AI inference platform for AMD Strix Halo — multi-backend slots, OpenAI-compatible gateway, Vue 3 + FastAPI + systemd.

    GitHub · Python · 87 stars · 12 forks · 0 stars in 24 hours · Trending score 0.32

  18. 18
    datawhalechina/torch-rechub

    A Lighting Pytorch Framework for Recommendation Models, Easy-to-use and Easy-to-extend.

    GitHub · Jupyter Notebook · 1,243 stars · 162 forks · 0 stars in 24 hours · Trending score 0.30

  19. 19
    gregordinary/ggml-rocket

    Drop-in ggml backend for Rockchip NPUs: offloads llama.cpp/whisper.cpp prefill to the RK3588 NPU

    GitHub · C++ · 28 stars · 4 forks · 0 stars in 24 hours · Trending score 0.28

  20. 20
    Kreuzhofen/hk-npu-studio

    HK NPU STUDIO — Local AI for Snapdragon® PCs. NPU-accelerated image generation for Windows 11 ARM64. Featuring Phoenix Boost.

    GitHub · Python · 19 stars · 1 forks · 0 stars in 24 hours · Trending score 0.24

  21. 21
    FluidInference/mobius

    Your models on any xPU

    GitHub · Python · 98 stars · 26 forks · 0 stars in 24 hours · Trending score 0.24

  22. 22
    microsoft/WindowsML

    Official repo for Windows ML - Microsoft's high-performance local AI inferencing framework for Windows.

    GitHub · C# · 52 stars · 6 forks · 0 stars in 24 hours · Trending score 0.23

  23. 23
    Henley04/SXSEditor

    Create&Synthesis&Modify your AI-powered Virtual Singer. Powered by SoulX-Singer

    GitHub · JavaScript · 19 stars · 1 forks · 0 stars in 24 hours · Trending score 0.22

  24. 24
    Atomic-Germ/OpenFlowLM-Next

    Active and open development fork of FastFlowLM.

    GitHub · C++ · 44 stars · 18 forks · 0 stars in 24 hours · Trending score 0.20