Write and run custom C kernels for Intel Core Ultra NPUs
-
Updated
Oct 8, 2026 - C
#
npu-acceleration
Here are 10 public repositories matching this topic...
Open-source production-ready mobile server-less AI apps. Clone, customize, and ship on Android & iOS with MLange.
edge-computing npu edge-ai on-device-ml on-device-ai edge-tts vibe-coding vibecoding on-device-inference on-device-llm npu-acceleration
-
Updated
Jul 18, 2026 - Swift
Production Android AI with ExecuTorch 1.0 - Deploy PyTorch models to mobile with NPU acceleration and 50KB footprint
kotlin-android java-android pytorch-mobile pytorch-android edge-inference android-ai real-time-ai executorch arm-optimization mobile-ml privacy-preserving-ai mobile-deployment on-device-inference npu-acceleration executorch-1-0 qualcomm-hexagon lightweight-ml cpu-gpu-npu meta-executorch
-
Updated
Nov 14, 2025 - Python
Real-time SAM2 segmentation on edge devices - 40x faster C++ inference with ONNX Runtime for iOS/Android deployment
computer-vision tensorrt embedded-ai edge-ai edge-deployment onnx-runtime cpp-inference zero-shot-segmentation ios-deployment sam2 arm-optimization lightweight-ai on-device-inference edgetam real-time-segmentation npu-acceleration mobile-segmentation picosam android-edge prompt-segmentation
-
Updated
Nov 14, 2025 - C++
Open-source implementation for Airoha NPU. WIP, do not use.
-
Updated
Oct 5, 2026 - C
Face authentication system for Linux using OpenVINO/ONNX written in Rust
linux rust authentication face face-recognition face-detection pam-module openvino npu npu-acceleration
-
Updated
Oct 7, 2026 - Rust
Eklavya: A local-AI "Learning OS" designed to eliminate academic burnout. Powered by AMD Ryzen AI to deliver hyper-personalized, privacy-first cinematic education. +3
-
Updated
Feb 20, 2026 - JavaScript
Whisper encoder on the AMD XDNA1 NPU (Ryzen AI, Phoenix) under Linux — open toolchain only: XRT, MLIR-AIE/IRON, peano. Includes an HTTP service speaking whisper.cpp's contract.
-
Updated
Jul 26, 2026 - Python
A vibe-coded Neural Processing Unit design bundled with a Python testing suite. The design needs extensive testing.
-
Updated
May 29, 2026 - SystemVerilog
An optimized Softmax approximation framework for NPU-accelerated LLM inference. It features a non-uniform segmentation strategy and variable-degree polynomial approximation optimized via Particle Swarm Optimization (PSO).
-
Updated
Sep 24, 2026 - Python
Add this topic to your repo
To associate your repository with the npu-acceleration topic, visit your repo's landing page and select "manage topics."