a8nova/adreno-llms

Converted TFLite Model Zoo for Android with LiteRT CompiledModel GPU acceleration

Demonstration of running a native LLM on Android device.

Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code

Android native AI inference library, bringing text, image, video, STT, TTS inference

Samsone: A Family of Open Small Audio Language Models for On-Device Inference

GPU-Accelerated AI/ML Inference

MobiInfer runs 35B-A3B-class MoE models fully on-device on the Qualcomm Hexagon NPU, streaming experts from flash with lookahead scheduling (LES) and DSpark speculation.

A repo for llm on ncnn

Quantization, kernels, runtime and inference engine for mobiles, wearables, smart home and robots.