Git - the stupid content tracker - This is a publish-only "broken out" repository and all pull requests are ignored. Please follow Documentation/SubmittingPatches procedure for any of your improvem…

LLM inference in C/C++

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

A tiny Alpine based docker image to quickly setup an L2TP over IPsec VPN client w/ PSK.

run DeepSeek-R1 GGUFs on KTransformers

Sample benchmark demonstrating the VK_NV_cooperative_vector extension

Sample benchmark demonstrating the VK_KHR_cooperative_matrix extension

A VPN Designed for Lossy Links, with Build-in Forward Error Correction(FEC) Support. Improves your Network Quality on a High-latency Lossy Link.

A Tunnel which Turns UDP Traffic into Encrypted UDP/FakeTCP/ICMP Traffic by using Raw Socket,helps you Bypass UDP FireWalls(or Unstable UDP Environment)

Library for specialized dense and sparse matrix operations, and deep learning primitives.

A parser for SQLite create table sql statements.

Gravity Programming Language

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

Universal cross-platform tokenizers binding to HF and sentencepiece

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

MindSpore is a new open source deep learning training/inference framework that could be used for mobile, edge and cloud scenarios.

Tencent Hunyuan A13B (short as Hunyuan-A13B), an innovative and open-source LLM built on a fine-grained MoE architecture.

An open-source AI agent that brings the power of Gemini directly into your terminal.

heterogeneity-aware-lowering-and-optimization

High-efficiency floating-point neural network inference operators for mobile, server, and Web

LiteRT, successor to TensorFlow Lite. is Google's On-device framework for high-performance ML & GenAI deployment on edge platforms, via efficient conversion, runtime, and optimization

An app that brings language models directly to your phone.

A frontend for running models on mobile or connecting to your preferred API providers.

Running any GGUF SLMs/LLMs locally, on-device in Android

Inference RWKV v5, v6 and v7 with Qualcomm AI Engine Direct SDK

A Go agent harness and service framework