Unified management and routing for llama.cpp, MLX and vLLM models with web dashboard.

A daemon that automatically manages the performance states of NVIDIA GPUs.

Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc

LLM inference in C/C++

Thai natural language processing in Python

Compile Time Regular Expression in C++

Reliable & unreliable messages over UDP. Robust message fragmentation & reassembly. P2P networking / NAT traversal. Encryption.

ARCHIVED / Forum Thread: https://osu.ppy.sh/forum/t/270446/ / (Yes, I know that the code is awful. This was more or less my first bigger code project and had to be migrated from VB to C#)

JSON for Modern C++

macros support for VS Code

An all-in-one Docker image for deep learning. Contains all the popular DL frameworks (TensorFlow, Theano, Torch, Caffe, etc.)

Convert ROS Bag package to MP4 File format

An Open Source Machine Learning Framework for Everyone