NUMA-Aware Contention-Free Dynamically-Auto-Tuning Bash-Native Streaming Parallelization Engine

RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink

A proxy for minimax-m2, enabling interleaved thinking, and tool calls.

llama-benchy - llama-bench style benchmarking tool for all backends

glider is a forward proxy with multiple protocols support, and also a dns/dhcp server with ipset management features(like dnsmasq).

Matrix multiplication schemes

Proxmox VE Helper-Scripts (Community Edition)

A powerful data recovery utility for Linux with many advanced features based on Scott Dwyer's HDDSuperClone.

A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).

Web UI for training and running open models like Gemma 4, Qwen3.5, DeepSeek, gpt-oss locally.

⚔️Python Rate-Limiter using Leaky-Bucket Algorithm Family

Windows for ARM in a Docker container.

A simple, single binary, message queue. Supports HTTP/2 and Redis Protocol.

Training LLMs with QLoRA + FSDP

Windows inside a Docker container.

PyPy is a very fast and compliant implementation of the Python language.

Foundational Models for State-of-the-Art Speech and Text Translation

A collection of GPT system prompts and various prompt injection/leaking knowledge.

Useful scripts to get out of Google Photos

Remote GUI for Transmission torrent daemon

🐑 A SOCKS5 Proxy server written in Rust

📋 A list of open LLMs available for commercial use.

Fast, light, simple Docker containers & Linux machines

A python-based chatbot for Mattermost (http://www.mattermost.org).

An app that connects to a Ricoh GR iii (or iiix) and downloads all images

OSINT for YouTube made simple.

Like Python's ZipFile module, except it works as a generator that provides the file in many small chunks.

What the f*ck Python? 😱