Port of Nvidia LocateAnything-3B on ggml

Systematic 24-hour benchmark study of Qwen3.6-27B inference on dual NVIDIA RTX PRO 6000 Blackwell SM120 (TP=2). 8 experiments comparing repne/vllm fork vs upstream vLLM across FP8/BF16/NVFP4/Q8_0 q…

7.67× LoRA / 8.35× Full FT speedup for Qwen3.5 (0.8B–27B) on NVIDIA DGX Spark — wall-clock parity with rented H100. Lossless within BF16. Three-command interactive wizard handles model picker, data…

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

eBPF-powered silent observer for containerized runtimes, built for malware analysis sandboxes and Agentic AI monitoring.

Tiny, Fast, and Deployable anywhere — automate the mundane, unleash your creativity

Fulloch - The Fully Local Home Voice Assistant

Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps

A Streamlit app for generating high-quality Q&A training datasets from text and PDFs, leveraging Gemini, Claude, and OpenAI for LLM fine-tuning.

SOTA search powered LLM

Distributed Reinforcement Learning for LLM Fine-Tuning with multi-GPU utilization

The official API server for Exllama. OAI compatible, lightweight, and fast.

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.

ControlNet++: All-in-one ControlNet for image generations and editing!

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

A command line tool and library for transferring data with URL syntax, supporting DICT, FILE, FTP, FTPS, GOPHER, GOPHERS, HTTP, HTTPS, IMAP, IMAPS, LDAP, LDAPS, MQTT, MQTTS, POP3, POP3S, RTSP, SCP,…

EGo is an open-source SDK that enables you to develop your own confidential apps in the Go programming language.

The missing link between spreadsheets and data visualization

Parse and Query log files as time series

Golang implementation of the Raft consensus protocol

Lightweight, fast and dependency-free Cron expression parser (due checker, next/prev due date finder), task runner, job scheduler and/or daemon for Golang (tested on v1.13+) and standalone usage. I…

S3 FileSystem (fs.FS) implementation

Generative Art in Go

Terminal string styling for go done right, with full and painless Windows 10 support.

Concurrency patterns in Go

Make bootable Linux disk images (ab)using Docker

A fast and simple JWT implementation for Go

k-means clustering algorithm implementation written in Go