Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

📹 Recorder | Open-source web app to record screen and camera directly in your browser | No installation required | No tracking | Fully local | 🚀

AIOS: LLM Agent Operating System

An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.

Nosh is Not a Shell, but a Library to Implement CLIs for Networking Devices

collection of benchmarks to measure basic GPU capabilities

Meta's Time libraries

macOS multi-mouse & multi-external display assignment for complex screen and peripheral workstations.

A tool that allows you to convert NMAP results to html, csv, json, markdown, graphviz (dot), sqlite, excel and d2-lang. Simply put it's nmap converter.

NVIDIA Data Center GPU Manager (DCGM) is a project for gathering telemetry and measuring the health of NVIDIA GPUs

NVIDIA GPU metrics exporter for Prometheus leveraging DCGM

SSH3: faster and rich secure shell using HTTP/3, checkout our article here: https://arxiv.org/abs/2312.08396 and our Internet-Draft: https://datatracker.ietf.org/doc/draft-michel-ssh3/

An open source, self-hosted implementation of the Tailscale control server

Open Overleaf/ShareLaTex projects in vscode, with full collaboration support.

Ancillary open source software to support confidential computing on NVIDIA GPUs

Qdrant - High-performance, massive-scale Vector Database for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

Port of OpenAI's Whisper model in C/C++

A minimal programming example for a chat server

An OpenConfig reference device implementation

PruningRadixTrie - 1000x faster Radix trie for prefix search & auto-complete

C Library for NVM Express on Linux

local-first semantic code search engine

NVMeVirt: A Versatile Software-defined Virtual NVMe Device

Userspace eBPF VM