shadeMe
Follow
Lists (16)
Stars
Intelligent Mixture-of-Models Router for Efficient LLM Inference
A hardware monitoring project that provides high-performance tools, Python libraries, and C++ header files for retrieving and displaying detailed hardware information.
State of the art sorting and segmented sorting, including OneSweep. Implemented in CUDA, D3D12, and Unity style compute shaders. Theoretically portable to all wave/warp/subgroup sizes.
Share your Immich photos and albums in a safe way without exposing your Immich instance to the public.
Lightweight network IP scanner written in Go. With notifications, history, export to Grafana
Distributed LLM inference. Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.
Automatic CPU speed & power optimizer for Linux
Efficient Triton Kernels for LLM Training
Install NixOS everywhere via SSH [maintainers=@Mic92 @Lassulus @phaer @Enzime @a-kenji]
music library manager and MusicBrainz tagger
Self-Hosted, Personal Music Server, designed for collectors and music maniacs
Utility for mass-downloading LRC synced lyrics for your offline music library.
LRCLIB server written in Rust with Axum and SQLite3 database
Unlock the full potential of music: Stream effortlessly with one app!
A Material 3 YouTube Music client for Android
Lightweight Music Server. Access your self-hosted music using a web interface.
Design circuit boards with code! ✨ Get software-like design reuse 🚀, validation, version control and collaboration in hardware; starting with electronics ⚡️
OpenSource GPU, in Verilog, loosely based on RISC-V ISA
AudioMuse-AI leverages Librosa and TensorFlow for sonic analysis, powering similar song discovery and smart playlists within Jellyfin and Navidrome API.
More routines for operating on iterables, beyond itertools
A lightweight mac status bar development port monitor
Amperfy is an iOS/iPadOS/macOS app to play songs from an Ampache or Subsonic server
Simple bash script to rebalance pool data between all mirrors when adding vdevs to a pool.
A minimal tensor processing unit (TPU), inspired by Google's TPU V2 and V1
The quickest way to rename acquired shows and movies for use in your media center.
Tilus is a tile-level kernel programming language with explicit control over shared memory and registers.
A modern Jellyfin client built with Expo