Sign in

Repository Index

65,264 visible repositories in the index

Tags: All Tags
Tags

A repository shows when it has any selected Tag.

Filters

Filters

Clear all filters

361–384 of 472 · Most stars

Pure-Rust inference engine for Qwen GGUF models (Qwen3 to Qwen3.8, dense and MoE up to 770B+). CUDA and Vulkan (NVIDIA, AMD), hybrid CPU+GPU experts, MTP speculative decoding, OpenAI and Anthropic compatible server. Up to ~1.7x llama.cpp decode on a 12 GB RTX 3060.

:ghost: GhostText plugin for Neovim with zero dependencies :tada: Supports neovim running inside WSL too! :partying_face: Windows/Linux/macOS supported out-of-the-box! :smile: (Other OSes need python3.6+ installed)

TranslatedA lightweight floating desktop monitor for Windows: battery power consumption and runtime, CPU/GPU/memory usage and power consumption, network speed, real latency, and disconnection alerts. Native C++ / Direct2D, with mini mode using about 0.1% CPU.

  • battery
  • cpp
  • desktop-widget
  • direct2d