Starred repositories
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
Experimental Raven Ridge iGPU CU unlock: 8 → 11 CUs with a scoped amdgpu patch
Unlock full speed FP16 tensor core of NVIDIA Turing GPUs
Your GeForce runs AI at half speed. This fixes it for 20/30/40 series cards. Up to 2× FP16 / BF16 / TF32 tensor throughput
AUR packages for llama-cpp Linux binaries for various targets
Cross-platform Xcode replacement. Build and deploy iOS apps with SwiftPM on Linux, Windows, macOS.
A modern, polished GTK4/Libadwaita graphical wrapper for ryzenadj (AMD power management adjustment tool).
Embedded controller for the IK Multimedia Tonex One, Tonex Pedal, and Valeton GP5 guitar pedals
ReFS FUSE driver and tools for Linux, macOS, BSD, Windows, Illumos, etc. License: GPLv2+
This free RAM cleaner uses native Windows features to optimize memory areas. It's a compact, portable, and smart application.
One llama.cpp flag unlocks +33-39% decode speed for Qwen3.8-27B on consumer GPUs. The MTP head already ships inside your GGUF. Recipe, paired benchmarks, probe tool.
GLM-5.3-Flash × J-Space capability realization — benchmark presentation of the J-Space Cognition Suite
Lightweight header-only C++20 enum and typename reflection
A curated suite of AI agent skills for systems and low-level programming with C/C++, Rust, and Zig toolchains, covering compilers, debuggers, profilers, build systems, sanitizers, and binary analysis
Open source alternative to Semrush and Ahrefs
victortassinari / FossFLOW
Forked from leonj1/OpenFLOWMake beautiful isometric infrastructure diagrams
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
Clone a voice from a few minutes of audio and generate speech locally: Qwen3-TTS fine-tuning pipeline with CLI and web UI
Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.
SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.
PrismML-Eng / llama.cpp
Forked from ggml-org/llama.cppLLM inference in C/C++
SSD-streaming inference engine for giant MoE models (Rust + CUDA). GLM 5.2 743B at 2 tok/s and Hy3 295B at 7 tok/s on two consumer 16GB GPUs. Zero-config multi-GPU: measures PCIe bandwidth, places …
A library for writing reactive single page web apps