Havuz

audio.cpp, ggml tabanlı ortak bir C++ runtime üzerinden farklı ses modellerinde yerel inference çalıştırmayı sağlayan bir framework’tür.

Neden yükseliyor · 96 günlük yaşına rağmen 3067 yıldızın yanı sıra son 28 günde 272 commit ve 18 farklı yazar görünüyor; bu, README’deki geniş model desteğinin yanında kayda değer bir geliştirme hareketliliğine işaret ediyor. README performans iyileştirmeleri ve yeni model desteği bildiriyor, ancak bu kıyasların bağımsız doğrulaması verilen bilgilerden anlaşılamıyor.

37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cp

Speech synthesis, speech recognition and voice activity detection for voice conversation, in C++ on ggml: Qwen3-TTS, Irodori-TTS, Qwen3-ASR,

Edit photos by describing the change, on your own GPU. A free, open-source alternative to Nano Banana and ChatGPT image editing: photos stay

Bilingual English and Mandarin text to speech in C++ and GGUF. Voice design, cloning, direction and experimental voice conversion. Vulkan ba

Unofficial RPCS3 port for PlayStation 5 — run PS3 games as a native PS5 homebrew title. Alpha 0.1.0 source release.

Fast, offline OCR for Node.js & C++. PP-OCRv6 with Core ML / WebGPU hardware acceleration — recognize text in images with confidence scores

FunASR.NET：.NET 10 纯 C# 普通话 ASR/TTS，CPU SIMD、可选 Vulkan，浏览器和 SIP 音频示例，中文文档与真实原版测速对照。

Smart inference engine that adapts to your hardware to run models faster, even when they don’t fit in memory

AI coding agent harness for any hardware, local or cloud (OpenAI-compatible engines). Tuned for AMD Strix Halo: Qwen3.8 125B on the iGPU, NP

An MCP server for RenderDoc: Empowering AI assistants to analyze GPU frame captures and debug graphics pipelines.

Evidence-backed AMD Strix Halo local-AI setup and benchmarks: Qwen3.8, Ollama, llama.cpp, Vulkan/ROCm, large GGUFs, and cross-OEM results.

Model Dispatch and Memory Allocator: an LLM inference engine for the hardware you own. Custom CPU, ROCm, Vulkan, CUDA, Metal and Level Zero

Run Windows and Linux programs on Windows, Linux and Android. A user-mode NT and Linux kernel emulator with WHP/KVM acceleration.

Native TypeScript game engine — compiles to Metal, DirectX 12, Vulkan, and OpenGL

Generate textured, segmented and rigged GLB assets entirely on your own GPU.

Press a key, speak, text lands at your cursor. Press another, get a spoken answer. Local-first, lightweight voice dictation and assistant fo

Self-hosted, browser-based AI dungeon RPG, fully local on an AMD Strix Halo APU: narrator + per-character agents on one local LLM (Gemma 4 2

Winning Qwen and DeepSeek setups for AMD Strix Halo: pinned Ansible recipes and matched benchmarks on a 128 GiB Ryzen AI Max+ 395 / Radeon 8

llama.cpp/ik_llama.cpp launcher: loads big MoE models across mismatched multi-GPU rigs by exact VRAM math.

Self-hosted LLM/RAG stack in one command — AMD Strix Halo / x86_64 (ROCm/Vulkan, Docker Compose)

Local AI engine in Rust: run GGUF and ONNX models for chat, vision, speech and embeddings on your own GPU, RAM and CPU, with automatic place

LLM inference engine for AMD RDNA4 — Rust + Vulkan compute shaders, gguf & native FP8.

Real-time Gaussian splatting SDKs for Android/Vulkan, iOS/Metal and React Native, sharing a C++17 engine.

A Vulkan-based rendering backend for Manim, built with Python at first but C now. Helping you to preview the rendering result earlier.

A local LLM server built for concurrent work. Drop-in replacement for Ollama and/or OpenAI and Ollama APIs on one port. Requests that share

renew engine: an AI-first game engine in Rust, built to be operated. Bit-deterministic fixed-timestep simulation in Q47.16 fixed point, Vulk

Local LLMs that run lean, load instantly and keep getting smarter. A from-scratch runtime + model format in Zig: zero-copy mmap, CPU/CUDA/Vu

Speech-first inference runtime in Rust — TTS / ASR / speech-to-speech / VC / speaker ID / VAD. An ONNX Runtime alternative that loads GGUF &