Pre-built wheels for llama-cpp-python across platforms and CUDA versions

RTX 5090 & RTX 5060 Docker container with PyTorch + TensorFlow. First fully-tested Blackwell GPU support for ML/AI. CUDA 12.8, Python 3.11, Ubuntu 24.04. Works with RTX 50-series (5090/5080/5070/5060) and RTX 40-series.

Easy recipes to speed up latency of Flux, QwenImage, and LTX-2 with NVFP4 and MXFP8 on Blackwell.

EN: An overfitted SD prompt engine with severe "aesthetic snobbery," forcibly transforming mundane ideas into professional-grade physical rendering instructions. CN: 一个具备“审美洁癖”的过拟合提示词引擎，强行将平庸构思纠偏为具备极致物理质感的工业级渲染指令。

Real-time NVIDIA GPU command capture, decoding, and visualization

AI kernal/api/ui multi-agent orchestration

兼容50系显卡的SoftVC VITS Singing Voice Conversion-50Series-CUDA13-Pytorch2.10

HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency

Japanese GUI + Whisper auto-transcription for CosyVoice. RTX 5090 tested.

Complete installation guide for ComfyUI-Hunyuan3DWrapper on NVIDIA Blackwell GPUs (RTX 5070 Ti, 5080, 5090) Covers custom_rasterizer manual compilation for sm_120 / compute_120 architecture.

Windows Native + Blackwell GPU (RTX 50 series) support fork. No flash-attn required, single-GPU optimized, one-click launch.

vLLM installation for NVIDIA DGX Spark with Blackwell GB10 GPUs

"The evolution of a 2-year journey into AI. From Python to C++, AlyssaNet is a multi-LLM cognitive framework designed for emotional emergence and permanent memory. (my life's project btw)"