Cross-platform installer for Triton and SageAttention on ComfyUI. Simplifies GPU-accelerated inference setup for Windows users with automated dependency management and RTX 5090 support.

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.

Bio-inspired LLM architecture achieving ~5x reduction in Attention FLOPs via Context-Aware Target-Sparsity Routing. Features custom OpenAI Triton kernels optimized for RTX 5090, delivering 1.41M tok/s throughput.

A high-performance local AI pipeline for restoring VHS audio, transcribing with Whisper, and translating subtitles using NLLB-200.

Autonomous node manager for Vast.ai - Dynamic pricing, GPU monitoring, auto-bidding & watchdog for dual RTX 5090 compute rigs. Production-ready with REST API, web dashboard, and systemd integration.

⚡ Compare AI models by Accuracy × Cost × Carbon — RTX 5090 benchmarks reveal 4-bit quantization wastes energy on small models

Lightweight GPU & CPU system tray monitor for NVIDIA GPUs (RTX 5090, RTX 6000, RTX 4090, RTX 3090, Tesla, TCC mode). Real-time power, temperature, VRAM & CPU usage badges. Works where HWMonitor, GPU-Z & MSI Afterburner fail.

This is a simulation of the Founders Edition 5090 Nvidia GPU:

Pre-built onnxruntime-gpu 1.24.1 with Blackwell sm_120 CUDA kernels (RTX 5090/5080/5070)

Enterprise-grade Sovereign AI Stack optimized for NVIDIA Blackwell (sm_120) & vLLM. Features 256K context window, 5.8k tok/s prefill, and integrated observability via Langfuse.