kijai/ComfyUI-MemoryVisualization

A simple node that can dynamically adjust the reserved memory of a workflow in real-time, used to avoid the utilization of shared memory.

This custom_node for ComfyUI adds one-click "Virtual VRAM" for any UNet and CLIP loader as well MultiGPU integration in WanVideoWrapper, managing the offload/Block Swap of layers to DRAM *or* VRAM to maximize the latent space of your card. Also includes nodes for directly loading entire components (UNet, CLIP, VAE) onto the device you choose

A universal swap node that supports ComfyUI native workflow, allowing 4_6G users to experience Klein9B or other large models

The htop for LLM inference see exactly where every GB of VRAM goes and get measured quantization savings.

🔥 Real-time NVIDIA GPU dashboard

Real-time terminal power monitor — CPU · GPU · RAM wattage dashboard Visibility

VRAM-efficient MiniMax H3 for ComfyUI: QKV/RoPE/MLP activation chunking, automatic OOM chunk reduction, and CK/SLA/Sol/Hybrid attention for SM75 and SM80+ GPUs.

A powerful set of tools for ComfyUI

A custom node for ComfyUI that dynamically manages RAM usage by intelligently controlling cache purging based on available system memory.