Get current GPU status: VRAM usage, utilization, temperature, and power draw.

List all processes currently using the GPU (compute and graphics).

See exactly which models are loaded on the GPU, their sizes, and devices. Requires the GPU optimizer inside ComfyUI.

Automatically free VRAM by offloading models to CPU. Offloads largest models first until threshold is met. Set target_free_mb to specify how much VRAM to free, or 0 for auto.

Move a specific model from GPU to CPU by index. Use gpu_memory_map to see model indices. Pass -1 to offload the largest model.

Set the VRAM auto-management threshold (50-95%). When VRAM exceeds this, models are automatically offloaded to CPU.

Enable or disable automatic VRAM management. When enabled, the optimizer automatically offloads models when VRAM exceeds the threshold.

Unload ALL models from VRAM inside ComfyUI and empty the CUDA cache. More thorough than vram_flush.

Check if ComfyUI is running, responding, and whether the GPU optimizer is active.

Start ComfyUI with GPU optimizer. Automatically reserves VRAM headroom for system stability.

Stop ComfyUI and free VRAM.

Restart ComfyUI: stop, flush VRAM, start fresh with GPU optimizer.

Kill ALL GPU compute processes and free VRAM. Use with caution.

Read the last N lines of the ComfyUI log.