MEMORY MANAGEMENT

Open benlahouel-sketch opened this issue 1 month ago • 2 comments

Between version v0.4.0 and version v0.5.1 the VRAM use is gone up by 3%. Please advise. Thanks.

Dec 21 '25 03:12 benlahouel-sketch

Can I get your GPU, OS, and workflow, and at least the VRAM model loading stats

Dec 21 '25 10:12 rattus128

Platform: Linux ** Python version: 3.10.12 (main, Nov 4 2025, 08:48:33) [GCC 11.4.0]

Total VRAM 16073 MB, total RAM 64215 MB pytorch version: 2.9.0+cu128 Set vram state to: NORMAL_VRAM Device: cuda:0 NVIDIA GeForce RTX 4060 Ti : cudaMallocAsync Using async weight offloading with 2 streams Enabled pinned memory 61004.0 working around nvidia conv3d memory bug. Using pytorch attention Python version: 3.10.12 (main, Nov 4 2025, 08:48:33) [GCC 11.4.0] ComfyUI version: 0.5.1 ComfyUI frontend version: 1.34.9

Dec 22 '25 16:12 blahouel