The latest version takes twice as long to complete.

[m8rr]

I was trying to test comfy-aimdo version: 0.4.7, but it's running twice as slow on the latest version of ComfyUI-MemoryVisualization. It was working fine with the version from a few days ago (the version that didn't have a pagefile).
windows11

[INFO] setup plugin alembic.autogenerate.schemas
[INFO] setup plugin alembic.autogenerate.tables
[INFO] setup plugin alembic.autogenerate.types
[INFO] setup plugin alembic.autogenerate.constraints
[INFO] setup plugin alembic.autogenerate.defaults
[INFO] setup plugin alembic.autogenerate.comments
[INFO] Setting output directory to: E:\output
[INFO] Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_mxfp8', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'gemv_awq_w4a16', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'quantize_svdquant_w4a4', 'scaled_mm_mxfp8', 'scaled_mm_nvfp4', 'scaled_mm_svdquant_w4a4', 'stochastic_rounding_fp8']}
[INFO] Found comfy_kitchen backend triton: {'available': True, 'disabled': True, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8']}
[INFO] Found comfy_kitchen backend cuda: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'gemv_awq_w4a16', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'quantize_svdquant_w4a4', 'scaled_mm_nvfp4', 'scaled_mm_svdquant_w4a4', 'stochastic_rounding_fp8']}
[INFO] Checkpoint files will always be loaded safely.
[INFO] Total VRAM 12282 MB, total RAM 32085 MB
[INFO] pytorch version: 2.12.0+cu130
[INFO] Enabled fp16 accumulation.
[INFO] Set vram state to: NORMAL_VRAM
[INFO] Device: cuda:0 NVIDIA GeForce RTX 4070 SUPER : cudaMallocAsync
[INFO] Using async weight offloading with 2 streams
[INFO] Enabled pinned memory 12834.0
[INFO] Using sage attention
aimdo: src-win/cuda-detour.c:38:INFO:aimdo_setup_hooks: installing 6 hooks
aimdo: src-win/cuda-detour.c:28:DEBUG:install_hook_entries: hooks successfully installed
aimdo: src-win/shmem-detect.c:80:INFO:comfy-aimdo WDDM adapter match: NVIDIA GeForce RTX 4070 SUPER runtime_luid=00000000:0000d70a dxgi_luid=00000000:0000d70a
aimdo: src/control.c:240:INFO:comfy-aimdo inited for GPU: NVIDIA GeForce RTX 4070 SUPER (VRAM: 12281 MB)
[INFO] DynamicVRAM support detected and enabled
[INFO] Python version: 3.13.12 (tags/v3.13.12:1cbe481, Feb  3 2026, 18:22:25) [MSC v.1944 64 bit (AMD64)]
[INFO] ComfyUI version: 0.22.0
[INFO] comfy-aimdo version: 0.4.7
[INFO] comfy-kitchen version: 0.2.9
[INFO] Setting temp directory to: E:\output\temp
[INFO] comfyui-frontend-package version: 1.44.19
[INFO] comfyui-workflow-templates version: 0.9.91
[INFO] comfyui-embedded-docs version: 0.5.1
[INFO] comfy-kitchen version: 0.2.9
[INFO] comfy-aimdo version: 0.4.7
[INFO] [Prompt Server] web root: D:\AI\ComfyUI_windows_portable\python_embeded\Lib\site-packages\comfyui_frontend_package\static
[INFO] Asset seeder disabled
[INFO] ComfyUI-GGUF: Allowing full torch compile

It works fine with ANIMA safetensor, but there is an issue with LTX2.3 and WAN GGUF rattus128/ComfyUI-GGUF node on the dynamic-vram branch.

with ComfyUI-MemoryVisualization

[INFO] Requested to load LTXAV
[INFO] Model LTXAV prepared for dynamic VRAM loading. 16915MB Staged. 0 patches attached. Force pre-loaded 608 weights: 6567 KB.
100%|████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:41<00:00,  8.35s/it]
[INFO] 0 models unloaded.
[INFO] Model LTXAV prepared for dynamic VRAM loading. 16915MB Staged. 0 patches attached. Force pre-loaded 608 weights: 6567 KB.
100%|████████████████████████████████████████████████████████████████████████████████████| 3/3 [00:43<00:00, 14.40s/it]
[INFO] Requested to load AudioVAE

without ComfyUI-MemoryVisualization

[INFO] Requested to load LTXAV
[INFO] Model LTXAV prepared for dynamic VRAM loading. 16915MB Staged. 0 patches attached. Force pre-loaded 608 weights: 6567 KB.
100%|████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:24<00:00,  4.83s/it]
[INFO] 0 models unloaded.
[INFO] Model LTXAV prepared for dynamic VRAM loading. 16915MB Staged. 0 patches attached. Force pre-loaded 608 weights: 6567 KB.
100%|████████████████████████████████████████████████████████████████████████████████████| 3/3 [00:27<00:00,  9.19s/it]
[INFO] Requested to load AudioVAE

[Ph0rk0z]

You know.. I noticed this sometimes. Having the visualizer open increased generation time. I was able to fix by refreshing the page. It would even happen when I was watching it visualize APi workflows. But then for some reason it magically went away.

[m8rr]

polling interval 5s (looking at the ComfyUI tab)
5/5 [00:26<00:00, 5.28s/it]

100ms (ComfyUI tab)
5/5 [02:10<00:00, 26.10s/it]

100ms (google tab)
5/5 [00:31<00:00, 6.32s/it]

Initial docking support version (b3cae03)
100ms (ComfyUI tab)
5/5 [00:24<00:00, 4.87s/it]

It could be a browser issue or something else, but anyway, there seems to be a problem with the latest version.
Microsoft Edge is up to date. Version 148.0.3967.96 (Official build) (64-bit)
AMD 780M IGPU + 4070s (oculink)

[m8rr]

It really starts slowing down right from the page file addition commit. Everything was fine up until the commit just before it.

slow: Add pagefile tracking 90acc6c

fine: Fit values and units better 4380135