Nodes/IAMCCS-nodes/GGUF Accelerator (patch_on_device)
ComfyUI Node

GGUF Accelerator (patch_on_device)

A ComfyUI node in IAMCCS/Optimize with 8 inputs and 2 outputs.

By IAMCCS·Created 10 months ago·Updated about a month ago· 109
GGUF Accelerator (patch_on_device)
  • model
  • model
  • report
modeauto_oom_safe
patch_on_devicetrue
move_patches_nowtrue
min_free_vram_mb1500
oom_fallbacktrue
move_policyall_or_nothing
leave_free_vram_mb1024
CategoryIAMCCS/Optimize

Inputs (8)

NameTypeDefaultDescription
modelMODEL
modeCOMBOauto_oom_safeauto_oom_safe: tries patch_on_device+eager move, falls back to offload on OOM | manual: use toggles below
patch_on_deviceBOOLEANtrue
move_patches_nowBOOLEANtrueIf enabled, attempts to pre-move patch tensors to the model load_device to reduce runtime transfers. Can increase VRAM usage.
min_free_vram_mbINT15000–65536(auto_oom_safe) If free VRAM is below this, we disable patch_on_device to reduce OOM risk. 0 disables the check.
oom_fallbackBOOLEANtrueIf a CUDA OOM happens while moving patches, automatically switches to offload and continues.
move_policyCOMBOall_or_nothingWhen pre-moving patches: all_or_nothing moves everything only if it fits the VRAM budget; partial_* moves a subset within the budget.
leave_free_vram_mbINT10240–65536When pre-moving patches to CUDA, try to keep at least this much VRAM free. 0 disables budget limiting.

Outputs (2)

NameTypeDescription
modelMODEL
reportSTRING