ComfyUI Node: Torch Compile Speed Settings

Authored by eddyhhlure1Eddy

Created

Updated

24 stars

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Category

optimization

Inputs

backend
  • inductor
  • cudagraphs
fullgraph BOOLEAN
mode
  • default
  • max-autotune
  • max-autotune-no-cudagraphs
  • reduce-overhead
  • speed
dynamic BOOLEAN
dynamo_cache_size_limit INT
compile_transformer_blocks_only BOOLEAN
reuse_if_similar BOOLEAN
experimental_ptx BOOLEAN
ptx_fast_math BOOLEAN
warmup_runs INT
ptx_cache_dir STRING
dynamo_recompile_limit INT

Outputs

WANCOMPILEARGS

Extension: ComfyUI-TorchCompileSpeed

Standalone torch.compile optimization node for ComfyUI with speed-focused presets

Authored by eddyhhlure1Eddy

Looking for a different node?

More nodes in ComfyUI-TorchCompileSpeed

Other optimization nodes

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Learn more