Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →artokun/triton-sageattention
Install Triton + SageAttention to accelerate ComfyUI (the sageattn attention_mode and inductor torch.compile used by WanVideoWrapper / many video graphs) — Windows-first (triton-windows + woct0rdho prebuilt SageAttention wheels matched to torch/CUDA/python into the RIGHT python), plus Linux (official triton + build) and Mac (N/A → sdpa/MPS). Critically also covers the SAFE sdpa / no-compile fallback so an example that assumes sageattn + torch.compile still runs when these aren't installed (video
Passed 19 of 22 test cases with the skill, and 7 of 22 without it.
and 17 more in the full report
12 fixed7 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am running ComfyUI on Windows with PyTorch 2.10.0+cu130. I want to install triton-windows via pip. What exact package version constraint should I specify in the pip command?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies installing triton-windows with the constraint <3.7. | Missed | Passed |
The instructions your model reads when the skill loads.
See also
comfyui-launch-flagsfor the full attention / VRAM / cache flag matrix. Note the Z-Image exception: Z-Image is broken under--use-sage-attention, so launch it with--use-pytorch-cross-attentioninstead.
If kitchen action:"status" (or panel_kitchen) reports kitchen present and
int8_attention_is_available on this GPU, launch with --use-ck-attention
and skip the sageattention wheel dance. Kitchen INT8 attention is a ComfyUI
flag; it does not need a version-matched sageattention wheel. Restart
required, consent-gated like every restart.
Only fall through to the Triton + SageAttention install below when kitchen INT8 is unknown or not available. A failed kitchen probe is unknown, not a no.
Two optional accelerators that many modern video graphs (especially kijai's ComfyUI-WanVideoWrapper) reference by default:
import sageattention), a quantized attention kernel.
Selected via a node's attention_mode = sageattn (WanVideoWrapper) or ComfyUI's
--use-sage-attention startup flag. ~20 to 40% faster sampling on supported
NVIDIA GPUs.torch.compile needs.
WanVideoWrapper's WanVideoTorchCompileSettings (and any torch.compile/
inductor node) compiles the model through Triton for another speedup.The risk. Both are version-locked to your exact torch + CUDA + python. A wrong wheel does worse than fail to install. It can break the torch install (mismatched CUDA DLLs,
ImportError, or silent NaNs). And the failure mode of not having them is a hard crash before any sampling:ValueError: Can't import SageAttention: No module named 'sageattention', or compile errors /triton: unavailablein the startup log. This is exactly thevideo-extendTRAP 5.
**Therefore the default is to get a working render FIRST with the
test cases passed, vs 7 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.