triton-sageattention SKILL.md skillB
triton-sageattention from artokun/comfyui-mcp is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add artokun/comfyui-mcp/triton-sageattention@git:20260825.ea35391Pins git:20260825.ea35391 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- artokun/comfyui-mcp
- Path
plugin/skills/triton-sageattention/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260825.ea35391, committed Aug 25, 2026
- First version recorded
- Aug 6, 2026
- Size
- 19,877 bytes
- Repository stars
- 896
- License
- MIT
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). Also covers the SAFE sdpa / no-compile fallback so an example that assumes sageattn + torch.compile still runs when these aren't installed…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Triton + SageAttention (ComfyUI acceleration) > See also [`comfyui-launch-flags`](../comfyui-launch-flags/SKILL.md) for 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-attention` instead. ## Prefer kitchen INT8 attention when it is available 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. ## Overview Two optional accelerators that many modern video graphs (especially kijai's ComfyUI-WanVideoWrapper) reference by default: - SageAttention (`import sageattention`), a quantized attention kernel. Selected via a node's `attention_mode = sageattn` (WanVideoWrapper) or ComfyUI's …
Read the whole file at its exact version.
How to install
mdr add artokun/comfyui-mcp/triton-sageattention@sha256:6b6502b2104a81c8The line at the top of this page pins the label git:20260825.ea35391, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_q3pddcro44ctwnrh)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Aug 6, 2026 and Aug 25, 2026, about one every 5 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260825.ea35391 latest | 2026-08-25 | ea35391 | 19,877 B | B | view · diff |
| git:20260822.039e7e3 | 2026-08-22 | 039e7e3 | 20,227 B | B | view · diff |
| git:20260819.9fe9ea3 | 2026-08-19 | 9fe9ea3 | 19,324 B | B | view · diff |
| git:20260816.e017aec | 2026-08-16 | e017aec | 20,410 B | B | view · diff |
| git:20260806.6206d94 | 2026-08-06 | 6206d94 | 20,404 B | B | view |
Audit of the latest version
- fail: No recursive delete of root, home or parent (matched: rm -rf ~/)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (19877 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
artokun/comfyui-mcp · 896 stars · license MIT · pushed 2026-11-04 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_q3pddcro44ctwnrh GET https://markdownregistry.com/api/v1/resolve?ref=artokun/comfyui-mcp/triton-sageattention GET https://markdownregistry.com/api/v1/blob/6b6502b2104a81c87293214642d643d25b0a38e5e96522e5e058fc384d6729ce
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.