Skip to content
The Daily Repo

DazzleML / comfyui-triton-and-sageattention-installer

Cross-platform installer for Triton and SageAttention on ComfyUI. Simplifies GPU-accelerated inference setup for Windows users with automated dependency management and RTX 5090 support.

Why this job: says: comfyui; topics: stable-diffusion, comfyui

What it does

  • One-command installation. No manual compilation or complex setup required
  • Windows-first design. Specifically addresses Windows compilation challenges
  • Automatic CUDA detection. Detects your GPU and CUDA version automatically
  • Pre-built wheel support. Uses pre-compiled wheels to avoid build issues
  • Visual Studio automation. Handles Build Tools installation if needed

Get started

python comfyui_triton_sageattention.py --install --with-custom-nodes --backup

You need: Windows 10/11 (stubs for Linux/macOS experimental); NVIDIA GPU with CUDA support; Existing ComfyUI installation

Maintenance
Active
Last commit 3 months ago
Stars
248
+2 this week
Licence
MIT
Allows business use
Downloads for
None listed
No release files
Latest version
v0.8.15
Released 3 months ago
Built with
Python
88% of the code

Is it looked after?

Contributors
1
Last 90 days
Issues
74% closed
9 still open
Pull requests
0 merged
0 waiting
Releases
19
18 in the last year

Similar repos

Repos similar to this one
RepoStarsLast commitLicenceDownloads for
Comfy-Org / ComfyUI145,880todayGPL-3.0Windows
YanWenKun / ComfyUI-Windows-Portable62323 days agoGPL-3.0Windows
More: languages, topics and project record

Languages

  • Python 88%
  • HTML 12%

Topics

  • automation
  • build-tools
  • cli-tool
  • comfyui
  • cuda
  • gpu-acceleration
  • installer
  • pytorch
  • rtx-5090
  • sageattention
  • stable-diffusion
  • triton

Project record

  • JobImage generation
  • StatusListed
  • Commits55
  • Forks8
  • Watching1
  • Stars in 28 days+9
  • CreatedJul 22, 2025
  • First seen by usNov 7, 2026
  • CheckedNov 7, 2026

Type to search.

Try