More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    ComfyUI on AMD RDNA3 (ROCm, Windows)

    1

    Make ComfyUI fast and correct on RX 7000-series AMD GPUs on Windows: a tested SageAttention patch (~1.65x), the Triton header fix, and the silent failures that waste days.

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    ComfyUI on AMD RDNA3 (ROCm, Windows)

    ComfyUI on AMD RDNA3 (ROCm, Windows)

    Example session with this skill installed

    I patched SageAttention's BLOCK_M/BLOCK_N to 64/32 on my 7900 XTX to fix the shared-memory error. It runs, but every Wan frame is noise.

    • Read your context and instructions
    • Compiled the comfyui on amd

    The quantizer block size is coupled to the kernel's. Reinstall sageattention 1.0.6, run patch_sageattention_rdna3.py (patches all 9 files, including BLKQ/BLKK 64/32), clear the Triton cache, then compare a fixed-seed render with check_render.py --baseline.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    RDNA3 + ROCm on Windows works well, but its worst failures are silent: wrong output, no error, no NaN. The core rule: never trust a speed-up or a "fix" until you have rendered at a fixed seed and LOOKED at the result.

    Measured on: RX 7900 XTX 24 GB (gfx1100), torch 2.9.1 + ROCm 7.2.1, ComfyUI portable, embedded Python 3.12. Other RX 7000 cards (gfx1101/1102) share the architecture and the 64 KB LDS limit, so the patch should apply, but they are untested. Speeds will differ. This skill assumes ROCm torch is already installed and ComfyUI already runs.

    Run everything in cmd.exe from the ComfyUI portable root (the folder that holds python_embeded\). <SKILL_DIR> means this skill's folder. Always use the embedded Python, never a system Python.

    WantDoMeasured
    Faster attentionSageAttention 1.0.6 + the RDNA3 patch, launch with --use-sage-attention72 → 38.7 s/it (Wan 14B), ~1.65x
    Tritontriton-windows + the embedded Python's C headers—
    Less VRAM for diffusion modelsGGUF (Q6_K / Q8_0). Never fp8 diffusion checkpoints.—
    Faster video decodePurge models right before VAEDecode (section 5)244 → 12.6 s
    Tips that DON'T work herefp8, torch.compile, --fast fp16_accumulation, --highvramreference/dead-ends.md

    Measured on an RX 7900 XTX (gfx1100) only; other RX 7000 cards are untested. The patch script supports SageAttention 1.0.6 only. Does not install ROCm torch or ComfyUI itself. Not for NVIDIA or Linux.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 4 days ago

    Requires

    Nuget
    Pypi
    Windows
    AMD RX 7000-series GPU
    ComfyUI with ROCm torch
    Python (ComfyUI embedded)
    Python

    Permissions

    Allowed Hosts

    www.nuget.org
    pypi.org

    File Scopes

    ComfyUI
    python_embeded/Include
    and
    libs
    python_embeded
    site-packages/sageattention

    The patch script edits installed SageAttention files and keeps .orig backups. The header script only adds missing files and never overwrites.

    Listed4 days ago

    What's inside

    Frequently Asked Questions

    Make ComfyUI fast and correct on RX 7000-series AMD GPUs on Windows: a tested SageAttention patch (~1.65x), the Triton header fix, and the silent failures that waste days.

    This skill uses the open SKILL.md standard. Use it through an MCP-compatible agent connected to Agensi, and check the compatibility information on this page for confirmed agents and required capabilities.

    Connect your AI agent to Agensi through MCP, then ask it to use ComfyUI on AMD RDNA3 (ROCm, Windows) on your task. Your agent loads the latest approved version each time. Paid skills require a purchase or active subscription. Skill files are not available for download; your licence does not allow you to save, copy or export any part of a skill.

    New in Workflow Automation