hyperloom-qwen3-14b-fp8-12h

Set it and forget it: 12h AMD ROCm Qwen3-14B FP8 tuning, auto-woven into a speed net. Wake up to results, not logs.

Updated 2026-08-13 · Source https://github.com/AMD-AGI/Hyperloom/tree/HEAD/examples/hyperloom-qwen…

What does this skill do?

Run a 12-hour Hyperloom Qwen3-14B-FP8 optimization session. Use when the user wants a medium-length Hyperloom demo on the local AMD ROCm environment.

Why is it worth installing?

Unlike others, it auto-resumes from crashes and tailors memory layout for AMD, so every FLOP counts across the full 12h.

How do you install it?

git clone --depth 1 https://github.com/AMD-AGI/Hyperloom.git Then point your agent at the skill directory.

Where does it come from?

Repository: AMD-AGI/Hyperloom 138 stars on GitHub at the time of listing. The repository ships 1 skills in total. Homepage: https://rocm.docs.amd.com/projects/hyperloom

developmentskillAMD-AGI

hyperloom-custom-advanced  ·  hyperloom-remote-mn-qwen3-30b