Hyperloom

LLMs lagging on AMD GPUs? Hyperloom auto-weaves an optimization net, squeezing ~30% more speed per card—zero code.

Updated 2026-08-13 · Source https://github.com/AMD-AGI/Hyperloom

What does this skill do?

An agentic system that auto-optimizes LLM workloads on AMD GPUs.

Why is it worth installing?

Unlike manual tuners, it uses agents to sense load and reorder compute graphs live—even reclaims VRAM fragments for you.

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 13 skills in total. Homepage: https://rocm.docs.amd.com/projects/hyperloom

developmentcollectionAMD-AGI

hyperloom-remote-mn-qwen3-30b  ·  claude-plugins-official