Autonomously optimizes end-to-end LLM inference throughput on AMD Instinct GPUs and reports a validated gain, using the Hyperloom multi-agent optimizer. Given a model, framework, workload (TP/EP, concurrency, ISL/OSL, precision), an objective and a time budget, it explores per-workload which levers to pull (serving/config parameters and env, framework enablement and source patches, and hot…
安装
npx skills add amd/skills --skill hyperloom-workload-optimizernpx skills add amd/skills --skill hyperloom-workload-optimizer -a claude-code -gnpx skills add amd/skills --skill hyperloom-workload-optimizer -a codex -ggemini skills install https://github.com/amd/skills.git --path skills/hyperloom-workload-optimizergh skill install amd/skills hyperloom-workload-optimizergit clone --depth 1 https://github.com/amd/skills /tmp/amd__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/amd__skills/skills/hyperloom-workload-optimizer ~/.claude/skills/hyperloom-workload-optimizer # Claude Code
cp -R /tmp/amd__skills/skills/hyperloom-workload-optimizer ~/.agents/skills/hyperloom-workload-optimizer # Codex, Cursor, Gemini CLI, Copilot, OpenCode