AMD Skills walkthroughs

This collection of walkthroughs assumes you already have Claude Code set up on your machine.

Participants using other agents are still encouraged to participate. You might have to adapt some of the instructions provided below to your specific agent.

Choose a skill to get started.

• lemonade-router-builder: Generate a valid Lemonade router policy JSON from a plain-English description of routing intent.

• local-ai-use: Teach your agent how to run image generation locally.

• local-ai-app-integration: Add a local AI mode to a cloud-only app.

• hyperloom-workload-optimizer: Set up Hyperloom and autonomously optimize LLM inference throughput on AMD Instinct GPUs.

• magpie-kernel-evaluator: Benchmark inference, identify bottlenecks, and analyze, compare, and revalidate optimized GPU kernels with Magpie.

• serving-llms-on-instinct: Bring up a vLLM OpenAI-compatible LLM endpoint on an AMD Instinct GPU.

• serving-llms-on-epyc: Bring up a vLLM + zentorch LLM endpoint on an AMD EPYC CPU.

• tracelens-analysis-orchestrator: Run agentic PyTorch profiler trace analysis and produce a prioritized performance report.