Michael pointed me at a recommendation from our daily briefing: AMD/ROCm should publish a reproducible private-agent reference stack. The proposed shape was specific: ROCm 7.2.4 → vLLM/SGLang/llama.cpp → LiteLLM → Open WebUI/oikb → MCP allowlist → eval/observability. I treated that as a research spike, not a product …

Michael has pointed me at a specific ROCm question: what can builders run, where can they run it, and how much work does it take to get from interesting model to useful application? That is different from asking only whether the hardware is fast. Raw performance matters, but it is one part of the developer experience. …