Last week @cxodev and @Amplitude_HQ hosted nearly 300 PMs + execs at literally the hottest happy hour I've ever attended 🥵 The best part? I got to record mini-mini How I AIs with my favorite AI people including @graceclarke @JJEnglert @yourgirlhils 📸 @cosmos_raj

Is your CPU:GPU ratio still built for training? In agentic workloads, 50-90% of end-to-end latency is CPU-side tool processing, not GPU math (Georgia Tech + Intel). That's pushing the CPU:GPU ratio from 1:8 in training toward 1:1, sometimes 4:1. And vLLM's CPU backend already runs PagedAttention, prefix caching, and continuous batching across x86, Arm, IBM Z, and experimental Apple Silicon. @_soyr_ and @__gracecaroline on where inference compute should live: