What's New in Inference Engineering — Philip Kiely, Baseten
Baseten's Philip Kiely presents the first public addendum to his Inference Engineering book covering new advances since February 2026.
“This is the first public addendum of all new information since the book came out.”
Philip Kiely of Baseten gave a talk at the AI Engineer World's Fair updating his popular Inference Engineering book with new developments in Turboquant, KV compaction, deflash, and speculative decoding. It matters as a practitioner-focused snapshot of fast-moving inference optimization techniques, though the excerpt is largely introductory and light on concrete technical claims.