Showing 1–6 of 6 · #latency

Nov 07MODELSHow to evaluate a new AI model in two weeks: a practical review framework6 min ↗Nov 04MODELSChoosing a model is a budget decision, not a leaderboard decision6 min ↗Oct 11PAPERSSpeculative decoding: faster answers without changing them6 min ↗Oct 07TESTSWhat do reasoning tokens actually cost you? How to measure and control them6 min ↗Sep 08BENCHMARKSDesigning an LLM latency benchmark that matches what users feel6 min ↗Aug 14TESTSDoes "think step by step" help on short tasks?6 min ↗