04:00
2026-08-21
machinebrief.com
machine-learning
FleetSieve: Decision-Critical Profiling for SLO-Aware LLM Fleet Configuration
FleetSieve, a new profiling method for LLM serving fleets, reaches the oracle aggregate decision using 22,200 GPU-seconds, 6.9% less than uniform random profiling on a fixed H100 grid for a 31B-parame…