Mahdi Alizadeh

AKTS: Sub-Microsecond Kernel Policy Switching for Language-Model Agents

GPU-backed LLM servers often multiplex interactive requests with background batch work on the same CPUs. During a request burst, the scheduler should protect time-to-first-token; between bursts, it should let background work make progress. A fixed kernel policy leaves one of these objectives on the table, so agentic OS...