Metronome: Bound the Cache, Keep the Beat for Real-Time Interaction Model Serving 文章

ArXiv CS.AI2026-07-07PAPERen作者: Jiaying Meng, Bojie Li

详细信息

来源站点
ArXiv CS.AI
作者
Jiaying Meng, Bojie Li
文章类型
PAPER
语言
en
发布日期
2026-07-07

摘要

arXiv:2607.02640v1 Announce Type: cross Abstract: Real-time interaction models -- Moshi, MiniCPM-o, Qwen-Omni -- turn serving into a periodic real-time task: on every frame a session ingests streaming audio and must respond by a recurring wall-clock deadline, while its KV cache grows monotonically and stays pinned for the whole conversation. This regime hides a dangerous failure mode. On a real full-duplex stack, sustained load does not degrade serving gracefully: it falls off a cliff, jumping in one step from milliseconds per frame to a stalled engine when accumulated session state exhausts the KV pool. The collapse is metastable -- identical five-minute runs collapse or survive on run-to-run variance -- and silent: latency and deadline-miss metrics read healthy throughout. We show one move restores both stability and observability: bound each session's resident state, and latency starts telling the truth. Metronome's in-engine KV window eliminates the collapse (0/20 vs.

相关事件

暂无数据

相关公司查看全部 (2)

A
AMI团队RESEARCH_INSTITUTE
A
ACTIONNONPROFIT

相关人物

暂无数据