arXiv AI By Maxwell Twelftree, David Lemphers, An-chi He, Yue Yang

Not Every Sync Is Safe: Calibrated DiLoCo Scheduling for Shared AI Infrastructure

Read the original on arXiv AI →

arXiv:2607. 02544v1 Announce Type: cross Abstract: DiLoCo-style training reduces communication by letting learner islands train locally before occasional outer synchronization, making it attractive for fragmented industrial AI fleets where training shares hardware with latency-sensitive serving.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI
Jul 7

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

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.

By Jiaying Meng, Bojie Li