We study optimization of distributed model inference over resource-constrained edge resources. We propose a framework that optimizes the trade-off between model accuracy and communication costs by controlling latent representation compression to meet strict Quality of Service (QoS) throughput targets. For settings with...
Peyman Gholami, Theodoros-Thirimachos Davarakis, Teng Li et al.· 0 citations
Preliminary results from a geo-distributed LLM training prototype that treats networking constraints as first-order design concerns are presented, motivating adaptive networking support for synchronization, compression, placement, telemetry, and recovery in geo-distributed LLM training.
Zi-Yue Luo, Jiaxuan Cai, Cedric Le Denmat et al.· Conference on Applications,...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.