作者位次 #15/17ACL 2026Poster· ACL Industry Track
M obile LLM -Flash: Latency-Guided On-Device LLM Design for Industry Scale Deployment
Hanxian Huang · Igor Fedorov · Andrey Gromov · Bernard Beckerman · Naveen Suda · David Eriksson · Maximilian Balandat · Rylan Conway · Patrick Huber · Chinnadhurai Sankar · Ayushi Dalmia · Zechun Liu · Lemeng Wu · Tarek Elgamal · Adithya Sagar · Vikas Chandra · Raghuraman Krishnamoorthi
摘要
Real-time AI experiences call for on-device large language models (OD-LLMs) optimized for efficient deployment on resource-constrained hardware. The most useful OD-LLMs produce near-real-time responses and exhibit broad hardware compatibility, maximizing user reach. We present a methodology for d...