9 papers · 1 filter
MobileLLM-Flash: Latency-Guided On-Device LLM Design for Industry Scale Deployment
Hanxian Huang, Igor Fedorov, Andrey Gromov +14
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 nea…
Neural Computers
Mingchen Zhuge, Changsheng Zhao, Haozhe Liu +16
We propose a new frontier: Neural Computers (NCs) that unify computation, memory, and I/O of traditional computers in a learned runtime state. Our long-term goal is the Completely…
Basis Selection: Low-Rank Decomposition of Pretrained Large Language Models for Target Applications
Yang Li, Daniel Agyei Asante, Changsheng Zhao +3
Large language models (LLMs) significantly enhance the performance of various applications, but they are computationally intensive and energy-demanding. This makes it challenging t…
MobileLLM-Pro Technical Report
Patrick Huber, Ernie Chang, Wei Wen +16
Efficient on-device language models around 1 billion parameters are essential for powering low-latency AI applications on mobile and wearable devices. However, achieving strong per…
ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization
Zechun Liu, Changsheng Zhao, Hanxian Huang +13
The optimal bit-width for achieving the best trade-off between quantized model size and accuracy has been a subject of ongoing debate. While some advocate for 4-bit quantization, o…
SpinQuant: LLM quantization with learned rotations
Zechun Liu, Changsheng Zhao, Igor Fedorov +6
Post-training quantization (PTQ) techniques applied to weights, activations, and the KV cache greatly reduce memory usage, latency, and power consumption of Large Language Models (…