4 papers
Huawei Cloud Model-as-a-Service on the CloudMatrix384 SuperPod
Ao Xiao, Bangzheng He, Baoquan Zhang +125
Scaled-out MoE LLMs and scaled-up SuperPods create new systems challenges for production Model-as-a-Service (MaaS), requiring disaggregation, low-latency communication, and decentr…
Semantic Alignment and Reinforcement for Data-Free Quantization of Vision Transformers
Yunshan Zhong, Yuyao Zhou, Yuxin Zhang +5
Data-free quantization (DFQ) enables model quantization without accessing real data, addressing concerns regarding data security and privacy. With the growing adoption of Vision Tr…
ASER: Activation Smoothing and Error Reconstruction for Large Language Model Quantization
Weibo Zhao, Yubin Shi, Xinyu Lyu +3
Quantization stands as a pivotal technique for large language model (LLM) serving, yet it poses significant challenges particularly in achieving effective low-bit quantization. The…
DeltaDQ: Ultra-High Delta Compression for Fine-Tuned LLMs via Group-wise Dropout and Separate Quantization
Yanfeng Jiang, Zelan Yang, Bohua Chen +3
Large language models achieve exceptional performance on various downstream tasks through supervised fine-tuning. However, the diversity of downstream tasks and practical requireme…