1 citations · 1 across the 16 of their papers we have counts for
7 papers · 1 filter
FluxBin: Flexible LUT-based Ultra-low-bit LLM Inference by Algorithm-Kernel Synergy
Qingyao Yang, Runming Yang, He Xiao +7
While binary quantization theoretically promises extreme compression and acceleration for Large Language Models (LLMs), existing research often overlooks the necessity of specializ…
ROMER: Expert Replacement and Router Calibration for Robust MoE LLMs on Analog Compute-in-Memory Systems
Wenyong Zhou, Yuannuo Feng, Yizhe Chen +6
Large language models (LLMs) with mixture-of-experts (MoE) architectures achieve remarkable scalability by sparsely activating a subset of experts per token, yet their frequent exp…
Beyond Outliers: A Data-Free Layer-wise Mixed-Precision Quantization Approach Driven by Numerical and Structural Dual-Sensitivity
Hengyuan Zhang, Xinrong Chen, Zunhai Su +10
Layer-wise mixed-precision quantization (LMPQ) enables effective compression under extreme low-bit settings by allocating higher precision to sensitive layers. However, existing me…
Nonparametric Teaching of Attention Learners
Chen Zhang, Jianghui Wang, Bingyang Cheng +7
Attention learners, neural networks built on the attention mechanism, e.g., transformers, excel at learning the implicit relationships that relate sequences to their corresponding…
Fighter: Unveiling the Graph Convolutional Nature of Transformers in Time Series Modeling
Chen Zhang, Weixin Bu, Wendong Xu +3
Transformers have achieved remarkable success in time series modeling, yet their internal mechanisms remain opaque. This work demystifies the Transformer encoder by establishing it…
PTQTP: Post-Training Quantization to Trit-Planes for Large Language Models
He Xiao, Runming Yang, Qingyao Yang +6
Post-training quantization (PTQ) of large language models (LLMs) to extremely low bit-widths remains challenging due to the fundamental trade-off between computational efficiency a…
Exploring Layer-wise Information Effectiveness for Post-Training Quantization in Small Language Models
He Xiao, Qingyao Yang, Dirui Xie +7
Large language models with billions of parameters are often over-provisioned: many layers contribute little unique information yet dominate the memory and energy footprint during i…