Low Bit-Width LLM Acceleration via Symmetric Lookup Format and Compute-in-Decoding Paradigm
- 1 July 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 75 (7) , 2604-2617
Abstract
No abstract availableKeywords
Funding Information
- Yangtze River Delta Science and Technology Innovation Community Joint Fundamental Research Project (2024CSJZN0504)
This publication has 27 references indexed in Scilit:
- LightRot: A Light-Weighted Rotation Scheme and Architecture for Accurate Low-Bit Large Language Model InferenceIEEE Journal on Emerging and Selected Topics in Circuits and Systems, 2025
- FACIL: Flexible DRAM Address Mapping for SoC-PIM Cooperative On-device LLM Inference2025
- FIGLUT: An Energy-Efficient Accelerator Design for FP-INT GEMM Using Look-Up Tables2025
- MECLA: Memory-Compute-Efficient LLM Accelerator with Scaling Sub-matrix Partition2024
- FIGNA: Integer Unit-Based Accelerator Design for FP-INT GEMM Preserving Numerical Accuracy2024
- BitWave: Exploiting Column-Based Bit-Level Sparsity for Deep Learning Acceleration2024
- 20.2 A 28nm 74.34TFLOPS/W BF16 Heterogenous CIM-Based Accelerator Exploiting Denoising-Similarity for Diffusion Models2024
- I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference2023
- quip, v.2023
- 1.1 Computing's energy problem (and what we can do about it)2014