Work

Mixed INT4-INT8 LLM Quantization via Progressive Layerwise Assignment with Dynamic Sensitivity Estimation

Year: 2025

Type: conference-paper

Source: IEEE International Symposium on Circuits and Systems proceedings

DOI: 10.1109/iscas56072.2025.11043378

Authors: Jihoon Kim, Minseok Seo, Xuan Truong Nguyen

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: closed

OpenAlex ID: W4411726797

FWCI: 0.781

Cites: 12

Cited by: 1

Related to: 10