Work

InFormer: A High-throughput, Ultra-efficient In-memory Compute-based Floating-point Arithmetic Accelerator for Transformers

Year: 2025

Type: conference-paper

Source: ACM Great Lakes Symposium on VLSI (GLSVLSI)

DOI: 10.1145/3716368.3735246

Authors: Hasita Veluri, Dilip Vasudevan

Institution: Lawrence Berkeley National Laboratory

Language: English

Topic: Advanced Memory and Neural Computing

Subfield: Electrical and Electronic Engineering

Field: Engineering

Domain: Physical Sciences

Open Access status: closed

Funder: U.S. Department of Energy

Award: G42916606

OpenAlex ID: W4411713585

FWCI:

Cites: 14

Cited by:

Related to: 10