Work

PNM Meets Sparse Attention: Enabling Multi-Million Tokens Inference at Scale

Year: 2025

Type: article

Source: IEEE Computer Architecture Letters

DOI: 10.1109/lca.2025.3624272

Authors: Sookyung Choi, Myunghyun Rhee, Euiseok Kim, Kwangsik Shin, Youngpyo Joo, Hoshik Kim

Institution: SK Hynix (South Korea)

Language: English

Topic: Parallel Computing and Optimization Techniques

Subfield: Hardware and Architecture

Field: Computer Science

Domain: Physical Sciences

Open Access status: closed

OpenAlex ID: W4415445367

FWCI: 2.332

Cites: 8

Cited by: 5

Related to: 10