SADIMM: Accelerating Sparse Attention using DIMM-based Near-memory Processing

Published in IEEE TC, 2025

Recommended citation: Huize Li, Dan Chen, and Tulika Mitra. (2025). "SADIMM: Accelerating Sparse Attention using DIMM-based Near-memory Processing." IEEE Transactions on Computers (TC). 74(2), pp. 542-554.
Download Paper