Researchers from SK hynix published a technical paper titled “StreamDQ: Near-Memory Weight DeQuantization in Custom HBM for Scalable AI Inference Acceleration.”
The paper proposes StreamDQ for “a lightweight architectural enhancement that enables on-the-fly dequantization in the memory subsystem for high-throughput, large-batch LLM inference,” and reports “up to 7.08× speedup and 90.23% lower energy” for mixed-precision GEMM.
Find the technical paper here. July 2026.
Jeong, Minki, Daegun Yoon, Soohong Ahn, Seungyong Lee, Nameun Kang, Hyeonseok Ju, Ieryung Park, Joonseop Sim, Youngpyo Joo, and Hoshik Kim. “StreamDQ: Near-Memory Weight DeQuantization in Custom HBM for Scalable AI Inference Acceleration.” arXiv, July 2026. https://doi.org/10.48550/arXiv.2607.08993.
Leave a Reply