Lincoln: Real-Time 50~100B LLM Inference on Consumer Devices with LPDDR-Interfaced, Compute-Enabled Flash Memory.
Weiyi Sun, Mingyu Gao, Zhaoshi Li, Aoyang Zhang, Iris Ying Chou, Jianfeng Zhu, Shaojun Wei, Leibo Liu
Browse the full HPCA paper archive.