Liu Liu

Ecssd: Hardware/data layout co-designed in-storage-computing architecture for extreme classification

Siqi Li
•
Read more

Dynamic n: M fine-grained structured sparse attention mechanism

Zhaodong Chen
•
Read more

Alcop: Automatic load-compute pipelining in deep learning compiler for ai-gpus

Guyue Huang
•
Read more

TranCIM: Full-digital bitline-transpose CIM-based sparse transformer accelerator with pipeline/parallel reconfigurable modes

Fengbin Tu
•
Read more

Dynamic sparse attention for scalable transformer acceleration

Liu Liu
•
Read more