Search papers, labs, and topics across Lattice.
School of Electrical Engineering, Korea Advanced Institue of Science and Technology (KAIST)
3
9
3
16
Unlock 6.6x faster and 4.4x more energy-efficient on-premise MoE serving with a hardware-software co-design that turns MoE's memory bottleneck into a strength.
GyRot achieves state-of-the-art 4-bit accuracy in LLMs while tripling speed and energy efficiency through a unique synergy of rotation and group quantization.
Achieving 27.4 TOPS/W energy efficiency for 4-bit inference, LightRot redefines the benchmarks for low-bit large language models.
