1.088B 파라미터 Pure SNN의 Random Init 기반 수렴 성공
I scaled a pure Spiking Neural Network (SNN) to 1.088B parameters from scratch. Ran out of budget, but here is what I found
Wafer-Scale Engine 통한 21 PB/s 대역폭 및 초고속 LLM 추론 달성
Cerebras risked it all on dinner plate-sized AI accelerators a decade ago. Today it’s worth $66 billion
Deterministic Initialization 통한 62.3% Sparsity 달성 및 모델 최적화
Stop Guessing Which Weights Your Neural Network Actually Learned: Deterministic Initialization That Tracks Every Change