(1) Transformer 아키텍쳐에서 진행되는 연산 이해(2) Collective Communication 에 대한 이해원본 문서 링크: https://arxiv.org/abs/2405.17245 Galaxy: A Resource-Efficient Collaborative Edge AI System for In-situ Transformer InferenceTransformer-based models have unlocked a plethora of powerful intelligent applications at the edge, such as voice assistant in smart home. Traditional deployment approaches offload the inference ..
