Tag: Sparse Computation
All the papers with the tag "Sparse Computation".
Comet: Accelerating Private Inference for Large Language Model by Predicting Activation Sparsity
grok-3-latestScore: 0.62Published: at 05:29本文提出 *Comet* 系统,通过预测激活稀疏性并设计高效私有推理协议,在保护隐私的同时显著加速大型语言模型的推理,实现了 1.87× 到 2.63× 的性能提升。