fkodom/grouped-query-attention-pytorch

(Unofficial) PyTorch implementation of grouped-query attention (GQA) from "GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints" (https://arxiv.org/pdf/2305.13245.pdf)

语言：Python · GitHub 星标：196 · Fork：14

在 GitHub 上查看原仓库