specific method · filed under model architecture
IndexShare
IndexShare is a sparse-attention mechanism that computes which earlier tokens each layer attends to once and reuses those indices across layers.1 Instead of each attention layer independently selecting tokens to focus on, it shares the indices among layers, cutting the cost of long-context attention.2
Trade-off It reduces per-token computational cost at long context while maintaining strong accuracy.3
How this definition was written
Summarised by glm-5.3-flash from 1 source; every sentence is checked against the quote it cites.
computing sparse attention indices once and reusing them across every four attention layers
— GLM-5.2 Explained: Z.ai Open-Weights Frontier Model - TechNowevery attention layer must independently compute which earlier tokens to focus on, an expensive operation
— GLM-5.2 Explained: Z.ai Open-Weights Frontier Model - TechNowthis reduces per-token computational cost by 2.9× at 1M-token context while maintaining strong accuracy
— GLM-5.2 Explained: Z.ai Open-Weights Frontier Model - TechNow