indexer_state_bytes

Function indexer_state_bytes 

Source
pub fn indexer_state_bytes(capacity: usize, index_head_dim: usize) -> usize
Expand description

Bytes ONE sequence’s indexer cache occupies for ONE DSA layer at capacity rows.

SSOT for the three allocations in Glm5NextDsaState::alloc and for the serve’s per-sequence reserve. = capacity * (4 * index_head_dim + 1), i.e. 513 B/token/layer at GLM-5.3’s index_head_dim = 128. Replicated — EP does NOT halve it.