VERIFY_ROW_CAP

Constant VERIFY_ROW_CAP 

Source
pub const VERIFY_ROW_CAP: usize = 256;
Expand description

2026-09-29: Most rows (R = Σ ks) one batched MTP verify scores: 128 sequences at one draft (the serve’s widest batch, DECODE_META_MAX_ROWS). It sizes the verify block-table rows (sizes/regions.rs) and the logits floor here; model-engine’s VERIFY_ROW_CAP and the scheduler’s VERIFY_ROW_BUDGET are this value. Was 160 (32 sequences at up to five rows).