qsa_score_rows

Function qsa_score_rows 

Source
pub fn qsa_score_rows(
    gpu: &dyn GpuBackend,
    kernel: KernelHandle,
    q: DevicePtr,
    block_keys: DevicePtr,
    scores: DevicePtr,
    rows: u32,
    n_blocks_max: u32,
    first_pos: u32,
    score_stride: u32,
    ratio: u32,
    n_heads: u32,
    hd: u32,
    stream: u64,
) -> Result<()>
Expand description

2026-09-25: Per-row block scores for prefill rows; blocks at or past a row’s complete-block count score -inf.