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.