pub fn prefill_attention_paged_dflash(
gpu: &dyn GpuBackend,
kernel: KernelHandle,
q: DevicePtr,
k_cache: DevicePtr,
v_cache: DevicePtr,
output: DevicePtr,
block_table: DevicePtr,
q_len: u32,
kv_len: u32,
q_offset: u32,
num_q_heads: u32,
num_kv_heads: u32,
head_dim: u32,
cache_block_size: u32,
sliding_window: u32,
inv_sqrt_d: f32,
stream: u64,
) -> Result<()>Expand description
2026-09-25: prefill_attention_paged launched with
causal_mask_enabled = 0, the BF16-cache counterpart of
prefill_attention_paged_fp8_dflash.