pub fn prefill_attention_paged_nvfp4_64(
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,
block_stride_bytes: u64,
data_section_bytes: u64,
stream: u64,
) -> Result<()>