pub fn paged_decode_attn_fp8(
gpu: &dyn GpuBackend,
kernel: KernelHandle,
q: DevicePtr,
k_cache: DevicePtr,
v_cache: DevicePtr,
output: DevicePtr,
block_tables: DevicePtr,
seq_lens: DevicePtr,
max_blocks_per_seq: u32,
num_seqs: u32,
num_q_heads: u32,
num_kv_heads: u32,
head_dim: u32,
block_size: u32,
inv_sqrt_d: f32,
k_scale: f32,
v_scale: f32,
q_stride: u32,
cache_stride: u64,
sliding_window: u32,
stream: u64,
) -> Result<()>