pub fn reshape_and_cache_fp8(
gpu: &dyn GpuBackend,
kernel: KernelHandle,
key: DevicePtr,
value: DevicePtr,
k_cache: DevicePtr,
v_cache: DevicePtr,
slot_mapping: DevicePtr,
num_tokens: u32,
num_kv_heads: u32,
head_dim: u32,
block_size: u32,
k_scale: f32,
v_scale: f32,
key_stride: u32,
value_stride: u32,
cache_stride: u64,
stream: u64,
) -> Result<()>Expand description
k_cache/v_cache are the full pool base pointers.
cache_stride is in elements (block_size * num_kv_heads * head_dim).