pub fn mla_cache_assemble(
gpu: &dyn GpuBackend,
kernel: KernelHandle,
kv_latent: DevicePtr,
k_rope: DevicePtr,
k_cache: DevicePtr,
v_cache: DevicePtr,
kv_lora: u32,
rope: u32,
mla_cache_dim: u32,
stream: u64,
) -> Result<()>Expand description
MLA cache assembly: fuse [kv_latent|k_rope]→K and [kv_latent|zeros]→V into 1 kernel.