Function reshape_and_cache_nvfp4 

pub fn reshape_and_cache_nvfp4(
    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,
    key_stride: u32,
    value_stride: u32,
    block_stride_bytes: u64,
    data_section_bytes: u64,
    stream: u64,
) -> Result<()>

2026-09-25: Write each token’s K and V into the paged NVFP4 cache at its slot_mapping slot: E2M1 values with one E4M3 scale per 16. One block per token.