reshape_and_cache_bf16k_turbo4v

Function reshape_and_cache_bf16k_turbo4v 

Source
pub fn reshape_and_cache_bf16k_turbo4v(
    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,
    k_block_stride_bytes: u64,
    v_block_stride_bytes: u64,
    v_data_section_bytes: u64,
    stream: u64,
) -> Result<()>
Expand description

Write K/V to paged Bf16K + Turbo4V (TurboQuant+ safer-asym) cache.

K written as raw BF16 NHD, V as 4-bit Lloyd-Max + FP8 per-group scale with matched-norm correction. K and V pools have separate strides.