Function validate_required_kv_kernels 

pub fn validate_required_kv_kernels(
    gpu: &dyn GpuBackend,
    kv_dtype: KvCacheDtype,
    head_dim: usize,
) -> Result<()>

Startup fail-fast for --kv-cache-dtype: resolve every kernel handle the dtype’s dispatch arms require (chunked-prefill kernel, WHT bookends) and error with the full missing list — BEFORE the multi-minute weight load, instead of at first dispatch. See kernel_requirements.rs.