ClikaRT::ops::qk_layer_norm_

function

qk_layer_norm_()

Tensor& qk_layer_norm_(
    Tensor& query,
    OptionalTensor key = {},
    OptionalTensor value = {},
    OptionalTensor query_weight = {},
    OptionalTensor query_bias = {},
    OptionalTensor key_weight = {},
    OptionalTensor key_bias = {},
    std::int64_t head_dim = 0,
    std::optional<double> eps = std::nullopt
)

In-place qk_layer_norm: normalizes query (and key, when present) through their own storage (no output allocation); value is untouched. Same arguments and error conditions as qk_layer_norm(). Tensors are shared-storage handles, so the caller's operands see the writes. Returns query under the value surface, Result<void> under the Result surface; CLIKART_CHECK is the mode-stable spelling.

Declared in ClikaRT/compute/ops.h, line 3592