Function batched_mat_mul_same_shape_owned 

pub fn batched_mat_mul_same_shape_owned<T>(
    batch: usize,
    m: usize,
    k: usize,
    n: usize,
    a: Vec<T>,
    b: Vec<T>,
) -> Result<Vec<T>, MatrixMulError>
where
    T: TensorScalar + Copy,

Batched matrix multiplication while consuming column-major input buffers.

This is the owned-buffer counterpart of batched_mat_mul_same_shape. It avoids cloning the two input batches when callers have just built the contiguous buffers for a backend call.

Errors

Returns an error if the input buffer lengths do not match the declared shapes or if the backend rejects the batched GEMM.