extern "C" {

// out[i] = in[i] * alpha   (in-place safe: out may alias in)
__global__ void scale_f32(const float* in, float* out, float alpha, int n) {
    int idx = blockIdx.x * blockDim.x + threadIdx.x;
    if (idx < n) {
        out[idx] = in[idx] * alpha;
    }
}

void launch_scale_f32(const float* in, float* out, float alpha, int n, void* stream) {
    int block = 256;
    int grid = (n + block - 1) / block;
    scale_f32<<<grid, block, 0, (cudaStream_t)stream>>>(in, out, alpha, n);
}

}