broadcastAddVectorToMatrixGPU function

GPUTensor<Matrix> broadcastAddVectorToMatrixGPU(
  1. GPUTensor<Matrix> m,
  2. GPUTensor<Vector> v,
  3. CommandBuffer tape
)

Implementation

GPUTensor<Matrix> broadcastAddVectorToMatrixGPU(GPUTensor<Matrix> m, GPUTensor<Vector> v, CommandBuffer tape) {
  GPUTensor<Matrix> out = GPUTensor<Matrix>.empty(m.shape);

  tape.putInt(OP_BROADCAST_ADD);
  tape.putString(m.id);
  tape.putString(v.id);
  tape.putString(out.id);

  out.creator = GPUNode(
    <GPUTensor>[m, v],
        (CommandBuffer bTape) {
      // Backward pass logic (stubbed for inference)
    },
    opName: 'broadcastAddVectorToMatrixGPU',
    cost: m.shape[0] * m.shape[1],
  );

  return out;
}