Pennylane lightning.gpu, 28+ qubits quantum circuit

Hello, we use “lightning.qubit” in the GPU of the server, but there is a problem that has troubled us for a long time. The running of the program only occupies one GPU, and the utilization rate is very low, but the CPU utilization rate is high; if there are other programs running , the GPU utilization rate of this program is only 1%, which will be squeezed out by other programs and run very slowly. How can we solve this problem?