device: gpu
device_id: 0
cpu_thread_nums: 1
warmup: 20
repeat: 100
backend: paddle
profile_mode: end2end
include_h2d_d2h: false
use_fp16: false
collect_memory_info: true
sampling_interval: 1
precision_compare: false
xpu_l3_cache: 0
result_path: benchmark_gpu_paddle_fp32_e2e_mem.txt