Created by: nayanhalder

I am getting same response time in both 1 core and 8 core gpu. 

i am using CUDA10.1 and cudnn7.6

for 8 core gpu. before running python program, i am running the following command in ubuntu
export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7

am i missing any parameter to set.
please help.
i am running with following settings:

parser = argparse.ArgumentParser(description=__doc__)
add_arg = functools.partial(add_arguments, argparser=parser)
# yapf: disable
add_arg('num_samples',      int,    1,     "# of samples to infer.")
add_arg('beam_size',        int,    500,    "Beam search width.")
add_arg('num_proc_bsearch', int,    8,      "# of CPUs for beam search.")
add_arg('num_conv_layers',  int,    2,      "# of convolution layers.")
add_arg('num_rnn_layers',   int,    3,      "# of recurrent layers.")
add_arg('rnn_layer_size',   int,    1024,   "# of recurrent cells per layer.")
add_arg('alpha',            float,  2.5,    "Coef of LM for beam search.")
add_arg('beta',             float,  0.3,    "Coef of WC for beam search.")
add_arg('cutoff_prob',      float,  1.0,    "Cutoff probability for pruning.")
add_arg('cutoff_top_n',     int,    40,     "Cutoff number for pruning.")
add_arg('use_gru',          bool,   True,  "Use GRUs instead of simple RNNs.")
add_arg('use_gpu',          bool,   True,   "Use GPU or not.")
add_arg('share_rnn_weights',bool,   False,   "Share input-hidden weights across "
                                            "bi-directional RNNs. Not for GRU.")