name: "bert"
platform: "tensorrt_plan"
max_batch_size: 128
input [
  {
    name: "token_ids"
    data_type: TYPE_INT32
    dims: [128]
  },
  {
    name: "attn_mask"
    data_type: TYPE_INT32
    dims: [128]
  }
]
output [
  {
    name: "output"
    data_type: TYPE_FP32
    dims: [128, 768]
  },
  {
    name: "1634"
    data_type: TYPE_FP32
    dims: [768]
  }
]
instance_group {
  count: 1
  kind: KIND_GPU
}
dynamic_batching {
  preferred_batch_size: 16
}