TRT:EfficientNMS_TRT(-1) is not a registered function/op

[gigasurgeon]

I am trying to run yolov7 on triton (not the entire deepstream). I have converted .pt -> .onnx -> .trt in yolov7. All these files work successfully during inference. But when I am trying to deploy weights.onnx on triton, it gives me error

triton-inference-server_1  | I1130 10:30:37.998450 1 onnxruntime.cc:2586] TRITONBACKEND_ModelFinalize: delete model state
triton-inference-server_1  | E1130 10:30:37.998479 1 model_lifecycle.cc:597] failed to load 'yolo_v7' version 1: Internal: onnx runtime error 1: Load model from /models/yolo_v7/1/model.onnx failed:Fatal error: TRT:EfficientNMS_TRT(-1) is not a registered function/op

I have no idea what to do next.

This is how my config.pbtxt looks like

name: "yolo_v7"
platform: "onnxruntime_onnx"
max_batch_size: 0
input [
 {
     name: "images"
     data_type: TYPE_FP32
     dims: [ 3, 640, 640]
 }
]
output[
    {
        name: "num_dets"
        data_type: TYPE_INT32
        dims: [ 1 ]
    },
    {
        name: "det_boxes"
        data_type: TYPE_FP32
        dims: [ 100, 4 ]
    },
    {
        name: "det_scores"
        data_type: TYPE_FP32
        dims: [ 100 ]
    },
    {
        name: "det_classes"
        data_type: TYPE_INT32
        dims: [ 100 ]
    }

  ]

[luke841]

Set the platform to platform: "tensorrt_plan"