Error while running triton-server docker with fil backed on MacOS 14.3

[suvratjain1995]

Getting following error when running xgboost model (fil backend) with triton container on MacOS14.3

Error UNAVAILABLE: Invalid argument: unable to find 'libtriton_fil.so' or 'fil/model.py' for model 'xgboost_model', in /opt/tritonserver/backends/fil

Docker File

FROM nvcr.io/nvidia/tritonserver:23.12-py3
ARG MODEL_REPOSITORY=/models/
RUN mkdir -p ${MODEL_REPOSITORY}
COPY ./src ${MODEL_REPOSITORY}
EXPOSE 8000 8001 8002
USER 4000 
ENTRYPOINT ["tritonserver", "--model-repository", "/models", "--strict-model-config=false"]

Folder Structure :-

 xgboost_model
│       ├── 1
│       │   └── xgboost.json
│       └── config.pbtxt

config.pbtxt

backend: "fil"
max_batch_size: 32768
input [
 {
    name: "input__0"
    data_type: TYPE_FP32
    dims: [ 2294 ]
  }
]
output [
 {
    name: "output__0"
    data_type: TYPE_FP32
    dims: [ 2 ]
  }
]
instance_group [{
 kind: KIND_CPU
}]
parameters [
  {
    key: "model_type"
    value: { string_value: "xgboost_json" }
  },
  {
    key: "output_class"
    value: { string_value: "true" }
  },
  {
      key: "predict_proba"
      value: { string_value: "true" }
  },
  {
      key: "threshold"
      value: { string_value: "0.5" }
  },
  {
      key: "storage_type"
      value: { string_value: "AUTO" }
  }
]
dynamic_batching {}

Image version :- nvcr.io/nvidia/tritonserver:23.12-py3

Model is able to load successfully in Linux

[ducfilan]

fil backend is not available in M series chip.