feat: add support for multiple model files

[anhappdev]

• Closes Pass multiple model paths to backend #902
• The function signature will stay the same:

mlperf_backend_ptr_t mlperf_backend_create(
    const char *model_path, 
    mlperf_backend_configuration_t *configs,
    const char *native_lib_path
)

• Here is an example how to have multiple models:

  delegate_choice: {
    delegate_name: "NNAPI"
    accelerator_name: "npu"
    accelerator_desc: "NPU"
    model_file: {
      model_path: "https://file1.tflite"
      model_checksum: "abc"
    }
    model_file: {
      model_path: "https://file2.tflite"
      model_checksum: "def"
    }
  }

• If there is only one model file, the model_path will point to the model file like before.
• If there are multiple model files, the model_path will point to a single directory where all files are located in there.

[github-actions]

MLCommons CLA bot All contributors have signed the MLCommons CLA ✍️ ✅

[sonarqubecloud]

Quality Gate passed

Issues
0 New issues
0 Accepted issues

Measures
0 Security Hotspots
0.0% Coverage on New Code
0.0% Duplication on New Code

See analysis details on SonarCloud

[anhappdev]

@freedomtan @mohitmundhragithub @AhmedTElthakeb Please take a look at the first comment to know how to define multiple models in the backend settings.