# QAic backend

The QAic backend runs precompiled Qualcomm Program Container (QPC) binaries on Cloud AI inference accelerators.

## QAic Model Repository

For qaic backend configuration, the `backend` parameter should be set
to `qaic`.

### Cloud AI parameters

Parameters are user-provided key-value pairs that Triton passes to the
backend runtime environment as variables; they can be used in the backend
processing logic.

- qpc\_path : path to the compiled binary of the model (programqpc.bin). If not
provided; the server searches for the QPC file in the model folder.
- device\_id : ID of Cloud AI device on which inference is targeted (optional;
if not provided, the server automatically picks an available device).
- set\_size : size of the runtime inference queue. Default: 20.
- no\_of\_activations : Number of activations of a model’s network to use. Default: 1.

Sample `config.pbtxt`:

name: "yolov5m_qaic"
    backend: "qaic"
    max_batch_size : 4
    default_model_filename : "aic100/model.onnx"
    input [
      {
        name: "images"
        data_type: TYPE_FP32
        dims: [3, 640, 640 ]
      }
    ]
    output [
      {
        name: "feature_map_1"
        data_type: TYPE_FP32
        dims: [3, 80, 80, 85]
      },
      {
        name: "feature_map_2"
        data_type: TYPE_FP32
        dims: [3, 40, 40, 85]
      },
      {
        name: "feature_map_3"
        data_type: TYPE_FP32
        dims: [3, 20, 20, 85]
      }
    ]
    parameters [
      {
        key: "qpc_path"
        value: { string_value: "/path/to/qpc" }
      },
      {
        key: "device_id"
        value: { string_value: "0" }
      }
    ]
    instance_group [
      {
        count: 2
        kind: KIND_MODEL
      }
    ]
    Copy to clipboard

## Start Triton server

Start the Triton server within the Triton container with the model repository path.

/opt/tritonserver/bin/tritonserver --model-repository=</path/to/repository>
    Copy to clipboard

Last Published: Aug 25, 2026

[Previous Topic
Build Triton Image with QAic Backends](https://docs.qualcomm.com/bundle/publicresource/80-99100-3/topics/build-triton-image.md) [Next Topic
ONNX Runtime backend](https://docs.qualcomm.com/bundle/publicresource/80-99100-3/topics/onnxruntime-backend.md)