# `Dala.ML.ONNX`
[🔗](https://github.com/manhvu/dala/blob/main/lib/dala/ml/onnx.ex#L1)

Public API for ONNX Runtime inference.

Provides cross-platform ML inference via ONNX Runtime with hardware
acceleration on both iOS and Android:

- **iOS**: CoreML Execution Provider → Apple Neural Engine
- **Android**: NNAPI Execution Provider → Qualcomm Hexagon / MediaTek APU
- **Fallback**: CPU execution on all platforms

All NIF functions run on the dirty CPU scheduler to avoid blocking BEAM.

## Usage

    # Load model from file
    {:ok, session_id} = Dala.ML.ONNX.load_model_from_file("model.onnx")

    # Or from binary data
    {:ok, session_id} = Dala.ML.ONNX.create_session(model_binary)

    # Run inference
    {:ok, output} = Dala.ML.ONNX.run(session_id, input_binary)

    # Clean up
    :ok = Dala.ML.ONNX.destroy_session(session_id)

# `available?`

```elixir
@spec available?() :: boolean()
```

Check if ONNX Runtime NIF is available.

# `create_session`

```elixir
@spec create_session(binary()) :: {:ok, integer()} | {:error, term()} | :not_supported
```

Create an ONNX inference session from model binary data.

Returns `{:ok, session_id}` on success.

# `destroy_session`

```elixir
@spec destroy_session(integer()) :: :ok | {:error, term()} | :not_supported
```

Destroy an ONNX session and free associated resources.

# `load_model_from_file`

```elixir
@spec load_model_from_file(String.t()) ::
  {:ok, integer()} | {:error, term()} | :not_supported
```

Load an ONNX model from a file path and create a session.

# `run`

```elixir
@spec run(integer(), binary()) :: {:ok, binary()} | {:error, term()} | :not_supported
```

Run inference on a session with the given input binary data.

Input must be a binary of f32 values in the correct shape for the model.
Returns `{:ok, output_binary}` where output_binary is f32 values.

# `runtime_available?`

```elixir
@spec runtime_available?() :: boolean() | :not_supported
```

Check if ONNX Runtime is available and initialized on this platform.

# `session_count`

```elixir
@spec session_count() :: integer() | :not_supported
```

Return the number of active ONNX sessions.

---

*Consult [api-reference.md](api-reference.md) for complete listing*