keras-team/keras · error · ValueError

LiteRT export requires TensorFlow or PyTorch backend.

Error message

LiteRT export requires TensorFlow or PyTorch backend.

What it means

Error "LiteRT export requires TensorFlow or PyTorch backend." thrown in keras-team/keras.

Source

Thrown at keras/src/models/model.py:951

            "tf_saved_model",
            "onnx",
            "openvino",
            "litert",
            "torch",
        )
        if format not in available_formats:
            raise ValueError(
                f"Unrecognized format={format}. Supported formats are: "
                f"{list(available_formats)}."
            )

        # Check if LiteRT export is available (requires TensorFlow or
        # PyTorch backend)
        if format == "litert" and backend.backend() not in (
            "tensorflow",
            "torch",
        ):
            raise ValueError(
                "LiteRT export requires TensorFlow or PyTorch backend."
            )

        # Check if Torch export is available (requires PyTorch backend)
        if format == "torch" and backend.backend() != "torch":
            raise ValueError("Torch export requires PyTorch backend.")

        if format == "tf_saved_model":
            export_saved_model(
                self,
                filepath,
                verbose,
                input_signature=input_signature,
                **kwargs,
            )
        elif format == "onnx":
            export_onnx(
                self,

View on GitHub (pinned to 7a34a03db6)

When it happens

Trigger: Thrown at keras/src/models/model.py:951 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of keras-team/keras@7a34a03db6 (2026-08-25). Data as JSON: /api/errors/5897cc327204a0be. Report an issue: GitHub.