optimum/executorch/modeling.py [513:535]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        echo: bool = True,
        max_seq_len: Optional[int] = None,
    ):
        """
        Perform text generation task for a given prompt using the ExecuTorch model.

        Args:
            tokenizer (`PreTrainedTokenizer`):
                The tokenizer used to encode and decode the prompt and output.
            prompt (`str`):
                The text prompt to complete.
            echo (`bool`, *optional*):
                Whether to include prompt tokens in the generated output. Defaults to `True`.
            max_seq_len (`int`, *optional*):
                Maximum sequence length for the generated output.
                Defaults to None and uses the model's `max_cache_size` attribute.
                Will be truncated to maximal cache size if larger than `max_cache_size`.
        """
        self.tokenizer = tokenizer

        # Reset stats for a new generation
        self.stats.reset()
        self.stats.on_inference_start()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



optimum/executorch/modeling.py [1054:1076]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        echo: bool = True,
        max_seq_len: Optional[int] = None,
    ):
        """
        Perform text generation task for a given prompt using the ExecuTorch model.

        Args:
            tokenizer (`PreTrainedTokenizer`):
                The tokenizer used to encode and decode the prompt and output.
            input_features (`str`):
                Log-mel spectrogram for 30-second audio chunk. Can be obtained using the WhisperProcessor. Should be of shape [1, 80, 3000] or
                [1, 128, 3000]. For details, check out the processor config.
            echo (`bool`, *optional*):
                Whether to include prompt tokens in the generated output. Defaults to `True`.
            max_seq_len (`int`, *optional*):
                Maximum sequence length for the generated output.
                Defaults to None and uses the model's `max_cache_size` attribute.
                Will be truncated to maximal cache size if larger than `max_cache_size`.
        """
        self.tokenizer = tokenizer

        self.stats.reset()
        self.stats.on_inference_start()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -