def init_cache()

in training/flax/distil_whisper/modeling_flax_whisper.py [0:0]

• 32 lines of code
• 1 McCabe index (conditional complexity)

    def init_cache(self, batch_size, max_length, encoder_outputs):
        r"""
        Args:
            batch_size (`int`):
                batch_size used for fast auto-regressive decoding. Defines the batch size of the initialized cache.
            max_length (`int`):
                maximum possible length for auto-regressive decoding. Defines the sequence length of the initialized
                cache.
            encoder_outputs (`Union[FlaxBaseModelOutput, tuple(tuple(jnp.ndarray)]`):
                `encoder_outputs` consists of (`last_hidden_state`, *optional*: `hidden_states`, *optional*:
                `attentions`). `last_hidden_state` of shape `(batch_size, sequence_length, hidden_size)`, *optional*)
                is a sequence of hidden-states at the output of the last layer of the encoder. Used in the
                cross-attention of the decoder.
        """
        # init input variables to retrieve cache
        decoder_input_ids = jnp.ones((batch_size, max_length), dtype="i4")
        decoder_attention_mask = jnp.ones_like(decoder_input_ids)
        decoder_position_ids = jnp.broadcast_to(
            jnp.arange(jnp.atleast_2d(decoder_input_ids).shape[-1]),
            decoder_input_ids.shape,
        )

        def _decoder_forward(
            module,
            decoder_input_ids,
            decoder_attention_mask,
            decoder_position_ids,
            **kwargs,
        ):
            decoder_module = module._get_decoder_module()
            return decoder_module(
                decoder_input_ids,
                decoder_attention_mask,
                decoder_position_ids,
                **kwargs,
            )

        init_variables = self.module.init(
            jax.random.PRNGKey(0),
            decoder_input_ids=decoder_input_ids,
            decoder_attention_mask=decoder_attention_mask,
            decoder_position_ids=decoder_position_ids,
            encoder_hidden_states=encoder_outputs[0],
            init_cache=True,
            method=_decoder_forward,  # we only need to call the decoder to init the cache
        )
        return unfreeze(init_variables["cache"])