optimum/habana/transformers/models/phi/modeling_phi.py [514:588]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        )

        hidden_states = outputs.last_hidden_state
        _, seq_len, _ = hidden_states.shape
        if seq_len > 1 and trim_logits and not self.training:
            if token_idx is not None:
                hidden_states = hidden_states.index_select(1, token_idx - 1)
            else:
                hidden_states = hidden_states[:, -1, :]
        # Only compute necessary logits, and do not upcast them to float if we are not computing the loss
        slice_indices = slice(-logits_to_keep, None) if isinstance(logits_to_keep, int) else logits_to_keep
        logits = self.lm_head(hidden_states[:, slice_indices, :])

        loss = None
        if labels is not None:
            loss = self.loss_function(logits=logits, labels=labels, vocab_size=self.config.vocab_size, **kwargs)

        return CausalLMOutputWithPast(
            loss=loss,
            logits=logits,
            past_key_values=outputs.past_key_values,
            hidden_states=outputs.hidden_states,
            attentions=outputs.attentions,
        )

    def prepare_inputs_for_generation(
        self,
        input_ids,
        past_key_values=None,
        attention_mask=None,
        inputs_embeds=None,
        cache_position=None,
        position_ids=None,
        use_cache=True,
        num_logits_to_keep=None,
        token_idx=None,
        **kwargs,
    ):
        """
        Inherits from PhiForCausalLM: https://github.com/huggingface/transformers/blob/v4.37.1/src/transformers/models/phi/modeling_phi.py
        The only differences are:
        - add new args token_idx
        - add token_idx into model_inputs
        - from step2 when enable KV cache, slice next_input_ids from input_ids base on the token_idx
        - from step2 when enable KV cache, slice next_position_ids from position_ids base on the token_idx
        """
        reuse_cache = kwargs.get("reuse_cache")
        # Omit tokens covered by past_key_values
        if past_key_values is not None:
            if token_idx is not None:
                idx = token_idx + kwargs.get("inputs_embeds_offset", 0) - 1
                input_ids = torch.index_select(input_ids, 1, idx)
            else:
                if inputs_embeds is not None:  # Exception 1
                    input_ids = input_ids[:, -cache_position.shape[0] :]
                elif (
                    input_ids.shape[1] != cache_position.shape[0]
                ):  # Default case (the "else", a no op, is Exception 2)
                    input_ids = input_ids[:, cache_position]
        elif reuse_cache and token_idx is not None:
            # With reuse_cache, KV cache is pre allocated hence for the 1st token we can slice the inputs till token idx for the fwd pass
            input_ids = input_ids[:, :token_idx]
            attention_mask = attention_mask[:, :token_idx]

        if attention_mask is not None and position_ids is None:
            # create position_ids on the fly for batch generation
            position_ids = attention_mask.long().cumsum(-1) - 1
            position_ids.masked_fill_(attention_mask == 0, 1)
            if past_key_values:
                if token_idx is not None:
                    position_ids = torch.index_select(position_ids, 1, token_idx - 1)
                else:
                    position_ids = position_ids[:, -input_ids.shape[1] :]
                # This `clone` call is needed to avoid recapturing cuda graphs with `torch.compile`'s  `mode="reduce-overhead`, as otherwise the input `position_ids` would have various stride during the decoding. Here, simply using `.contiguous()` is not sufficient as in the batch size = 1 case, `position_ids` is already contiguous but with varying stride which retriggers a capture.
                position_ids = position_ids.clone(memory_format=torch.contiguous_format)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



optimum/habana/transformers/models/starcoder2/modeling_starcoder2.py [737:803]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        )

        hidden_states = outputs.last_hidden_state
        _, seq_len, _ = hidden_states.shape
        if seq_len > 1 and trim_logits and not self.training:
            if token_idx is not None:
                hidden_states = hidden_states.index_select(1, token_idx - 1)
            else:
                hidden_states = hidden_states[:, -1, :]

        # Only compute necessary logits, and do not upcast them to float if we are not computing the loss
        slice_indices = slice(-logits_to_keep, None) if isinstance(logits_to_keep, int) else logits_to_keep
        logits = self.lm_head(hidden_states[:, slice_indices, :])

        loss = None
        if labels is not None:
            loss = self.loss_function(logits=logits, labels=labels, vocab_size=self.config.vocab_size, **kwargs)

        return CausalLMOutputWithPast(
            loss=loss,
            logits=logits,
            past_key_values=outputs.past_key_values,
            hidden_states=outputs.hidden_states,
            attentions=outputs.attentions,
        )

    def prepare_inputs_for_generation(
        self,
        input_ids,
        past_key_values=None,
        attention_mask=None,
        inputs_embeds=None,
        cache_position=None,
        position_ids=None,
        use_cache=True,
        num_logits_to_keep=None,
        token_idx=None,
        **kwargs,
    ):
        reuse_cache = kwargs.get("reuse_cache")
        if past_key_values is not None:
            if token_idx is not None:
                idx = token_idx + kwargs.get("inputs_embeds_offset", 0) - 1
                input_ids = torch.index_select(input_ids, 1, idx)
            else:
                if inputs_embeds is not None:  # Exception 1
                    input_ids = input_ids[:, -cache_position.shape[0] :]
                elif (
                    input_ids.shape[1] != cache_position.shape[0]
                ):  # Default case (the "else", a no op, is Exception 2)
                    input_ids = input_ids[:, cache_position]
        elif reuse_cache and token_idx is not None:
            # With reuse_cache, KV cache is pre allocated hence for the 1st token we can slice the inputs till token idx for the fwd pass
            input_ids = input_ids[:, :token_idx]
            attention_mask = attention_mask[:, :token_idx]

        if attention_mask is not None and position_ids is None:
            # create position_ids on the fly for batch generation
            position_ids = attention_mask.long().cumsum(-1) - 1
            position_ids.masked_fill_(attention_mask == 0, 1)
            if past_key_values:
                if token_idx is not None:
                    position_ids = torch.index_select(position_ids, 1, token_idx - 1)
                else:
                    position_ids = position_ids[:, -input_ids.shape[1] :]
                # This `clone` call is needed to avoid recapturing cuda graphs with `torch.compile`'s  `mode="reduce-overhead`, as otherwise the input `position_ids` would have various stride during the decoding. Here, simply using `.contiguous()` is not sufficient as in the batch size = 1 case, `position_ids` is already contiguous but with varying stride which retriggers a capture.
                position_ids = position_ids.clone(memory_format=torch.contiguous_format)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -