def concatenate()

in server/text_generation_server/models/causal_lm.py [0:0]


    def concatenate(cls, batches: List["CausalLMBatch"]) -> "CausalLMBatch":
        # Used for padding
        total_batch_size = 0
        max_input_length = 0
        padding_right_offset = 0
        for batch in batches:
            total_batch_size += len(batch)
            max_input_length = max(max_input_length, batch.max_input_length)
            padding_right_offset = max(padding_right_offset, batch.padding_right_offset)

        # Batch attributes
        requests = []
        requests_idx_mapping = {}
        input_lengths = []
        prefix_offsets = []
        read_offsets = []
        all_input_ids = []
        next_token_choosers = []
        stopping_criterias = []
        top_n_tokens = []
        max_tokens = 0

        # Batch tensors
        input_ids = None
        attention_mask = None
        position_ids = None
        past_key_values = []
        top_n_tokens_tensor = None

        # Used for slicing correctly inside the tensors
        # Equivalent to a cumsum on batch sizes
        start_index = 0
        for i, batch in enumerate(batches):
            requests.extend(batch.requests)
            input_lengths.extend(batch.input_lengths)
            prefix_offsets.extend(batch.prefix_offsets)
            read_offsets.extend(batch.read_offsets)
            all_input_ids.extend(batch.all_input_ids)
            next_token_choosers.extend(batch.next_token_choosers)
            stopping_criterias.extend(batch.stopping_criterias)
            top_n_tokens.extend(batch.top_n_tokens)

            if i == 0:
                requests_idx_mapping = batch.requests_idx_mapping
            else:
                # We need to offset the mapping for each batch by the cumulative batch size
                for k, v in batch.requests_idx_mapping.items():
                    requests_idx_mapping[k] = v + start_index

            # Slicing end index for this batch
            end_index = start_index + len(batch)

            # We only concatenate batches that did at least one step
            if batch.past_key_values is None:
                raise ValueError("only concatenate prefilled batches")

            # Create empty tensor
            # input_ids is always of shape [batch_size, 1]
            # We do not need to pad it
            if input_ids is None:
                input_ids = batch.input_ids.new_empty((total_batch_size, 1))
            # Copy to correct indices
            input_ids[start_index:end_index] = batch.input_ids

            # Create padded tensor
            if attention_mask is None:
                attention_mask = batch.attention_mask.new_zeros(
                    (total_batch_size, max_input_length + padding_right_offset),
                )

            if top_n_tokens_tensor is None:
                top_n_tokens_tensor = batches[0].top_n_tokens_tensor.new_zeros(
                    total_batch_size,
                )
            top_n_tokens_tensor[start_index:end_index] = batch.top_n_tokens_tensor

            # We need to slice the attention mask to remove padding from previous steps
            # and to remove unused allocated space
            left_offset = max_input_length - batch.max_input_length
            batch_left_offset = (
                batch.attention_mask.shape[1]
                - batch.max_input_length
                - batch.padding_right_offset
            )
            attention_mask[
                start_index:end_index,
                left_offset:-padding_right_offset,
            ] = batch.attention_mask[
                :,
                batch_left_offset : -batch.padding_right_offset,
            ]

            # Create empty tensor
            # position_ids is always of shape [batch_size, 1]
            if position_ids is None:
                position_ids = batch.position_ids.new_empty((total_batch_size, 1))
            position_ids[start_index:end_index] = batch.position_ids

            # Shenanigans to get dimensions because BLOOM outputs a past with a different shape
            # BLOOM Keys:   [batch_size * num_heads, head_dim, seq_length]
            # BLOOM Values: [batch_size * num_heads, seq_length, head_dim]
            # And ensure that we can update tensors in-place
            if isinstance(batch.past_key_values[0], tuple):
                batch.past_key_values = [
                    [t.view(len(batch), -1, *t.shape[-2:]) for t in layer]
                    for layer in batch.past_key_values
                ]
            elif len(batch.past_key_values[0][0].shape) == 3:
                for layer in batch.past_key_values:
                    for k, t in enumerate(layer):
                        layer[k] = t.view(len(batch), -1, *t.shape[-2:])

            # Add eventual padding tokens that were added while concatenating
            max_tokens += batch.max_tokens + (
                max_input_length - batch.max_input_length
            ) * len(batch)

            start_index = end_index

        first_past_kvs = batches[0].past_key_values
        _, num_heads, padded_sequence_length, head_dim = first_past_kvs[0][1].shape

        padded_past_values_shape = (
            total_batch_size,
            num_heads,
            max_input_length - 1,
            head_dim,
        )

        if batches[0].keys_head_dim_last:
            padded_past_keys_shape = padded_past_values_shape
        else:
            # seq_length is last for BLOOM
            padded_past_keys_shape = (
                total_batch_size,
                num_heads,
                head_dim,
                max_input_length - 1,
            )

        # Iterate over attention layers
        # Concatenate past key values layer by layer to allow incremental garbage collection
        for j in range(len(first_past_kvs)):
            padded_past_keys = first_past_kvs[j][0].new_zeros(padded_past_keys_shape)
            start_index = 0
            for batch in batches:
                past_keys = batch.past_key_values[j][0]
                # Clear reference to the original tensor
                batch.past_key_values[j][0] = None

                # Slicing end index for this batch
                end_index = start_index + len(batch)
                # We slice the keys to remove the padding from previous batches
                past_seq_len = batch.max_input_length - 1
                if batch.keys_head_dim_last:
                    padded_past_keys[start_index:end_index, :, -past_seq_len:, :] = (
                        past_keys[:, :, -past_seq_len:, :]
                    )
                else:
                    # BLOOM case
                    padded_past_keys[start_index:end_index, :, :, -past_seq_len:] = (
                        past_keys[:, :, :, -past_seq_len:]
                    )
                del past_keys

                start_index = end_index

            padded_past_values = first_past_kvs[j][1].new_zeros(
                padded_past_values_shape
            )
            start_index = 0
            for batch in batches:
                past_values = batch.past_key_values[j][1]
                # Clear reference to the original tensor
                batch.past_key_values[j][1] = None

                # Slicing end index for this batch
                end_index = start_index + len(batch)
                # We slice the past values to remove the padding from previous batches
                past_seq_len = batch.max_input_length - 1
                padded_past_values[start_index:end_index, :, -past_seq_len:, :] = (
                    past_values[:, :, -past_seq_len:, :]
                )
                del past_values

                # Update values
                start_index = end_index

            past_key_values.append([padded_past_keys, padded_past_values])

        return cls(
            batch_id=batches[0].batch_id,
            requests=requests,
            requests_idx_mapping=requests_idx_mapping,
            input_ids=input_ids,
            attention_mask=attention_mask,
            position_ids=position_ids,
            past_key_values=past_key_values,
            all_input_ids=all_input_ids,
            input_lengths=input_lengths,
            prefix_offsets=prefix_offsets,
            read_offsets=read_offsets,
            next_token_choosers=next_token_choosers,
            stopping_criterias=stopping_criterias,
            top_n_tokens=top_n_tokens,
            top_n_tokens_tensor=top_n_tokens_tensor,
            max_input_length=max_input_length,
            padding_right_offset=padding_right_offset,
            keys_head_dim_last=batches[0].keys_head_dim_last,
            max_tokens=max_tokens,
        )