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,
)