Files
vllm/vllm/model_executor/parallel_utils/utils.py

71 lines
2.4 KiB
Python

# Copyright 2023 The vLLM team.
# Adapted from
# https://github.com/NVIDIA/Megatron-LM/blob/main/megatron/core/tensor_parallel/utils.py
# Copyright (c) 2022, NVIDIA CORPORATION. All rights reserved.
from typing import List, Sequence
import torch
def ensure_divisibility(numerator, denominator):
"""Ensure that numerator is divisible by the denominator."""
assert numerator % denominator == 0, "{} is not divisible by {}".format(
numerator, denominator)
def divide(numerator, denominator):
"""Ensure that numerator is divisible by the denominator and return
the division value."""
ensure_divisibility(numerator, denominator)
return numerator // denominator
def split_tensor_along_last_dim(
tensor: torch.Tensor,
num_partitions: int,
contiguous_split_chunks: bool = False,
) -> List[torch.Tensor]:
""" Split a tensor along its last dimension.
Arguments:
tensor: input tensor.
num_partitions: number of partitions to split the tensor
contiguous_split_chunks: If True, make each chunk contiguous
in memory.
Returns:
A list of Tensors
"""
# Get the size and dimension.
last_dim = tensor.dim() - 1
last_dim_size = divide(tensor.size()[last_dim], num_partitions)
# Split.
tensor_list = torch.split(tensor, last_dim_size, dim=last_dim)
# Note: torch.split does not create contiguous tensors by default.
if contiguous_split_chunks:
return tuple(chunk.contiguous() for chunk in tensor_list)
return tensor_list
class VocabUtility:
""" Split the vocabulary into `world_size` chunks and return the first
and last index of the vocabulary belonging to the `rank`
partition: Note that indices in [fist, last)
"""
@staticmethod
def vocab_range_from_per_partition_vocab_size(
per_partition_vocab_size: int, rank: int) -> Sequence[int]:
index_f = rank * per_partition_vocab_size
index_l = index_f + per_partition_vocab_size
return index_f, index_l
@staticmethod
def vocab_range_from_global_vocab_size(global_vocab_size: int, rank: int,
world_size: int) -> Sequence[int]:
per_partition_vocab_size = divide(global_vocab_size, world_size)
return VocabUtility.vocab_range_from_per_partition_vocab_size(
per_partition_vocab_size, rank)