torch_utils.py

# Copyright 2023 The HuggingFace Team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""
PyTorch utilities: Utilities related to PyTorch
"""
from typing import List, Optional, Tuple, Union

from . import logging
from .import_utils import is_torch_available, is_torch_version


if is_torch_available():
    import torch

logger = logging.get_logger(__name__)  # pylint: disable=invalid-name

try:
    from torch._dynamo import allow_in_graph as maybe_allow_in_graph
except (ImportError, ModuleNotFoundError):

    def maybe_allow_in_graph(cls):
        return cls


def randn_tensor(
    shape: Union[Tuple, List],
    generator: Optional[Union[List["torch.Generator"], "torch.Generator"]] = None,
    device: Optional["torch.device"] = None,
    dtype: Optional["torch.dtype"] = None,
    layout: Optional["torch.layout"] = None,
):
    """This is a helper function that allows to create random tensors on the desired `device` with the desired `dtype`. When
    passing a list of generators one can seed each batched size individually. If CPU generators are passed the tensor
    will always be created on CPU.
    """
    # device on which tensor is created defaults to device
    rand_device = device
    batch_size = shape[0]

    layout = layout or torch.strided
    device = device or torch.device("cpu")

    if generator is not None:
        gen_device_type = generator.device.type if not isinstance(generator, list) else generator[0].device.type
        if gen_device_type != device.type and gen_device_type == "cpu":
            rand_device = "cpu"
            if device != "mps":
                logger.info(
                    f"The passed generator was created on 'cpu' even though a tensor on {device} was expected."
                    f" Tensors will be created on 'cpu' and then moved to {device}. Note that one can probably"
                    f" slighly speed up this function by passing a generator that was created on the {device} device."
                )
        elif gen_device_type != device.type and gen_device_type == "cuda":
            raise ValueError(f"Cannot generate a {device} tensor from a generator of type {gen_device_type}.")

    if isinstance(generator, list):
        shape = (1,) + shape[1:]
        latents = [
            torch.randn(shape, generator=generator[i], device=rand_device, dtype=dtype, layout=layout)
            for i in range(batch_size)
        ]
        latents = torch.cat(latents, dim=0).to(device)
    else:
        latents = torch.randn(shape, generator=generator, device=rand_device, dtype=dtype, layout=layout).to(device)

    return latents


def is_compiled_module(module):
    """Check whether the module was compiled with torch.compile()"""
    if is_torch_version("<", "2.0.0") or not hasattr(torch, "_dynamo"):
        return False
    return isinstance(module, torch._dynamo.eval_frame.OptimizedModule)