Skip to content

disable_mmap in pipeline from_pretrained #12854

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
hlky wants to merge 1 commit into
base: main
Choose a base branch
from
+9 −0
Open

disable_mmap in pipeline from_pretrained #12854

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions src/diffusers/pipelines/pipeline_loading_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -758,6 +758,7 @@ def load_sub_model(
use_safetensors: bool,
dduf_entries: Optional[Dict[str, DDUFEntry]],
provider_options: Any,
disable_mmap: bool,
quantization_config: Optional[Any] = None,
):
"""Helper method to load the module `name` from `library_name` and `class_name`"""
Expand Down Expand Up @@ -854,6 +855,9 @@ def load_sub_model(
else:
loading_kwargs["low_cpu_mem_usage"] = False

if is_diffusers_model:
loading_kwargs["disable_mmap"] = disable_mmap

if is_transformers_model and is_transformers_version(">=", "4.57.0"):
loading_kwargs.pop("offload_state_dict")

Expand Down
5 changes: 5 additions & 0 deletions src/diffusers/pipelines/pipeline_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -707,6 +707,9 @@ def from_pretrained(cls, pretrained_model_name_or_path: Optional[Union[str, os.P
loading `from_flax`.
dduf_file(`str`, *optional*):
Load weights from the specified dduf file.
disable_mmap ('bool', *optional*, defaults to 'False'):
Whether to disable mmap when loading a Safetensors model. This option can perform better when the model
is on a network mount or hard drive, which may not handle the seeky-ness of mmap very well.

> [!TIP] > To use private or [gated](https://huggingface.co/docs/hub/models-gated#gated-models) models, log-in
with `hf > auth login`.
Expand Down Expand Up @@ -758,6 +761,7 @@ def from_pretrained(cls, pretrained_model_name_or_path: Optional[Union[str, os.P
use_onnx = kwargs.pop("use_onnx", None)
load_connected_pipeline = kwargs.pop("load_connected_pipeline", False)
quantization_config = kwargs.pop("quantization_config", None)
disable_mmap = kwargs.pop("disable_mmap", False)

if torch_dtype is not None and not isinstance(torch_dtype, dict) and not isinstance(torch_dtype, torch.dtype):
torch_dtype = torch.float32
Expand Down Expand Up @@ -1041,6 +1045,7 @@ def load_module(name, value):
use_safetensors=use_safetensors,
dduf_entries=dduf_entries,
provider_options=provider_options,
disable_mmap=disable_mmap,
quantization_config=quantization_config,
)
logger.info(
Expand Down