huggingface
Add `disable_mmap` to option to Pipeline
What does this PR do?
Addressed some of the issues brought up in #12599. Using mmaped safetensors on networked volumes can lead to very slow load/device transfer times. More context: https://github.com/huggingface/safetensors/issues/562#issuecomment-2634544710
We have the disable_mmap option for single file and models to skip using safetensors default mmaped loading, but didn't add it to from_pretrained in pipelines.
Fixes # (issue)
Before submitting
- [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
- [ ] Did you read the contributor guideline?
- [ ] Did you read our philosophy doc (important for complex PRs)?
- [ ] Was this discussed/approved via a GitHub issue or the forum? Please add a link to it if that's the case.
- [ ] Did you make sure to update the documentation with your changes? Here are the documentation guidelines, and here are tips on formatting docstrings.
- [ ] Did you write any new necessary tests?
Who can review?
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR.
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.
