transformers
[offload] respect `max_memory` argument when factoring in unused reserved memory
#37982
Merged

[offload] respect `max_memory` argument when factoring in unused reserved memory #37982

gante merged 4 commits into huggingface:main from gante:respect_max_memory
gante
gante respect user arg
f10854cd
github-actions github-actions marked this pull request as draft 1 year ago
github-actions
gante gante requested a review from ydshieh ydshieh 1 year ago
gante gante requested a review from Cyrilvallez Cyrilvallez 1 year ago
gante gante marked this pull request as ready for review 1 year ago
HuggingFaceDocBuilderDev
gante None check
4eefa97d
gante take recent changes
01a92a23
ydshieh
ydshieh approved these changes on 2025-05-06
gante gante changed the title [offload] respect `max_memory` argument [offload] respect `max_memory` argument when factoring in unused reserved memory 1 year ago
gante comments
8ae6a1b4
Cyrilvallez
Cyrilvallez approved these changes on 2025-05-06
gante gante merged a9384f84 into main 1 year ago
gante gante deleted the respect_max_memory branch 1 year ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone