Distributed Deep Neural Network Training Framework
Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training
FlexFlow is a Deep Neural Network (DNN) framework that automatically discovers fast parallelization strategies for distributed DNN training. It goes beyond traditional methods like data and model parallelism by exploring various parallelization opportunities across Samples, Operators, Attributes, and Parameters. FlexFlow features a unique execution simulator to quantify the runtime performance of different strategies and employs an automated search algorithm to identify highly optimized approaches that typically exceed the performance of manually designed strategies. This framework allows for flexible DNN training through combinations of dimension-based parallelization.
{{ ui.publicListPage.ownerName }}
{{ ui.publicListPage.meta.description }}
This collection is empty.
Нажмите «Порядок» вверху, перетащите элементы, затем снова «Порядок» (готово). Порядок сохраняется автоматически.
Appearance
General
UID: {{ user.id }}
Sign in from your profile to sync lists and saved items.
dStore {{ version }}
Пока нет листов — создайте новый ниже.
{{ pocketNoteSubjectLabel }}
Выделите текст — над ним появится панель форматирования.
{{ publicListShareUrl(user.lists[ui.list.editingListId]) }}
No results found
Try another name or paste a Telegram link, e.g. t.me/liberwsbot
Список серий пока недоступен.
Version {{update.version}} {{update.date ? moment(update.date).format('LL') : ''}}
