pytorch/ignite

Support for TorchSnapshot for efficient checkpoint saving and loading

Open

#2,752 创建于 2022年10月24日

在 GitHub 查看
 (3 评论) (0 反应) (0 负责人)Python (4,313 star) (602 fork)batch import
enhancementhelp wanted

描述

🚀 Feature

TorchSnapshot is a performant, memory-efficient checkpointing library for PyTorch applications, designed with large, complex distributed workloads in mind. It includes many optimizations to control for memory usage and optimize checkpoint writing for DDP-style workloads over torch.save/torch.load. For more information, please check out the readme: https://github.com/pytorch/torchsnapshot#why-torchsnapshot

This could be a nice addition to Ignite, similar to the existing Checkpoint handler

cc @yifuwang

贡献者指南

技术栈
python
领域
machine learning
议题类型
feature
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
3
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
3-5 days
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
stale
清晰度议题是否清楚说明期望改动、验收标准和下一步。
clear
前置要求
PyTorch Ignite basicsUnderstanding of checkpointing concepts
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
30
研究方向
Start by reviewing the existing Checkpoint handler in pytorch/ignite (likely in ignite/handlers/checkpoint.py) to understand the current implementation. Then explore the TorchSnapshot documentation and examples to understand its API and how it could replace or augment the current checkpointing. Consider contributing by implementing a new handler or modifying the existing one to support TorchSnapshot, similar to how Ignite handles other saving methods. Discuss design in the issue comments with maintainers before proceeding.