search

walkwithfastai / walkwithfastai.github.io

Host for https://walkwithfastai.com
Other
143 stars 53 forks source link

Integrate koila to avoid CUDA OOM errors #52

Open manisnesan opened 2 years ago

manisnesan commented 2 years ago

@muellerzr Adding this issue based on fastai-dev discussion . I would like to use this issue to learn about callbacks. I liked your idea about having a MemoryMangerCallback callback for this purpose.

https://twitter.com/jeanmarcalkazzi/status/1465418318068781062?s=20 https://github.com/rentruewang/koila

self-assign

muellerzr commented 2 years ago

Hey @manisnesan, how are we doing with this? :)

manisnesan commented 2 years ago

@muellerzr - Spent some time studying about callbacks. I will be making progress on this (mostly this week).

manisnesan commented 2 years ago

One potential issue with koila integration is it requires min python version >=3.8 https://github.com/rentruewang/koila/blob/v0.1.1/setup.py#L28