Re:Introduction to Google Cloud Functions
by tedk-42 on Wednesday November 04, 2020 @07:07AM
(#24988293)
You got the wrong idea about serverless if you think it should have a GPU attached to run your ML dataset.
Generally speaking, you want it to do something simple and quickly
Re:Introduction to Google Cloud Functions
by tuvan on Wednesday November 04, 2020 @08:56AM
(#24989060)
GPU can also help with inference. I think running a cloud function to evaluate an input on a pretrained model seems like a good use case.
Re:Introduction to Google Cloud Functions
by panabee on Wednesday November 04, 2020 @02:04PM
(#24991961)
For inference, not training. Sorry for the confusion.
Re:Introduction to Google Cloud Functions
by adwww on Wednesday November 04, 2020 @07:08AM
(#24988294)
Also the request timeout needs to be raised.
I have a few workloads that execute only very infrequently, which makes them suitable for functions, except when they do run they sometimes exceed the 10 minute timeout.
Re:Introduction to Google Cloud Functions
by tlarkworthy on Wednesday November 04, 2020 @08:08AM
(#24988642)
Cloud Run has 1 hour timeout in Beta https://cloud.google.com/run/docs/configuring/request-timeou...
Re:Introduction to Google Cloud Functions
by smashah on Wednesday November 04, 2020 @05:53AM
(#24987956)
What do you mean by file limit? I made a GCF service to handle 400mb+ video files
Re:Introduction to Google Cloud Functions
by bttrfl on Wednesday November 04, 2020 @05:59AM
(#24987986)
Not OP, but perhaps he meant size of data passed directly in a request which is indeed 10MB: https://cloud.google.com/functions/quotas
I don't think I had any issues loading larger files from Storage either.
If Google could ever lift these restrictions, GCF would be perfect for auto-scaling ML models.