Skip to content

Conversation

@salexspb
Copy link
Contributor

Summary:
This Predictor provides threadsafe interface and also
cleans-up activations after each run. So in multi-model setup
activation space doesn't explode

Differential Revision: D9842374

Summary:
This Predictor provides threadsafe interface and also
cleans-up activations after each run. So in multi-model setup
activation space doesn't explode

Differential Revision: D9842374

fbshipit-source-id: de618455a093bc565c191b16e29baf1c592610b4
@salexspb salexspb closed this Sep 17, 2018
salexspb added a commit to salexspb/pytorch that referenced this pull request Sep 17, 2018
Summary:
Pull Request resolved: pytorch#11731

This Predictor provides threadsafe interface and also
cleans-up activations after each run. So in multi-model setup
activation space doesn't explode

Reviewed By: highker

Differential Revision: D9842374

fbshipit-source-id: 4c50b9000bc904fd217d40939a35ea5b2b0fca01
facebook-github-bot pushed a commit that referenced this pull request Sep 19, 2018
Summary:
Pull Request resolved: #11779

Pull Request resolved: #11731

This Predictor provides threadsafe interface and also
cleans-up activations after each run. So in multi-model setup
activation space doesn't explode

Reviewed By: highker

Differential Revision: D9842374

fbshipit-source-id: bfe253ae5fc813e73a347c5147ff6b58d50781ea
@ezyang ezyang added the merged label Jun 26, 2019
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants