Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[BUG] Test Obsei in GPU environment #73

Closed
lalitpagaria opened this issue Apr 1, 2021 · 1 comment · Fixed by #87
Closed

[BUG] Test Obsei in GPU environment #73

lalitpagaria opened this issue Apr 1, 2021 · 1 comment · Fixed by #87
Assignees
@GirishPatel
Labels
bug Something isn't working high priority

Comments

@lalitpagaria
Copy link
Collaborator

No description provided.

@lalitpagaria lalitpagaria added the bug Something isn't working label Apr 1, 2021
@lalitpagaria
Copy link
Collaborator Author

lalitpagaria commented Apr 3, 2021 •
edited

@GirishPatel
We need to pass a device parameter to pipeline and it will automatically leverage GPU.
https://discuss.huggingface.co/t/pytorch-nlp-model-doesn-t-use-gpu-when-making-inference/1160/3

https://huggingface.co/transformers/main_classes/pipelines.html

So we have two choice. Either add variable a variable use_gpu in all transformer's based analyzer class. So use can control whether they want to use GPU or not. Default should be use GPU as CPU so it will work for all platforms. Let me know WDYT?

Sample https://github.com/deepset-ai/haystack/blob/master/haystack/summarizer/transformers.py

@GirishPatel GirishPatel mentioned this issue Apr 18, 2021
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@GirishPatel GirishPatel

Labels
bug Something isn't working high priority
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Added GPU support in analyzers GirishPatel/obsei
2 participants
@GirishPatel @lalitpagaria