Skip to content

Add a cache option for infer mode #70

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
Closed
wants to merge 10 commits into from
Closed

Add a cache option for infer mode #70

wants to merge 10 commits into from

Conversation

@blisc
Copy link
Collaborator

@blisc blisc commented Oct 25, 2019

Add initial compatibility for caching inference results so we don't repeat forward pass multiple times. Will improve efficiency of #67
Adds two options to neural_factory.infer():

  • cache: Cache all tensors during this forward pass
  • use_cache: Use cache during this forward pass

Currently, only implemented for single GPU.

@blisc blisc changed the title WIP: Add a cache option for infer mode [WIP] Add a cache option for infer mode Oct 25, 2019
@blisc blisc changed the title [WIP] Add a cache option for infer mode Add a cache option for infer mode Oct 25, 2019
@blisc blisc closed this Oct 25, 2019
@blisc blisc deleted the infer_cache branch November 8, 2019 21:48
blisc added a commit that referenced this pull request May 5, 2025
@blisc
add update config to infer script (#70)
db801cb 
* add update config to infer script

Signed-off-by: Jason <[email protected]>

* Update infer_and_evaluate.py

---------

Signed-off-by: Jason <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@blisc