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

Document ability to export cuML RF to predict on other machines #3890

Merged
merged 2 commits into from
May 28, 2021
Merged

Document ability to export cuML RF to predict on other machines #3890

merged 2 commits into from
May 28, 2021

Conversation

hcho3
Copy link
Contributor

@hcho3 hcho3 commented May 21, 2021

@review-notebook-app
Copy link

Check out this pull request on  ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.

Powered by ReviewNB

@dantegd dantegd added doc Documentation non-breaking Non-breaking change labels May 22, 2021
dantegd
dantegd requested changes May 22, 2021
View reviewed changes
Copy link
Member

@dantegd dantegd left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The notebook addition looks great!, Just requested a link from the main docstrings

docs/source/pickling_cuml_models.ipynb
"cell_type": "markdown",
"metadata": {},
"source": [
"Starting with cuML version 21.06, you can export cuML Random Forest models and run predictions with them on machines without an NVIDIA GPUs. The [Treelite](https://github.com/dmlc/treelite) package defines an efficient exchange format that lets you portably move the cuML Random Forest models to other machines. We will refer to the exchange format as \"checkpoints.\"\n",
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think adding a link to here from the main docstring of the RF classes (with a note like RF classes can be exported to Treelite for inference on machines without GPUs or so) would be useful for people looking at the api docs

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done

@dantegd dantegd added the 4 - Waiting on Author Waiting for author to respond to review label May 22, 2021
@hcho3 hcho3 requested a review from a team as a code owner May 27, 2021 04:57
@github-actions github-actions bot added the Cython / Python Cython or Python issue label May 27, 2021
dantegd
dantegd approved these changes May 27, 2021
View reviewed changes
Copy link
Member

@dantegd dantegd left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

lgtm

@dantegd dantegd added 5 - Ready to Merge Testing and reviews complete, ready to merge and removed 4 - Waiting on Author Waiting for author to respond to review labels May 27, 2021
@dantegd
Copy link
Member

dantegd commented May 28, 2021

rerun tests

@dantegd
Copy link
Member

dantegd commented May 28, 2021

@gpucibot merge

@hcho3
Copy link
Contributor Author

hcho3 commented May 28, 2021

rerun tests

@codecov-commenter
Copy link

Codecov Report

❗ No coverage uploaded for pull request base (branch-21.06@cb6ef52). Click here to learn what that means.
The diff coverage is n/a.

Impacted file tree graph

@@               Coverage Diff               @@
##             branch-21.06    #3890   +/-   ##
===============================================
  Coverage                ?   85.42%           
===============================================
  Files                   ?      226           
  Lines                   ?    17271           
  Branches                ?        0           
===============================================
  Hits                    ?    14754           
  Misses                  ?     2517           
  Partials                ?        0
Flag Coverage Δ
dask 48.99% <0.00%> (?)
non-dask 77.39% <0.00%> (?)

Flags with carried forward coverage won't be shown. Click here to find out more.

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update cb6ef52...52d0301. Read the comment docs.

@rapids-bot rapids-bot bot merged commit 5af84b3 into rapidsai:branch-21.06 May 28, 2021
@hcho3 hcho3 deleted the doc_export_treelite branch May 29, 2021 00:14
vimarsh6739 pushed a commit to vimarsh6739/cuml that referenced this pull request Oct 9, 2023
@hcho3
Document ability to export cuML RF to predict on other machines (rapi…
8ae8aca 
…dsai#3890)

See rapidsai#3853 (comment)

Authors:
  - Philip Hyunsu Cho (https://github.com/hcho3)

Approvers:
  - Dante Gama Dessavre (https://github.com/dantegd)

URL: rapidsai#3890
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@dantegd dantegd dantegd approved these changes

Assignees
No one assigned
Labels
5 - Ready to Merge Testing and reviews complete, ready to merge Cython / Python Cython or Python issue doc Documentation non-breaking Non-breaking change
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@hcho3 @dantegd @codecov-commenter