Add initial blog post for nvForest by btepera · Pull Request #211 · rapidsai/nvforest

btepera · 2026-09-04T03:34:52Z

Adds new blog tab to the nvForest docs and includes draft of initial blog post.

copy-pr-bot · 2026-09-04T03:34:55Z

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

coderabbitai · 2026-09-04T03:38:41Z

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Repository: rapidsai/nvforest/.coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 59514c8d-eaff-433f-9c63-99eb60167beb

📥 Commits

Reviewing files that changed from the base of the PR and between e50bc52 and e80e3cb.

📒 Files selected for processing (1)

docs/source/getting_started.rst

🚧 Files skipped from review as they are similar to previous changes (1)

docs/source/getting_started.rst

Included review availability: Your plan provides up to 12 included reviews per hour; 10 remain after this review.

📝 Summary

Summary by CodeRabbit

Documentation
- Added a blog post introducing nvForest, including supported formats, installation, deployment, Python usage, optimization, benchmarks, and migration guidance.
- Added a blog index that organizes dated posts with newest entries first.
- Added the blog to the main documentation navigation.
- Added a reference label for the advanced C++ getting-started section.
- Simplified documentation navigation by limiting its displayed depth.

Walkthrough

The documentation now includes an nvForest announcement blog post, usage guidance, optimization details, benchmark results, migration guidance, and updated Sphinx navigation.

Changes

nvForest documentation

Layer / File(s)	Summary
nvForest blog content `docs/source/blog/2026-09-03-supercharge-tree-inference.rst`	Adds nvForest overview, deployment details, Python and C++ examples, optimization guidance, benchmark results, and FIL migration instructions.
Documentation navigation updates `docs/source/blog/index.rst`, `docs/source/conf.py`, `docs/source/getting_started.rst`, `docs/source/index.rst`	Adds the blog to the documentation navigation, limits navigation depth, and adds a reference target for advanced C++ documentation.

Priority: ⬇️ Low

Estimated code review effort: 2 (Simple) | ~10 minutes

Change: Feature

Suggested reviewers: csadorf, chyunsu3

Merge Risk: ⚪ Minimal · up to e80e3

The documentation integration is correctly connected and has no actionable merge-blocking risk.

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly identifies the primary change: adding the initial nvForest blog post.
Description check	✅ Passed	The description accurately relates to the changes by mentioning the new documentation blog tab and the initial nvForest blog post.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check. Docstring coverage is scoped to functions touched by this diff. Analyzed 0 functions across 1…
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

✨ Finishing Touches 💡 1

🛠️ Fix failing CI checks 💡

Commit to this branch
Create a new PR

🧪 Generate unit tests (beta)

Create a new PR

_{Comment @coderabbitai help to get the list of available commands.}

csadorf

LGTM. Thanks for putting together this initial post and the blog infrastructure. I left three minor comments to clarify the FIL history, migration timeline, and benchmark results.

csadorf · 2026-09-08T11:09:13Z

+We are proud to announce nvForest, a lightweight library for fast inference
+for tree-based models on NVIDIA GPUs. nvForest builds on our past work on the
+`Forest Inference Library (FIL) <https://developer.nvidia.com/blog/supercharge-tree-based-model-inference-with-forest-inference-library-in-nvidia-cuml/>`_,
+which has lived inside cuML until now. With the release of nvForest, this


I'd rather say something like ‘which was previously part of cuML’ or ‘which was previously maintained and distributed in cuML.’

csadorf · 2026-09-08T11:12:26Z

+If you are using FIL today through ``cuml.fil.ForestInference``, you do not
+need to rewrite your code immediately. Going forward,
+``cuml.fil.ForestInference`` will become a lightweight shim that uses
+nvForest underneath and emits a deprecation warning pointing you to nvForest.


I think this needs to lead with the need to migrate. As written, it initially sounds as though users do not need to act and that we will maintain the shim indefinitely; the 26.10 deadline in the next sentence is relatively soon.

+1. cuml.fil.ForestInference is no longer available in cuML 26.10.

csadorf · 2026-09-08T11:18:26Z

+
+   Speedup factor by tree count.
+
+A single NVIDIA H100 (80GB HBM3) was used for GPU results, and a 2-socket


Are the figures showing only GPU results? If so, could we make that explicit? I assume the CPU machine here refers to the RandomForestRegressor.predict baseline comparison, but it is not clear from the surrounding text.

chyunsu3 · 2026-09-22T02:54:45Z

+cuML, scikit-learn, XGBoost, LightGBM, and any other Treelite-compatible
+model. It provides state-of-the-art performance on tree inference, a small


Should we even mention "Treelite" here?

chyunsu3 · 2026-09-22T03:32:26Z

+If you are using FIL today through ``cuml.fil.ForestInference``, you do not
+need to rewrite your code immediately. Going forward,
+``cuml.fil.ForestInference`` will become a lightweight shim that uses
+nvForest underneath and emits a deprecation warning pointing you to nvForest.


+1. cuml.fil.ForestInference is no longer available in cuML 26.10.

add initial blog post for nvForest

e50bc52

btepera requested a review from a team as a code owner September 4, 2026 03:34

csadorf approved these changes Sep 8, 2026

View reviewed changes

Merge branch 'main' into docs_blog

e80e3cb

chyunsu3 added doc Improvements or additions to documentation non-breaking Introduces a non-breaking change labels Sep 18, 2026

chyunsu3 reviewed Sep 22, 2026

View reviewed changes

Navigation Menu

Add initial blog post for nvForest - #211

Add initial blog post for nvForest#211
btepera wants to merge 2 commits into
rapidsai:mainfrom
btepera:docs_blog

btepera commented Sep 4, 2026

Uh oh!

copy-pr-bot Bot commented Sep 4, 2026

Uh oh!

coderabbitai Bot commented Sep 4, 2026 •

edited

Loading

Summary by CodeRabbit

Walkthrough

Changes

Uh oh!

csadorf left a comment

Uh oh!

csadorf Sep 8, 2026

Uh oh!

csadorf Sep 8, 2026

Uh oh!

chyunsu3 Sep 22, 2026

Uh oh!

csadorf Sep 8, 2026

Uh oh!

chyunsu3 Sep 22, 2026

Uh oh!

chyunsu3 Sep 22, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants


		Speedup factor by tree count.

		A single NVIDIA H100 (80GB HBM3) was used for GPU results, and a 2-socket

		cuML, scikit-learn, XGBoost, LightGBM, and any other Treelite-compatible
		model. It provides state-of-the-art performance on tree inference, a small

Conversation

btepera commented Sep 4, 2026

Uh oh!

copy-pr-bot Bot commented Sep 4, 2026

Uh oh!

coderabbitai Bot commented Sep 4, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary by CodeRabbit

Walkthrough

Changes

Uh oh!

csadorf left a comment

Choose a reason for hiding this comment

Uh oh!

csadorf Sep 8, 2026

Choose a reason for hiding this comment

Uh oh!

csadorf Sep 8, 2026

Choose a reason for hiding this comment

Uh oh!

chyunsu3 Sep 22, 2026

Choose a reason for hiding this comment

Uh oh!

csadorf Sep 8, 2026

Choose a reason for hiding this comment

Uh oh!

chyunsu3 Sep 22, 2026

Choose a reason for hiding this comment

Uh oh!

chyunsu3 Sep 22, 2026

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

coderabbitai Bot commented Sep 4, 2026 •

edited

Loading