docs: Revise news section for nemotron v3 and DAPO algorithm support#1640
docs: Revise news section for nemotron v3 and DAPO algorithm support#1640
Conversation
Updated news section with nemotron v3 and new DAPO algorithm support details and adjusted formatting. Signed-off-by: Wenwen Gao <94138584+snowmanwwg@users.noreply.github.com>
📝 WalkthroughWalkthroughThe README.md file has been updated to reorganize and add news items. Changes include introducing a new "Previous News" collapsible section, adding a NeMo-RL training announcement, restructuring a DAPO-related entry, and moving older news items. Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~5 minutes
Possibly related PRs
Suggested labels
Suggested reviewers
Pre-merge checks and finishing touches✅ Passed checks (4 passed)
✨ Finishing touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
README.md (1)
15-16: Address pre-existing markdown indentation violations (MD007).The linter flags unordered list indentation issues on lines 15, 16, and 21. While these lines are not part of your current changeset, fixing them now would improve overall markdown compliance. Markdown best practice requires 2-space indentation for nested lists, not 4 spaces.
Apply this diff to fix the indentation:
* [12/1/2025] [Release v0.4.0!](https://github.com/NVIDIA-NeMo/RL/releases/tag/v0.4.0) - * First release with official NGC Container [nvcr.io/nvidia/nemo-rl:v0.4.0](https://registry.ngc.nvidia.com/orgs/nvidia/containers/nemo-rl/tags). - * 📊 View the release run metrics on [Google Colab](https://colab.research.google.com/drive/1u5lmjHOsYpJqXaeYstjw7Qbzvbo67U0v?usp=sharing) to get a head start on your experimentation. + * First release with official NGC Container [nvcr.io/nvidia/nemo-rl:v0.4.0](https://registry.ngc.nvidia.com/orgs/nvidia/containers/nemo-rl/tags). + * 📊 View the release run metrics on [Google Colab](https://colab.research.google.com/drive/1u5lmjHOsYpJqXaeYstjw7Qbzvbo67U0v?usp=sharing) to get a head start on your experimentation. * [9/27/2025] [FP8 Quantization in NeMo RL](https://github.com/NVIDIA-NeMo/RL/discussions/1216) * [9/25/2025] On-policy Distillation - * Student generates on-policy sequences and aligns logits to a larger teacher via KL, achieving near-larger-model quality at lower cost than RL. See [On-policy Distillation](#on-policy-distillation). + * Student generates on-policy sequences and aligns logits to a larger teacher via KL, achieving near-larger-model quality at lower cost than RL. See [On-policy Distillation](#on-policy-distillation).Per markdownlint MD007 rule, while these are pre-existing in the file, addressing them now would align with the tooling and prevent future lint failures.
Also applies to: 21-21
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
README.md(1 hunks)
🧰 Additional context used
📓 Path-based instructions (1)
!(**/tests/**|**/test_*.py|**/test_*.sh)
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
Add the NVIDIA copyright header to all Python files and shell scripts (excluding tests). The header should include the current year
Files:
README.md
🪛 markdownlint-cli2 (0.18.1)
README.md
15-15: Unordered list indentation
Expected: 2; Actual: 4
(MD007, ul-indent)
16-16: Unordered list indentation
Expected: 2; Actual: 4
(MD007, ul-indent)
21-21: Unordered list indentation
Expected: 2; Actual: 4
(MD007, ul-indent)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (8)
- GitHub Check: build-container / main
- GitHub Check: sphinx-build / Build docs
- GitHub Check: Lint check
- GitHub Check: sphinx-build / Build docs
- GitHub Check: build-container / main
- GitHub Check: Lint check
- GitHub Check: Post automodel integration comment / Comment on PR
- GitHub Check: Post submodule check comment / Comment on PR
🔇 Additional comments (3)
README.md (3)
13-13: LGTM: Announce NeMo-RL's Nemotron v3 training achievement.The new announcement effectively highlights NeMo-RL's role in training a production model and provides a direct link to reproducible code. This is a valuable addition to the news section.
17-18: LGTM: DAPO section consolidation improves readability.Restructuring the DAPO announcement from two separate bullets into a single, comprehensive entry with linked extensions and reference documentation is an improvement. The content clearly describes the algorithm's features and provides actionable next steps via the guide link.
26-26: LGTM: Previous News section organized with GCP acceleration announcement.Adding the 9/30/2025 GCP acceleration announcement to a collapsible "Previous News" section helps keep the active news prominent while preserving historical context. The date and link formatting align with existing patterns.
Signed-off-by: Wenwen Gao <94138584+snowmanwwg@users.noreply.github.com>
…VIDIA-NeMo#1640) Signed-off-by: Wenwen Gao <94138584+snowmanwwg@users.noreply.github.com>
…VIDIA-NeMo#1640) Signed-off-by: Wenwen Gao <94138584+snowmanwwg@users.noreply.github.com> Signed-off-by: Parth Mannan <pmannan@nvidia.com>
…VIDIA-NeMo#1640) Signed-off-by: Wenwen Gao <94138584+snowmanwwg@users.noreply.github.com> Signed-off-by: yuanhangs <yuanhangs@nvidia.com>
…VIDIA-NeMo#1640) Signed-off-by: Wenwen Gao <94138584+snowmanwwg@users.noreply.github.com> Signed-off-by: yuanhangs <yuanhangs@nvidia.com>
…1640) Signed-off-by: Wenwen Gao <94138584+snowmanwwg@users.noreply.github.com>
…1640) Signed-off-by: Wenwen Gao <94138584+snowmanwwg@users.noreply.github.com>
…1640) Signed-off-by: Wenwen Gao <94138584+snowmanwwg@users.noreply.github.com>
Updated news section with nemotron v3 and new DAPO algorithm support details and adjusted formatting.
What does this PR do ?
Add a one line overview of what this PR aims to accomplish.
Issues
List issues that this PR closes (syntax):
Usage
# Add a code snippet demonstrating how to use thisBefore your PR is "Ready for review"
Pre checks:
Additional Information
Summary by CodeRabbit
Documentation
✏️ Tip: You can customize this high-level summary in your review settings.