Skip to content

docs: revamp ecosystem page, restructure training tutorials#683

Merged
bxyu-nvidia merged 25 commits intomainfrom
cwing/ecosystem
Feb 13, 2026
Merged

docs: revamp ecosystem page, restructure training tutorials#683
bxyu-nvidia merged 25 commits intomainfrom
cwing/ecosystem

Conversation

@cwing-nvidia
Copy link
Copy Markdown
Contributor

resolves #557

Summary

  • Rewrite ecosystem page: now covering training framework integrations (NeMo RL, TRL, Unsloth, OpenRLHF), environment library integrations (Reasoning Gym, Aviary, etc.), and related NeMo libraries
  • Move training tutorials from docs/tutorials/ to docs/training-tutorials/ for clearer separation from environment tutorials
  • Simplify the home page training section to use category-level cards (RL/GRPO and SFT/DPO) instead of per-framework cards
  • Fix broken cross-references caused by the file moves

Test plan

  • Build docs locally (make docs) and verify no broken links
  • Verify all toctree entries resolve correctly
  • Check that training-tutorials index, ecosystem, and home page render consistently

lbliii and others added 15 commits January 30, 2026 16:30
Signed-off-by: Lawrence Lane <llane@nvidia.com>
Signed-off-by: Lawrence Lane <llane@nvidia.com>
Signed-off-by: Lawrence Lane <llane@nvidia.com>
Signed-off-by: Lawrence Lane <llane@nvidia.com>
Simplify intro to emphasize goal of supporting broad set of RL training
frameworks and environment libraries. Add contribution invite with link
to issue template. Remove unnecessary tip box for new users.

Signed-off-by: Chris Wing <cwing@nvidia.com>
- Move model recipes (Nemotron Nano, Super) to new docs/model-recipes/ section
- Simplify training framework integrations list in ecosystem page
- Rename "Unsloth Training" to "Unsloth" for consistency
- Update toctree to add Model Recipes section after Training Tutorials

Signed-off-by: Chris Wing <cwing@nvidia.com>
- Remove verl.md and nemo-customizer.md pages (not ready yet)
- Reorganize training-tutorials/index.md with cleaner card layout
- Add OpenRLHF card linking to external integration
- Mark VeRL and NeMo Customizer as "Coming soon" with in-progress badges
- Remove card descriptions for consistency, add SFT & DPO section
- Reorder cards to match ecosystem page

Signed-off-by: Chris Wing <cwing@nvidia.com>
- Rename page to "Agentic RL Ecosystem"
- Simplify training framework list with specific tutorial descriptions
- Condense environment library integrations with README link
- Reframe NeMo libraries section as "related tools for your workflow"
- Remove redundant sections (community, building custom environments)
- Update RL framework integration guide to link to training tutorials index

Signed-off-by: Chris Wing <cwing@nvidia.com>
- Move nemo-rl-grpo/, unsloth-training.md, offline-training-w-rollouts.md
  from tutorials/ to training-tutorials/
- Update all cross-references across docs

Signed-off-by: Chris Wing <cwing@nvidia.com>
- Add descriptions to training framework grid cards on training-tutorials page
- Refine ecosystem page and model-recipes intro
- Update cross-references and nav (index, tutorials, data, get-started)
- Remove nemotron-super recipe

Signed-off-by: Chris Wing <cwing@nvidia.com>
# Conflicts:
#	docs/environment-tutorials/multi-node-docker.md
#	docs/index.md
#	docs/training-tutorials/index.md
@cwing-nvidia cwing-nvidia force-pushed the cwing/ecosystem branch 2 times, most recently from 3a31fed to c7620b7 Compare February 12, 2026 23:56
Files moved from docs/tutorials/ to docs/training-tutorials/ during the
integrations-content merge left stale cross-references in six files.

Signed-off-by: Chris Wing <cwing@nvidia.com>
Signed-off-by: Chris Wing <cwing@nvidia.com>
Replace per-framework cards with category-level cards (RL/GRPO and
SFT/DPO) to avoid playing favorites and scale as frameworks are added.

Signed-off-by: Chris Wing <cwing@nvidia.com>
- Fix ecosystem card badge (nemo-framework → ecosystem/integrations)
- Fix typo: mult-node → multi-node in training-tutorials index
- Fix TRL badge from primary to secondary for consistency
- Fix stale link in nemo-rl-grpo to creating-training-environment
- Remove duplicate training content from tutorials/index.md

Signed-off-by: Chris Wing <cwing@nvidia.com>
…ting-resource-server

- Fix multi-node-training.md link to creating-resource-server (now points to /environment-tutorials/creating-training-environment)
- Fix creating-resource-server.md link to offline-training-w-rollouts (now uses absolute path)

Signed-off-by: Chris Wing <cwing@nvidia.com>
cwing-nvidia and others added 4 commits February 12, 2026 16:09
- Wrap SFT & DPO card in grid container in training-tutorials/index.md
- Remove trailing transition (---) from tutorials/index.md
- Remove multi-verifier-training.md (will be added in a separate PR)

Signed-off-by: Chris Wing <cwing@nvidia.com>
…DME tables

These servers (Reasoning Gym, Aviary, Xlam FC, Math With Code) lack
huggingface_identifier in their configs, causing the update-readme-table
pre-commit hook to fail.

Signed-off-by: Chris Wing <cwing@nvidia.com>
@lbliii lbliii self-requested a review February 13, 2026 14:29
lbliii
lbliii previously approved these changes Feb 13, 2026
…ecosystem

Signed-off-by: Brian Yu <bxyu@nvidia.com>
@bxyu-nvidia bxyu-nvidia merged commit 9749997 into main Feb 13, 2026
6 checks passed
@bxyu-nvidia bxyu-nvidia deleted the cwing/ecosystem branch February 13, 2026 20:27
fsiino-nvidia pushed a commit that referenced this pull request Feb 21, 2026
resolves #557

## Summary

- Rewrite ecosystem page: now covering training framework integrations
(NeMo RL, TRL, Unsloth, OpenRLHF), environment library integrations
(Reasoning Gym, Aviary, etc.), and related NeMo libraries
- Move training tutorials from `docs/tutorials/` to
`docs/training-tutorials/` for clearer separation from environment
tutorials
- Simplify the home page training section to use category-level cards
(RL/GRPO and SFT/DPO) instead of per-framework cards
- Fix broken cross-references caused by the file moves

## Test plan

- [ ] Build docs locally (`make docs`) and verify no broken links
- [ ] Verify all toctree entries resolve correctly
- [ ] Check that training-tutorials index, ecosystem, and home page
render consistently

---------

Signed-off-by: Lawrence Lane <llane@nvidia.com>
Signed-off-by: Chris Wing <cwing@nvidia.com>
Signed-off-by: Brian Yu <bxyu@nvidia.com>
Co-authored-by: Lawrence Lane <llane@nvidia.com>
Co-authored-by: Brian Yu <bxyu@nvidia.com>
fsiino-nvidia pushed a commit that referenced this pull request Feb 21, 2026
resolves #557

## Summary

- Rewrite ecosystem page: now covering training framework integrations
(NeMo RL, TRL, Unsloth, OpenRLHF), environment library integrations
(Reasoning Gym, Aviary, etc.), and related NeMo libraries
- Move training tutorials from `docs/tutorials/` to
`docs/training-tutorials/` for clearer separation from environment
tutorials
- Simplify the home page training section to use category-level cards
(RL/GRPO and SFT/DPO) instead of per-framework cards
- Fix broken cross-references caused by the file moves

## Test plan

- [ ] Build docs locally (`make docs`) and verify no broken links
- [ ] Verify all toctree entries resolve correctly
- [ ] Check that training-tutorials index, ecosystem, and home page
render consistently

---------

Signed-off-by: Lawrence Lane <llane@nvidia.com>
Signed-off-by: Chris Wing <cwing@nvidia.com>
Signed-off-by: Brian Yu <bxyu@nvidia.com>
Co-authored-by: Lawrence Lane <llane@nvidia.com>
Co-authored-by: Brian Yu <bxyu@nvidia.com>
fsiino-nvidia pushed a commit that referenced this pull request Feb 21, 2026
resolves #557

## Summary

- Rewrite ecosystem page: now covering training framework integrations
(NeMo RL, TRL, Unsloth, OpenRLHF), environment library integrations
(Reasoning Gym, Aviary, etc.), and related NeMo libraries
- Move training tutorials from `docs/tutorials/` to
`docs/training-tutorials/` for clearer separation from environment
tutorials
- Simplify the home page training section to use category-level cards
(RL/GRPO and SFT/DPO) instead of per-framework cards
- Fix broken cross-references caused by the file moves

## Test plan

- [ ] Build docs locally (`make docs`) and verify no broken links
- [ ] Verify all toctree entries resolve correctly
- [ ] Check that training-tutorials index, ecosystem, and home page
render consistently

---------

Signed-off-by: Lawrence Lane <llane@nvidia.com>
Signed-off-by: Chris Wing <cwing@nvidia.com>
Signed-off-by: Brian Yu <bxyu@nvidia.com>
Co-authored-by: Lawrence Lane <llane@nvidia.com>
Co-authored-by: Brian Yu <bxyu@nvidia.com>
Signed-off-by: Frankie Siino <fsiino@nvidia.com>
abubakaria56 pushed a commit to abubakaria56/Gym that referenced this pull request Mar 2, 2026
…eMo#683)

resolves NVIDIA-NeMo#557 

## Summary

- Rewrite ecosystem page: now covering training framework integrations
(NeMo RL, TRL, Unsloth, OpenRLHF), environment library integrations
(Reasoning Gym, Aviary, etc.), and related NeMo libraries
- Move training tutorials from `docs/tutorials/` to
`docs/training-tutorials/` for clearer separation from environment
tutorials
- Simplify the home page training section to use category-level cards
(RL/GRPO and SFT/DPO) instead of per-framework cards
- Fix broken cross-references caused by the file moves

## Test plan

- [ ] Build docs locally (`make docs`) and verify no broken links
- [ ] Verify all toctree entries resolve correctly
- [ ] Check that training-tutorials index, ecosystem, and home page
render consistently

---------

Signed-off-by: Lawrence Lane <llane@nvidia.com>
Signed-off-by: Chris Wing <cwing@nvidia.com>
Signed-off-by: Brian Yu <bxyu@nvidia.com>
Co-authored-by: Lawrence Lane <llane@nvidia.com>
Co-authored-by: Brian Yu <bxyu@nvidia.com>
abubakaria56 pushed a commit to abubakaria56/Gym that referenced this pull request Mar 2, 2026
…eMo#683)

resolves NVIDIA-NeMo#557 

## Summary

- Rewrite ecosystem page: now covering training framework integrations
(NeMo RL, TRL, Unsloth, OpenRLHF), environment library integrations
(Reasoning Gym, Aviary, etc.), and related NeMo libraries
- Move training tutorials from `docs/tutorials/` to
`docs/training-tutorials/` for clearer separation from environment
tutorials
- Simplify the home page training section to use category-level cards
(RL/GRPO and SFT/DPO) instead of per-framework cards
- Fix broken cross-references caused by the file moves

## Test plan

- [ ] Build docs locally (`make docs`) and verify no broken links
- [ ] Verify all toctree entries resolve correctly
- [ ] Check that training-tutorials index, ecosystem, and home page
render consistently

---------

Signed-off-by: Lawrence Lane <llane@nvidia.com>
Signed-off-by: Chris Wing <cwing@nvidia.com>
Signed-off-by: Brian Yu <bxyu@nvidia.com>
Co-authored-by: Lawrence Lane <llane@nvidia.com>
Co-authored-by: Brian Yu <bxyu@nvidia.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

docs: add integrations section to README and ecosystem docs

3 participants