docs: add H200 and B200 to GPU architecture detection list

[ntheanh201]

Summary

The README's platform/GPU detection feature list omitted H200 and B200, even though both are supported: both have entries in the GPU defaults table (pkg/catalog/entries/_lib/gpu-defaults.yaml), and docs/concepts/catalog.md already states "Supported GPU architectures include GB200, GB300, H100, H200, and B200". The stale list made an on-prem HGX H200 cluster look unsupported at first glance — it is not (verified there).

Related Issue

Trivial docs fix, exempt per the template.

Type of Change

• 📚 Documentation

Component(s) Affected

• Documentation / CI

Testing

• Tests pass locally (docs-only change; no code paths affected)
• Manual testing completed — verified against a live 3-node on-prem HGX H200 cluster: nodes labeled nvidia.com/gpu.product: NVIDIA-H200 are detected, and nvcrectl certification render --platform onprem for communication/nccl-all-reduce renders a valid 3-node × 8-GPU Workflow
• No breaking changes (or documented)

Checklist

• Self-review completed
• Commits are signed off for the DCO (git commit -s)
• make manifests generate run (if *_types.go was modified) — n/a
• Golden files updated (if integration test output changed) — n/a
• Documentation updated (if needed) — this is the documentation
• Ready for review

[copy-pr-bot]

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]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: fd49368e-56b2-4a47-9075-0a85254362a5

📥 Commits

Reviewing files that changed from the base of the PR and between 0e82a8d and 93206e0.

📒 Files selected for processing (1)

• README.md

Included review availability: Your plan provides up to 12 included reviews per hour; 11 remain after this review.

---

📝 Walkthrough

Walkthrough

The README Features section now lists the L40S GPU architecture with the previously documented supported architectures.

Estimated code review effort: 1 (Trivial) | ~2 minutes

Merge Risk: 🟡 Moderate · up to 93206

The README adds L40S rather than the requested H200 and B200 entries, leaving the intended GPU architecture documentation incomplete and potentially misleading users about supported hardware.

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Title check	⚠️ Warning	The title describes adding H200 and B200, but the summarized change adds L40S to the README feature list. The title does not identify the architecture documented by the change.	Update the title to state that the README adds L40S to the supported GPU architecture list.

✅ Passed checks (4 passed)

Check name	Status	Explanation
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 0…
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.
Description check	✅ Passed	The description concerns the README GPU architecture detection list and a documentation-only change. It is related to the changed area, although it names H200 and B200 while the file summary identifie…

• Fix all pre-merge checks with AI

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

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