[rhaiis] Add presets for benchmark, cluster, and model aliases - #164
Conversation
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (7)
💤 Files with no reviewable changes (1)
🚧 Files skipped from review as they are similar to previous changes (4)
📝 WalkthroughWalkthroughRHAIIS orchestration now uses updated workload sizing, benchmark and cluster presets, runtime defaults, and an expanded model preset catalog. The agent analysis URL is cleared, and new model and quantization variants are added. ChangesRHAIIS orchestration configuration
Estimated code review effort: 2 (Simple) | ~10 minutes Possibly related PRs
Suggested labels: Suggested reviewers: 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 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 |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@projects/rhaiis/orchestration/presets.d/clusters.yaml`:
- Around line 5-10: Update prepare() to consume the plural
rhaiis.deploy.image_pull_secrets configuration instead of reading only
image_pull_secret, normalize its values into the validation input, and validate
every configured secret. Keep the CLI/config option shape and naming consistent
with this plural key so preset and command-line configurations follow the same
path.
In `@projects/rhaiis/orchestration/presets.d/presets.yaml`:
- Around line 192-203: Update the model_key values for the short aliases
nemotron-70b and nemotron3nano-30b to reference their corresponding -fp8 keys,
matching the existing nemotron-70b-fp8 and nemotron3nano-30b-fp8 entries. Leave
the explicit FP8 aliases unchanged.
🪄 Autofix
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro Plus
Run ID: 8672d424-2d62-4576-8d71-b3914969348a
📒 Files selected for processing (6)
projects/rhaiis/orchestration/config.d/rhaiis.yamlprojects/rhaiis/orchestration/config.d/workloads.yamlprojects/rhaiis/orchestration/presets.d/benchmarks.yamlprojects/rhaiis/orchestration/presets.d/clusters.yamlprojects/rhaiis/orchestration/presets.d/mehulvalidation.yamlprojects/rhaiis/orchestration/presets.d/presets.yaml
💤 Files with no reviewable changes (1)
- projects/rhaiis/orchestration/presets.d/mehulvalidation.yaml
|
/test fournos rhaiis nvidia benchmark hera ci-quick |
🔴 Submission of
|
Add new preset files to reduce boilerplate in FournosJob configs: - benchmarks.yaml: common benchmark settings (run_benchmark, profiler, dashboard, agent_analysis, slack_notify_always) - clusters.yaml: hera/zeus cluster configs (cluster_tag, image_pull_secrets, fs_group) - presets.yaml: expand model aliases to cover all models in models.yaml with short names defaulting to FP8 variants, add ci-quick preset with qwen3-0.6b/TP1 for fast validation runs Also remove unused top-level images fallback from rhaiis.yaml since all engines define their own images, and delete stale mehulvalidation.yaml preset. Co-authored-by: Cursor <cursoragent@cursor.com>
|
/test fournos rhaiis nvidia benchmark hera ci-quick |
🟢 Execution of
|
🟢 Submission of
|
|
/lgtm approve to get it merged 👍🏻 |
|
New changes are detected. LGTM label has been removed. |
|
[APPROVALNOTIFIER] This PR is NOT APPROVED This pull-request has been approved by: The full list of commands accepted by this bot can be found here. DetailsNeeds approval from an approver in each of these files:Approvers can indicate their approval by writing |
|
Note GitHub couldn't provide a complete incremental comparison for this pull request, so CodeRabbit is performing a full review instead. This review may take a little longer. |
|
/approved |
2 participants
Summary
benchmarks.yamlpreset with common benchmark settings (run_benchmark, profiler, dashboard, agent_analysis, slack_notify_always)clusters.yamlpreset with hera/zeus cluster configs (cluster_tag, image_pull_secrets, fs_group)presets.yamlmodel aliases to cover all models inmodels.yaml, with short names defaulting to FP8 variants and quantization suffixes for other variantsci-quickcomposite preset (qwen3-0.6b, TP=1, warmup off, dashboard off) for fast validation runsimagesfallback fromrhaiis.yamlsince all engines define their own imagesmehulvalidation.yamlpresetTest plan
args: [nvidia, benchmark, hera, ci-quick]and verify the correct config is appliedargs: [nvidia, benchmark, hera, nemotron3super-120b]and verify it matches previous behaviorMade with Cursor
Summary by CodeRabbit
New Features
Updates
ci-quickworkload token limits.ci-quickwith runtime, profiling, dashboard, notification, and model settings.