Skip to content

fix: rename DSC datasciencepipelines to aipipelines for RHOAI 3.4 - #14

Closed
itay1551 wants to merge 5 commits into
mainfrom
fix/rhoai-34-aipipelines
Closed

fix: rename DSC datasciencepipelines to aipipelines for RHOAI 3.4#14
itay1551 wants to merge 5 commits into
mainfrom
fix/rhoai-34-aipipelines

Conversation

@itay1551

@itay1551 itay1551 commented Jul 22, 2026

Copy link
Copy Markdown
Collaborator

Summary

  • Renames datasciencepipelinesaipipelines in ROSA and ARO DataScienceCluster charts for RHOAI 3.4 schema compatibility.
  • Unblocks ArgoCD SSA on pca-platform-config (field not declared in schema).

Test plan

  • Point ArgoCD pca-root at this branch and confirm pca-platform-config syncs
  • Confirm DataScienceCluster/default-dsc is created
  • Confirm LLMInferenceService CRD appears and pca-ai-serving progresses
  • Run make smoke once serving is ready

itay1551 added 5 commits July 22, 2026 12:38
RHOAI 3.4 removed datasciencepipelines from the DataScienceCluster schema;
SSA fails with "field not declared in schema" until the chart uses aipipelines.
ModelMesh is not in the DSC v2 schema and is unused by the llm-d/KServe path.
MaaS needs a DB secret and Authorino TLS we do not provision; keep it Removed
so DSC can become Ready while llm-d/KServe still runs.
v4.17 NFD operands crash on 4.21 (missing NodeFeatureGroup API), so the GPU
Operator never sees NFD labels and skips driver/device-plugin install.
Use a deterministic Grafana admin password under Argo and drop the global
Continue ConfigMap so DevSpaces cannot overwrite per-ns API keys/headers.
@itay1551
itay1551 marked this pull request as ready for review July 22, 2026 11:24
@itay1551
itay1551 requested a review from Hadar301 July 22, 2026 11:24
Hadar301 added a commit to Hadar301/private-coding-assistant that referenced this pull request Jul 22, 2026
- Remove continue-config from devspaces-global-config.yaml; DevSpaces
  operator propagates global CMs into user namespaces (subpath mount,
  read-only) and would clobber per-ns API key/headers. Continue config
  lives only in per-namespace continue-configmaps.yaml.
- DSC: modelsAsService → Removed, remove modelmeshserving (RHOAI 3.4)
- NFD image: v4.17 → v4.21

Co-Authored-By: Itay Katav <itay1551@users.noreply.github.com>
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
@Hadar301

Copy link
Copy Markdown
Collaborator

Adding changes from this PR in this commit let me know if I'm missing something

@itay1551

itay1551 commented Jul 23, 2026

Copy link
Copy Markdown
Collaborator Author

Adding changes from this PR in this commit let me know if I'm missing something

You missing the changes in the Grafana (two files) @Hadar301

Hadar301 added a commit to Hadar301/private-coding-assistant that referenced this pull request Jul 23, 2026
- llm-d-gateway-httproute: fallback service uses port 80 (KServe service
  exposes 80→8000; port 8000 is pod-direct only for InferencePool/EPP)
- pca-observability/values.yaml: update adminPassword comment to reflect
  deterministic hash approach (aligned with upstream PR rh-ai-quickstart#14)
- values-aro.yaml (operators): nfd.enabled: true — ARO requires NFD to
  label GPU nodes with nvidia.com/gpu.deploy.* so driver DaemonSet schedules

Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
Hadar301 added a commit that referenced this pull request Jul 23, 2026
- Remove continue-config from devspaces-global-config.yaml; DevSpaces
  operator propagates global CMs into user namespaces (subpath mount,
  read-only) and would clobber per-ns API key/headers. Continue config
  lives only in per-namespace continue-configmaps.yaml.
- DSC: modelsAsService → Removed, remove modelmeshserving (RHOAI 3.4)
- NFD image: v4.17 → v4.21

Co-Authored-By: Itay Katav <itay1551@users.noreply.github.com>
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
Hadar301 added a commit that referenced this pull request Jul 23, 2026
- llm-d-gateway-httproute: fallback service uses port 80 (KServe service
  exposes 80→8000; port 8000 is pod-direct only for InferencePool/EPP)
- pca-observability/values.yaml: update adminPassword comment to reflect
  deterministic hash approach (aligned with upstream PR #14)
- values-aro.yaml (operators): nfd.enabled: true — ARO requires NFD to
  label GPU nodes with nvidia.com/gpu.deploy.* so driver DaemonSet schedules

Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
@itay1551 itay1551 closed this Jul 26, 2026
@itay1551

Copy link
Copy Markdown
Collaborator Author

This code was added to #15 #15

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.

2 participants