Skip to content

fix(self-managed): bump llm stacks, nvcf-api and cassandra chart - #934

Merged
along-2017 merged 1 commit into
mainfrom
fix/self-managed/bump-llm-and-cassandra-chart-pins
Aug 18, 2026
Merged

fix(self-managed): bump llm stacks, nvcf-api and cassandra chart #934
along-2017 merged 1 commit into
mainfrom
fix/self-managed/bump-llm-and-cassandra-chart-pins

Conversation

@along-2017

@along-2017 along-2017 commented Aug 18, 2026

Copy link
Copy Markdown
Contributor

TL;DR

Bump the self-managed stack chart pins for the LLM addon and Cassandra: llm-request-router 1.6.6 -> 1.7.2, llm-api-gateway 1.0.1 -> 1.4.1, cassandra 0.17.0 -> 0.19.1. This makes the LLM request-priority feature deployable on a stack install and picks up the recent fixes and changes in the LLM components.

Additional Details

For QA

  • Local sanity test: installed the stack with these pins on a local cluster; the deployment came up end to end, including the Cassandra migrations job and the LLM addon.
  • Each pin verified against its release tag and traced to the image it carries.

Issues

Relates to #852

Checklist

  • I am familiar with the Contributing Guidelines.
  • I have signed off my commits for Developer Certificate of Origin (DCO) compliance.
  • New or existing tests cover these changes.
  • The documentation is up to date with these changes.

Summary by CodeRabbit

  • Updates
    • Updated the self-managed deployment stack’s core platform components to newer versions.
    • Updated the Cassandra-backed data service and request-routing components for improved compatibility and access to the latest fixes and enhancements.
    • Updated the API gateway component to its latest supported release.

…andra chart pins

Bump the self-managed stack to the latest released charts:

- llm-request-router 1.6.6 -> 1.7.2 (stargate image 0.3.2 -> 0.9.0)
- llm-api-gateway 1.0.1 -> 1.4.1 (image -> 0.13.0)
- cassandra 0.17.0 -> 0.19.1 (migrations image 0.11.0 -> 0.15.0,
  Cassandra base moved from Bitnami 5.0.6 to Apache 5.0.8)

The cassandra migrations in this range are additive only: a new
llm_config column on nvcf_api.functions_v3 and first-time creation of
the event_ledger, nvcf_autoscaler, and nvct_api keyspaces.

Signed-off-by: along <along@nvidia.com>
@along-2017
along-2017 requested a review from a team as a code owner August 18, 2026 01:16
@along-2017
along-2017 requested review from bright-poku and removed request for bright-poku August 18, 2026 01:16
@coderabbitai

coderabbitai Bot commented Aug 18, 2026

Copy link
Copy Markdown

Review Change Stack

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: 4d3b7425-37e5-40cb-ae26-fc0e76dd1d30

📥 Commits

Reviewing files that changed from the base of the PR and between d95e051 and 97cf1c4.

📒 Files selected for processing (2)
  • deploy/stacks/self-managed/helmfile.d/01-dependencies.yaml.gotmpl
  • deploy/stacks/self-managed/helmfile.d/02-core.yaml.gotmpl

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


📝 Walkthrough

Walkthrough

The self-managed Helmfile definitions update chart versions for Cassandra, llm-request-router, and llm-api-gateway.

Changes

Self-managed chart updates

Layer / File(s) Summary
Chart version updates
deploy/stacks/self-managed/helmfile.d/01-dependencies.yaml.gotmpl, deploy/stacks/self-managed/helmfile.d/02-core.yaml.gotmpl
Cassandra updates to 0.19.1, llm-request-router updates to 1.7.2, and llm-api-gateway updates to 1.4.1.

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

Merge Risk: 🔵 Low · up to 97cf1

This change upgrades the self-managed LLM and Cassandra charts, including runtime images and database migrations. It is mergeable with owner awareness, but the published chart contracts and additive schema changes should be validated to avoid startup or migration failures.

Suggested labels: released

Suggested reviewers: bright-poku

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name Status Explanation Resolution
Title check ⚠️ Warning The title follows Conventional Commits syntax, but fix does not match the primary nature of these chart and dependency version updates. Use a maintenance-oriented type such as chore(self-managed): bump LLM stack and Cassandra charts.
✅ 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.
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 Check skipped - CodeRabbit’s high-level summary is enabled.
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Commit unit tests in branch fix/self-managed/bump-llm-and-cassandra-chart-pins

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

@along-2017 along-2017 self-assigned this Aug 18, 2026
@along-2017
along-2017 requested review from a team, Max-NV, nvjmcnamee, sanjay-saxena and sbaum1994 and removed request for nvjmcnamee August 18, 2026 19:24
@along-2017
along-2017 added this pull request to the merge queue Aug 18, 2026
Merged via the queue into main with commit 5f672b8 Aug 18, 2026
15 checks passed
@along-2017
along-2017 deleted the fix/self-managed/bump-llm-and-cassandra-chart-pins branch August 18, 2026 20:09
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.

4 participants