Skip to content

[UPDATE][llamacppqwen35a3b][1.0.3]Upgrade to OlaresManifest (0.12.0) format#3158

Open
TShentu wants to merge 1 commit into
beclab:mainfrom
TShentu:sync-llamacppqwen35a3b-20260719-101538
Open

[UPDATE][llamacppqwen35a3b][1.0.3]Upgrade to OlaresManifest (0.12.0) format#3158
TShentu wants to merge 1 commit into
beclab:mainfrom
TShentu:sync-llamacppqwen35a3b-20260719-101538

Conversation

@TShentu

@TShentu TShentu commented Jul 19, 2026

Copy link
Copy Markdown
Member

App Title

llamacppqwen35a3b

Description

Upgrade llamacppqwen35a3b chart to OlaresManifest v3 format for Olares OS >=1.12.6.

  • Bump chart/manifest version 1.0.21.0.3
  • Set olaresManifest.version: '0.12.0' and apiVersion: 'v3'
  • Add workloadReplicas.llamacppqwen35a3b: 1, wire values.yaml / Deployment replicas
  • Update Olares dependency to >=1.12.6-0
  • Move CPU/memory/disk/GPU resource fields into spec.accelerator (mode: nvidia)
  • Update app/entrance icon to https://app.cdn.olares.com/appstore/llm/llamacpp/llm/qwen.png
  • Add zh-CN i18n (keep en-US)

Statement

  • I have tested this application to ensure it is compatible with the Olares OS version stated in the OlaresManifest.yaml

Made with Cursor

Co-authored-by: Cursor <cursoragent@cursor.com>
@Terminus-Gitbot

Copy link
Copy Markdown
Collaborator

Chart invalid. Error message: [container image 'ghcr.io/ggml-org/llama.cpp:server-cuda' is not accessible or does not exist: image not found or not accessible (HTTP 404)]

@TShentu

TShentu commented Jul 19, 2026

Copy link
Copy Markdown
Member Author

Hi @aamsellem ,
With the Olares 1.12.6 upgrade, we introduced a new API format (v3) for app installation. For legacy apps to continue being installable on systems running 1.12.6 or later, they must be updated to the new format. You can find the details here:
https://www.olares.com/docs/developer/develop/package/manifest

We've already drafted the necessary upgrade changes based on this new format. Could you please take a look at the pull request? If everything looks good, just select “Approve” in your review – Gitbot will automatically merge it afterward.

Additionally, I also updated the app's icon — its badge now accurately reflects the actual llama.cpp server.

Thanks again for your contribution!

@TShentu TShentu changed the title [UPDATE][llamacppqwen35a3b][1.0.3] [UPDATE][llamacppqwen35a3b][1.0.3]Upgrade to OlaresManifest v3 (0.12.0) format Jul 19, 2026
@TShentu
TShentu marked this pull request as ready for review July 19, 2026 08:01
@Terminus-Gitbot

Copy link
Copy Markdown
Collaborator

Chart invalid. Error message: [container image 'ghcr.io/ggml-org/llama.cpp:server-cuda' is not accessible or does not exist: image not found or not accessible (HTTP 404)]

@TShentu TShentu changed the title [UPDATE][llamacppqwen35a3b][1.0.3]Upgrade to OlaresManifest v3 (0.12.0) format [UPDATE][llamacppqwen35a3b][1.0.3]Upgrade to OlaresManifest (0.12.0) format Jul 20, 2026
@Terminus-Gitbot

Copy link
Copy Markdown
Collaborator

All checks passed. This PR will NOT be auto-merged because the author is not in the owners list. An owner must review and approve this PR before it can be merged.

@Terminus-Gitbot

Copy link
Copy Markdown
Collaborator

All checks passed. This PR will NOT be auto-merged because the author is not in the owners list. An owner must manually review and merge this PR.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants