fix(container): update image ghcr.io/ggml-org/llama.cpp (c848857 ➔ e7249fa)

[renovate]

This PR contains the following updates:

Package	Update	Change
ghcr.io/ggml-org/llama.cpp	digest	c848857 → e7249fa

---

Configuration

📅 Schedule: (in timezone Europe/Brussels)

• Branch creation
  • At any time (no schedule defined)
• Automerge
  • At any time (no schedule defined)

🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.

♻ Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.

🔕 Ignore: Close this PR and you won't be reminded about these updates again.

---

• If you want to rebase/retry this PR, check this box

---

This PR was generated by Mend Renovate. View the repository job log.

Summary by CodeRabbit

• Bug Fixes
  • Updated the Vulkan-backed AI inference services to use newer container image versions.
  • Improved reliability and compatibility for embedding and language model workloads without changing model or resource configuration.

[coderabbitai]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Pro Plus

Run ID: f5baa756-c355-4ebf-8922-b761ac4e9a0b

📥 Commits

Reviewing files that changed from the base of the PR and between f703cf2 and f40ddaf.

📒 Files selected for processing (3)

• kubernetes/apps/ai/llmkube/models/qwen3-embedding.yaml
• kubernetes/apps/ai/llmkube/models/qwen35-2b.yaml
• kubernetes/apps/ai/llmkube/models/vmcp-embedding.yaml

🔗 Linked repositories identified

CodeRabbit considers these linked repositories for cross-repo context during reviews:

• Tanguille/LLMKube (auto-detected)

---

📝 Walkthrough

Walkthrough

Three Kubernetes InferenceService manifests update the pinned llama.cpp:server-vulkan container image digests for Qwen embedding, Qwen 3.5 2B, and VMCP embedding models.

Changes

Vulkan image updates

Layer / File(s)	Summary
Refresh pinned Vulkan image references kubernetes/apps/ai/llmkube/models/qwen3-embedding.yaml, kubernetes/apps/ai/llmkube/models/qwen35-2b.yaml, kubernetes/apps/ai/llmkube/models/vmcp-embedding.yaml	The three InferenceService manifests use updated llama.cpp:server-vulkan SHA256 digests without other configuration changes.

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

Possibly related PRs

• Tanguille/cluster#4160: Updates pinned Vulkan llama.cpp image digests in the same InferenceService manifests.
• Tanguille/cluster#4173: Applies a similar digest-pinning change to the same Vulkan image references.
• Tanguille/cluster#4146: Updates a pinned InferenceService image digest in the same model-manifest directory.

Suggested reviewers: tanguille

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title accurately summarizes the main change: updating the pinned llama.cpp container image digest.
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.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch renovate/ghcr.io-ggml-org-llama.cpp-server-vulkan

---

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

[tanguille-cluster]

@@ spec.image @@
# inference.llmkube.dev/v1alpha1/InferenceService/ai/qwen3-embedding
! ± value change
- ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:c84885737a1904ec2732508331be31253c09463e417d4daa726d7464b94efe16
+ ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:e7249fa3c18189a825898832cc4d722d7f9c0160c29540ced793c833ab9f2432

@@ spec.image @@
# inference.llmkube.dev/v1alpha1/InferenceService/ai/qwen35-2b
! ± value change
- ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:c84885737a1904ec2732508331be31253c09463e417d4daa726d7464b94efe16
+ ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:e7249fa3c18189a825898832cc4d722d7f9c0160c29540ced793c833ab9f2432

@@ spec.image @@
# inference.llmkube.dev/v1alpha1/InferenceService/ai/vmcp-embedding
! ± value change
- ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:c84885737a1904ec2732508331be31253c09463e417d4daa726d7464b94efe16
+ ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:e7249fa3c18189a825898832cc4d722d7f9c0160c29540ced793c833ab9f2432