Update ghcr.io/allenporter/llama-cpp-server-cuda Docker tag to v2.18.0

[renovate[bot]]

This PR contains the following updates:

Package	Update	Change
ghcr.io/allenporter/llama-cpp-server-cuda	minor	v2.17.0 -> v2.18.0

---

Release Notes

allenporter/llama-cpp-server (ghcr.io/allenporter/llama-cpp-server-cuda)

### [`v2.18.0`](https://togithub.com/allenporter/llama-cpp-server/releases/tag/v2.18.0) [Compare Source](https://togithub.com/allenporter/llama-cpp-server/compare/v2.17.0...v2.18.0) #### What's Changed - Update dependency uvicorn to v0.30.0 by [@​renovate](https://togithub.com/renovate) in [https://github.com/allenporter/llama-cpp-server/pull/73](https://togithub.com/allenporter/llama-cpp-server/pull/73) - Update dependency transformers to v4.41.2 by [@​renovate](https://togithub.com/renovate) in [https://github.com/allenporter/llama-cpp-server/pull/74](https://togithub.com/allenporter/llama-cpp-server/pull/74) - Update dependency uvicorn to v0.30.1 by [@​renovate](https://togithub.com/renovate) in [https://github.com/allenporter/llama-cpp-server/pull/75](https://togithub.com/allenporter/llama-cpp-server/pull/75) - Update dependency pydantic-settings to v2.3.0 by [@​renovate](https://togithub.com/renovate) in [https://github.com/allenporter/llama-cpp-server/pull/76](https://togithub.com/allenporter/llama-cpp-server/pull/76) - Update dependency llama_cpp_python to v0.2.77 by [@​renovate](https://togithub.com/renovate) in [https://github.com/allenporter/llama-cpp-server/pull/77](https://togithub.com/allenporter/llama-cpp-server/pull/77) - Update dependency pydantic-settings to v2.3.1 by [@​renovate](https://togithub.com/renovate) in [https://github.com/allenporter/llama-cpp-server/pull/78](https://togithub.com/allenporter/llama-cpp-server/pull/78) - Update dependency cmake to v3.29.5 by [@​renovate](https://togithub.com/renovate) in [https://github.com/allenporter/llama-cpp-server/pull/79](https://togithub.com/allenporter/llama-cpp-server/pull/79) - Update dependency llama_cpp_python to v0.2.78 by [@​renovate](https://togithub.com/renovate) in [https://github.com/allenporter/llama-cpp-server/pull/80](https://togithub.com/allenporter/llama-cpp-server/pull/80) **Full Changelog**: https://github.com/allenporter/llama-cpp-server/compare/v2.17.0...v2.18.0

---

Configuration

📅 Schedule: Branch creation - "every weekend" in timezone America/Los_Angeles, Automerge - At any time (no schedule defined).

🚦 Automerge: Enabled.

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

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

---

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

---

This PR has been generated by Mend Renovate. View repository job log here.

[github-actions[bot]]

--- kubernetes/ml/prod Kustomization: flux-system/ml HelmRelease: llama/llama-cublas

+++ kubernetes/ml/prod Kustomization: flux-system/ml HelmRelease: llama/llama-cublas

@@ -34,13 +34,13 @@

               value: /data/models
             - name: CONFIG_FILE
               value: /config/model-config.json
             image:
               pullPolicy: IfNotPresent
               repository: ghcr.io/allenporter/llama-cpp-server-cuda
-              tag: v2.17.0
+              tag: v2.18.0
             resources:
               limits:
                 nvidia.com/gpu: 1
         initContainers:
           download-model:
             env:

[github-actions[bot]]

--- HelmRelease: llama/llama-cublas Deployment: llama/llama-cublas

+++ HelmRelease: llama/llama-cublas Deployment: llama/llama-cublas

@@ -52,13 +52,13 @@

       containers:
       - env:
         - name: MODEL_DIR
           value: /data/models
         - name: CONFIG_FILE
           value: /config/model-config.json
-        image: ghcr.io/allenporter/llama-cpp-server-cuda:v2.17.0
+        image: ghcr.io/allenporter/llama-cpp-server-cuda:v2.18.0
         imagePullPolicy: IfNotPresent
         livenessProbe:
           failureThreshold: 3
           initialDelaySeconds: 0
           periodSeconds: 10
           tcpSocket: