From d5403cba0edb8eccde6ebe761985d2a235f7698e Mon Sep 17 00:00:00 2001
From: "renovate[bot]" <29139614+renovate[bot]@users.noreply.github.com>
Date: Thu, 8 Oct 2026 06:13:46 +0000
Subject: [PATCH] =?UTF-8?q?chore(container):=20update=20image=20ghcr.io/gg?=
 =?UTF-8?q?ml-org/llama.cpp=20(=20af8c296=20=E2=86=92=2033868c0=20)?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 kubernetes/ai/llmkube/models/embed.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kubernetes/ai/llmkube/models/embed.yaml b/kubernetes/ai/llmkube/models/embed.yaml
index 9e65131a2..b68b9a148 100644
--- a/kubernetes/ai/llmkube/models/embed.yaml
+++ b/kubernetes/ai/llmkube/models/embed.yaml
@@ -22,7 +22,7 @@ spec:
   # CPU embedding service for the ToolHive gateway tool search.
   # Bound concurrent embedding work: eight slots and 2048-token batches
   # exceeded the 4Gi limit during ToolHive indexing.
-  image: ghcr.io/ggml-org/llama.cpp:server@sha256:af8c29600d1de84945de13fa7f126d06fdae16c4b19dc7db1c69c74287eae257
+  image: ghcr.io/ggml-org/llama.cpp:server@sha256:33868c035b21dc63f7c60b7438774283fd99215bc319114eb03de5df4ce7cd6b
   replicas: 1
   contextSize: 8192
   parallelSlots: 2