From 0728acbbb79c69ab4aaa314e9c14a615c00e3441 Mon Sep 17 00:00:00 2001
From: "renovate[bot]" <29139614+renovate[bot]@users.noreply.github.com>
Date: Mon, 27 Jul 2026 10:56:34 +0000
Subject: [PATCH] =?UTF-8?q?fix(container):=20update=20image=20ghcr.io/ggml?=
 =?UTF-8?q?-org/llama.cpp=20(e7249fa=20=E2=9E=94=20eddb40b)?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 kubernetes/apps/ai/llmkube/models/qwen3-embedding.yaml | 2 +-
 kubernetes/apps/ai/llmkube/models/qwen35-2b.yaml       | 2 +-
 kubernetes/apps/ai/llmkube/models/vmcp-embedding.yaml  | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/kubernetes/apps/ai/llmkube/models/qwen3-embedding.yaml b/kubernetes/apps/ai/llmkube/models/qwen3-embedding.yaml
index cfc9d3fbc2..0a1f0b56d8 100644
--- a/kubernetes/apps/ai/llmkube/models/qwen3-embedding.yaml
+++ b/kubernetes/apps/ai/llmkube/models/qwen3-embedding.yaml
@@ -38,7 +38,7 @@ spec:
   # Native upstream GTT-leak mitigation in LLMKube >=0.9.10; lifetime includes
   # startup and model load before this Vulkan embedder is recycled.
   maxPodLifetimeSeconds: 86400
-  image: ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:e7249fa3c18189a825898832cc4d722d7f9c0160c29540ced793c833ab9f2432
+  image: ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:eddb40b8a348a652c8829ef036df9bbbae537755ae7026bf6d4b403840cd468e
   # Two slots are the Vulkan-safe floor; more interleaving did not improve
   # throughput on this compute-bound iGPU. VMCP has its own embedder now.
   parallelSlots: 2 # Vulkan warmup hangs at parallel=1 (llama.cpp #24307)
diff --git a/kubernetes/apps/ai/llmkube/models/qwen35-2b.yaml b/kubernetes/apps/ai/llmkube/models/qwen35-2b.yaml
index d56bb1f302..9471893bc0 100644
--- a/kubernetes/apps/ai/llmkube/models/qwen35-2b.yaml
+++ b/kubernetes/apps/ai/llmkube/models/qwen35-2b.yaml
@@ -32,7 +32,7 @@ spec:
   # Must be recent enough for Qwen3.5's GDN (Gated Delta Networks) architecture;
   # verified to load `qwen35` and run GDN fully on Vulkan (no CPU fallback).
   # Tracked by the llmkube-models Renovate customManager (.renovaterc.json5).
-  image: ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:e7249fa3c18189a825898832cc4d722d7f9c0160c29540ced793c833ab9f2432
+  image: ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:eddb40b8a348a652c8829ef036df9bbbae537755ae7026bf6d4b403840cd468e
   parallelSlots: 2 # Vulkan warmup hangs at parallel=1 (llama.cpp #24307)
   contextSize: 16384 # GDN keeps KV tiny, so long ctx is cheap; 16K is plenty for offload
   jinja: true # use the model's chat template (correct Qwen3.5 formatting + tool calls)
diff --git a/kubernetes/apps/ai/llmkube/models/vmcp-embedding.yaml b/kubernetes/apps/ai/llmkube/models/vmcp-embedding.yaml
index 8eb3f0b9a1..428cceb246 100644
--- a/kubernetes/apps/ai/llmkube/models/vmcp-embedding.yaml
+++ b/kubernetes/apps/ai/llmkube/models/vmcp-embedding.yaml
@@ -50,7 +50,7 @@ spec:
   # Native upstream GTT-leak mitigation in LLMKube >=0.9.10; lifetime includes
   # startup and model load before this Vulkan embedder is recycled.
   maxPodLifetimeSeconds: 86400
-  image: ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:e7249fa3c18189a825898832cc4d722d7f9c0160c29540ced793c833ab9f2432
+  image: ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:eddb40b8a348a652c8829ef036df9bbbae537755ae7026bf6d4b403840cd468e
   # 2 slots (the Vulkan floor — warmup hangs at parallel=1, llama.cpp #24307):
   # the iGPU is compute-bound, so extra slots add interleave, not throughput
   # (measured on qwen3-embedding: 4 slots didn't move latency, Q8_0 did). Two