From 063de544582518057832e06d74eb9e568ea7088a Mon Sep 17 00:00:00 2001
From: "renovate[bot]" <29139614+renovate[bot]@users.noreply.github.com>
Date: Sun, 6 Sep 2026 11:17:14 +0000
Subject: [PATCH] =?UTF-8?q?fix(container):=20update=20image=20ghcr.io/ggml?=
 =?UTF-8?q?-org/llama.cpp=20(f862c90=20=E2=9E=94=209b67d4b)?=
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 4f95e1fb9..24bf2df0d 100644
--- a/kubernetes/apps/ai/llmkube/models/qwen3-embedding.yaml
+++ b/kubernetes/apps/ai/llmkube/models/qwen3-embedding.yaml
@@ -36,7 +36,7 @@ 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:f862c901a0089bc3dc326bd24f208bfcd147839783328d252e911a004c94ff3c
+  image: ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:9b67d4b09614453f5511e655aa6a7792ddb16e93ae9116134c910bb1951da645
   # 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 64c2db191..55f9fab20 100644
--- a/kubernetes/apps/ai/llmkube/models/qwen35-2b.yaml
+++ b/kubernetes/apps/ai/llmkube/models/qwen35-2b.yaml
@@ -33,7 +33,7 @@ spec:
   modelRef: qwen35-2b
   # 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).
-  image: ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:f862c901a0089bc3dc326bd24f208bfcd147839783328d252e911a004c94ff3c
+  image: ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:9b67d4b09614453f5511e655aa6a7792ddb16e93ae9116134c910bb1951da645
   parallelSlots: 2 # Vulkan warmup hangs at parallel=1 (llama.cpp #24307)
   # llama.cpp splits contextSize across parallelSlots, so 32768/2 = 16384 per slot.
   # GDN keeps KV tiny, so long ctx is cheap; 16K per slot is plenty for offload.
diff --git a/kubernetes/apps/ai/llmkube/models/vmcp-embedding.yaml b/kubernetes/apps/ai/llmkube/models/vmcp-embedding.yaml
index 56afd794b..778539a90 100644
--- a/kubernetes/apps/ai/llmkube/models/vmcp-embedding.yaml
+++ b/kubernetes/apps/ai/llmkube/models/vmcp-embedding.yaml
@@ -48,7 +48,7 @@ spec:
   # reloading at once on control-3 is the condition behind the podAffinity
   # deadlock; offsetting the period drops realignment from daily to every 3d.
   maxPodLifetimeSeconds: 64800
-  image: ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:f862c901a0089bc3dc326bd24f208bfcd147839783328d252e911a004c94ff3c
+  image: ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:9b67d4b09614453f5511e655aa6a7792ddb16e93ae9116134c910bb1951da645
   # Vulkan floor is 2 — warmup hangs at parallel=1 (llama.cpp #24307). The iGPU
   # is compute-bound, so more slots add interleave, not throughput.
   parallelSlots: 2