diff --git a/llamacpp/README.md b/llamacpp/README.md
index 34bd127..0ab8f8c 100644
--- a/llamacpp/README.md
+++ b/llamacpp/README.md
@@ -23,7 +23,8 @@ without re-downloading.
 
 ## GPU / Vulkan
 
-The `server-vulkan` image bundles the Mesa/RADV Vulkan driver, which supports
+The `server-vulkan` image (`ghcr.io/ggml-org/llama.cpp:server-vulkan`) bundles
+the Mesa/RADV Vulkan driver, which supports
 the Radeon 8060S (RDNA 3.5). Full layer offload (`-ngl 999`) puts the ~16 GiB
 Q4 model entirely in the 96 GiB VRAM pool.
 
diff --git a/llamacpp/deployment-qwen36.yaml b/llamacpp/deployment-qwen36.yaml
index 0c3da45..29d40af 100644
--- a/llamacpp/deployment-qwen36.yaml
+++ b/llamacpp/deployment-qwen36.yaml
@@ -5,9 +5,11 @@
 # (~16 GiB) is fully offloaded to the GPU via the Vulkan backend, leaving plenty
 # of VRAM for the KV cache.
 #
-# Image: ghcr.io/ggerganov/llama.cpp:server-vulkan bundles the Mesa/RADV Vulkan
-# driver, which supports the Radeon 8060S (RDNA 3.5). Pin to a digest for
-# production once the rolling tag is confirmed working.
+# Image: ghcr.io/ggml-org/llama.cpp:server-vulkan bundles the Mesa/RADV Vulkan
+# driver, which supports the Radeon 8060S (RDNA 3.5). The project moved from the
+# legacy `ggerganov/llama.cpp` namespace (which only has light/full tags) to
+# `ggml-org/llama.cpp` (server-vulkan + pinned build tags like server-vulkan-bXXXX).
+# Pin to a build tag (e.g. server-vulkan-b4738) for production reproducibility.
 #
 # GPU access: the container mounts /dev/dri (the DRM render nodes) and runs
 # privileged. This is the simplest reliable option on k3s without a Vulkan
@@ -66,7 +68,7 @@ spec:
           mountPath: /models
       containers:
       - name: llama-server
-        image: ghcr.io/ggerganov/llama.cpp:server-vulkan
+        image: ghcr.io/ggml-org/llama.cpp:server-vulkan
         imagePullPolicy: IfNotPresent
         args:
         - -m=/models/Qwen3.6-27B-UD-Q4_K_XL.gguf