A replica says what its engine computes on, and llama.cpp's word on the CPU refuses a GPU placement

llama.cpp's start-up output is read as a shard becomes ready: the devices it
used, its backend, and the layers it offloaded. That goes up with READY in a
new ShardStatus.compute, is kept on the shard, and is shown by the admin
API, ctl replicas (ON) and the console (COMPUTE). A shard given GPUs whose
engine says it found no usable GPU or offloaded no layer is stopped and
failed, even where nvidia-smi cannot be asked.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

docs/admin-api.openapi.json

@@ -3714,6 +3714,29 @@
           }
         }
       },
+      "ComputeView": {
+        "type": "object",
+        "description": "ComputeView is where an engine runs its model, by its own account.",
+        "properties": {
+          "backend": {
+            "type": "string",
+            "description": "Backend is CUDA, Vulkan, Metal, ROCm, GPU or CPU."
+          },
+          "devices": {
+            "type": "array",
+            "items": {
+              "type": "string"
+            }
+          },
+          "layers_offloaded": {
+            "type": "integer",
+            "description": "LayersOffloaded of LayersTotal went to the devices; absent when unsaid."
+          },
+          "layers_total": {
+            "type": "integer"
+          }
+        }
+      },
       "ControlPlane": {
         "type": "object",
         "description": "ControlPlane is one control plane.",
@@ -5779,6 +5802,10 @@
           "memory_bytes": {
             "type": "integer",
             "format": "int64"
+          },
+          "compute": {
+            "$ref": "#/components/schemas/ComputeView",
+            "description": "Compute is where the engine said it put the model as it became ready: absent when it did not say."
           }
         }
       },