Replicas counted per profile: seven on cards and four on CPUs under one name

A profile's replicas, set on any of a model's profiles, is how many of its
replicas run there; the scaling becomes the sum. The reconciler starts the
ones short of their profile before stopping the ones over, so a change of
split never runs fewer. ctl model replicas sets them, adding a profile on
CPUs to a GGUF model; the router already fills the higher-priority pool
first, which the CPU profile is put below.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

docs/admin-api.openapi.json

@@ -3227,6 +3227,58 @@
         }
       }
     },
+    "/api/v1/models/{name}/replicas": {
+      "post": {
+        "operationId": "postModelsNameReplicas",
+        "summary": "How many replicas run on each profile",
+        "description": "Seven on cards and four on CPUs, under the model's name. A profile not named keeps its count; cpu adds a profile on CPUs to a llama.cpp model that has none. Its scaling becomes the sum.",
+        "tags": [
+          "models"
+        ],
+        "parameters": [
+          {
+            "name": "name",
+            "in": "path",
+            "required": true,
+            "description": "The model's name in the catalog.",
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "$ref": "#/components/parameters/Actor"
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/ProfileReplicasRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/catalog.Model"
+                }
+              }
+            }
+          },
+          "401": {
+            "$ref": "#/components/responses/Unauthorized"
+          },
+          "default": {
+            "$ref": "#/components/responses/Error"
+          }
+        }
+      }
+    },
     "/api/v1/models/{name}/resources": {
       "post": {
         "operationId": "postModelsNameResources",
@@ -8103,6 +8155,13 @@
               "type": "string"
             }
           },
+          "profile_replicas": {
+            "type": "object",
+            "additionalProperties": {
+              "type": "integer"
+            },
+            "description": "ProfileReplicas is how many replicas run on each profile, for a model whose replicas are counted per profile; absent otherwise."
+          },
           "memory_gb": {
             "type": "integer",
             "description": "MemoryGB and CPUCores are what one replica reserves, from its first profile; MeasuredMemoryGB is the most one of its replicas uses now, 0 when none is measured."
@@ -8665,6 +8724,21 @@
           }
         }
       },
+      "ProfileReplicasRequest": {
+        "type": "object",
+        "description": "ProfileReplicasRequest counts a model's replicas per profile: profile name to replicas, and CPU, for a llama.cpp model with no profile on CPUs, the one to add.",
+        "properties": {
+          "profiles": {
+            "type": "object",
+            "additionalProperties": {
+              "type": "integer"
+            }
+          },
+          "cpu": {
+            "$ref": "#/components/schemas/modelsvc.CPUProfile"
+          }
+        }
+      },
       "ProjectView": {
         "type": "object",
         "description": "ProjectView is a project, with how many people and keys are in it.",
@@ -10510,6 +10584,10 @@
             "type": "integer",
             "description": "Priority orders profiles during placement; highest that fits wins."
           },
+          "replicas": {
+            "type": "integer",
+            "description": "Replicas, set on any of a model's profiles, is how many of its replicas run on this one: seven on cards and four on CPUs, all answering under the model's name, rather than each replica on the best profile that fits. The model's scaling is then the sum, min and max alike; a profile left at zero runs none."
+          },
           "startup_timeout": {
             "type": "integer",
             "format": "int64",
@@ -11906,6 +11984,21 @@
           }
         }
       },
+      "modelsvc.CPUProfile": {
+        "type": "object",
+        "description": "CPUProfile is a profile on CPUs to add to a llama.cpp model, for replicas counted per profile: what a replica of it reserves.",
+        "properties": {
+          "name": {
+            "type": "string"
+          },
+          "memory_gb": {
+            "type": "integer"
+          },
+          "cpu_cores": {
+            "type": "integer"
+          }
+        }
+      },
       "notify.Result": {
         "type": "object",
         "description": "Result is how one webhook answered a test.",