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>

internal/control/adminapi/api_test.go

@@ -16,6 +16,7 @@ import (
 	"gitea.mynodes.xyz/ilker/llmgw/internal/control"
 	"gitea.mynodes.xyz/ilker/llmgw/internal/control/catalog"
 	"gitea.mynodes.xyz/ilker/llmgw/internal/control/inventory"
+	"gitea.mynodes.xyz/ilker/llmgw/internal/control/modelsvc"
 	"gitea.mynodes.xyz/ilker/llmgw/internal/control/reconciler"
 	"gitea.mynodes.xyz/ilker/llmgw/internal/router/endpoint"
 	"gitea.mynodes.xyz/ilker/llmgw/internal/store"
@@ -263,6 +264,16 @@ func (f *fakeModels) SetAdapters(_ context.Context, name string, as []catalog.Ad
 	return catalog.Model{Name: name, Adapters: as}, f.err
 }
 
+func (f *fakeModels) SetProfileReplicas(_ context.Context, name string, counts map[string]int, _ *modelsvc.CPUProfile,
+	_ string,
+) (catalog.Model, error) {
+	m := catalog.Model{Name: name}
+	for p, n := range counts {
+		m.Profiles = append(m.Profiles, catalog.Profile{Name: p, Replicas: n})
+	}
+	return m, f.err
+}
+
 func (f *fakeModels) SetOwner(_ context.Context, name, owner, _ string) (catalog.Model, error) {
 	return catalog.Model{Name: name, Owner: owner}, f.err
 }