A node's page says which llmgw it runs and which model is on each GPU

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

CHANGELOG.md

@@ -26,6 +26,12 @@ APIs change between minors without a deprecation period.
 
 ## Unreleased
 
+### Added
+
+- **A node's page says what it runs.** It now shows the agent's version, marked when the control plane runs another,
+  and the engines with their versions. Each GPU row now names the models loaded on that card, and each engine row its
+  GPUs.
+
 ### Fixed
 
 - **A broken `auth.ldap` no longer stops every control plane.** It is the cluster's setting. A CA file that one

internal/web/locales/en/node.json

@@ -62,6 +62,8 @@
   "node.memory": "Memory",
   "node.cores_f": "%s cores",
   "node.no_engines": "No engines are placed on this node.",
+  "node.version_differs": "the control plane runs %s",
+  "node.gpu.models": "Models",
   "node.engines": "Engines: %s",
   "node.engines_none": "Engines: none installed",
   "node.model_files": "%d model file(s) on disk",

internal/web/locales/tr/node.json

@@ -61,6 +61,8 @@
   "node.memory": "Bellek",
   "node.cores_f": "%s çekirdek",
   "node.no_engines": "Bu düğüme yerleştirilmiş motor yok.",
+  "node.version_differs": "control plane %s çalıştırıyor",
+  "node.gpu.models": "Modeller",
   "node.engines": "Motorlar: %s",
   "node.engines_none": "Motorlar: hiçbiri kurulu değil",
   "node.model_files": "diskte %d model dosyası",

internal/web/node_page.go

@@ -6,6 +6,7 @@ import (
 	"html/template"
 	"log/slog"
 	"net/http"
+	"slices"
 	"sort"
 	"strings"
 	"time"
@@ -20,9 +21,13 @@ type nodePageData struct {
 	OnAdminListener bool
 	Node            adminapi.NodeView
 	Engines         []nodeEngine
-	Charts          *nodeCharts
-	HasHistory      bool
-	Back, Logs      string
+	// GPUModels are the models on each of the node's GPUs, by index.
+	GPUModels map[int][]string
+	// EngineVersions are the installed engines and their versions, sorted.
+	EngineVersions []string
+	Charts         *nodeCharts
+	HasHistory     bool
+	Back, Logs     string
 	// Self is this page's address, for the in-place refresh.
 	Self         string
 	Version, Now string
@@ -34,6 +39,7 @@ type nodePageData struct {
 // nodeEngine is one engine running on the node, and its share of it.
 type nodeEngine struct {
 	Replica, Model, Shard, State string
+	GPUs                         []int
 	CPUCores                     float64
 	MemoryBytes                  int64
 	// CPUShare is its cores as a percentage of the machine, for the bar.
@@ -128,7 +134,15 @@ func NodePage(src Source, history History, window time.Duration, onAdminListener
 					continue
 				}
 				e := nodeEngine{Replica: rep.ID, Model: rep.Model, Shard: sh.ID, State: sh.State,
-					CPUCores: sh.CPUCores, MemoryBytes: sh.MemoryBytes}
+					GPUs: sh.GPUs, CPUCores: sh.CPUCores, MemoryBytes: sh.MemoryBytes}
+				for _, g := range sh.GPUs {
+					if d.GPUModels == nil {
+						d.GPUModels = map[int][]string{}
+					}
+					if !slices.Contains(d.GPUModels[g], rep.Model) {
+						d.GPUModels[g] = append(d.GPUModels[g], rep.Model)
+					}
+				}
 				if l := d.Node.Load; l != nil && l.CPUs > 0 {
 					e.CPUShare = sh.CPUCores * 100 / float64(l.CPUs)
 				}
@@ -137,6 +151,10 @@ func NodePage(src Source, history History, window time.Duration, onAdminListener
 			}
 		}
 		sort.Slice(d.Engines, func(i, j int) bool { return d.Engines[i].CPUCores > d.Engines[j].CPUCores })
+		for e, v := range d.Node.EngineVersions {
+			d.EngineVersions = append(d.EngineVersions, e+" "+v)
+		}
+		sort.Strings(d.EngineVersions)
 
 		if history != nil {
 			d.Charts = loadNodeCharts(r.Context(), l, history, id, replicas, d.Node.GPUTotal, window, log)

internal/web/node_page_test.go

@@ -270,3 +270,48 @@ func TestTheClusterPageDrawsItsGPUsByClass(t *testing.T) {
 		}
 	}
 }
+
+// versionSource is hotSource with an agent a release behind, a model on its
+// second GPU, and engines with their versions.
+type versionSource struct{ hotSource }
+
+func (versionSource) Nodes() []adminapi.NodeView {
+	n := hotSource{}.Nodes()[0]
+	n.AgentVersion = "v0"
+	n.EngineVersions = map[string]string{"llamacpp": "b10991", "comfyui": "0.39.2"}
+	return []adminapi.NodeView{n}
+}
+
+func (versionSource) Replicas(string) []adminapi.ReplicaView {
+	r := fakeSource{}.Replicas("")
+	r[0].Shards[0].GPUs = []int{1}
+	return r
+}
+
+func TestANodesPageSaysWhatItRunsAndWhichModelIsOnEachGPU(t *testing.T) {
+	_, body := get(t, nodeMux(versionSource{}, nil), "http://x/admin/nodes/llmgw-node01", nil)
+	model := versionSource{}.Replicas("")[0].Model
+	for _, want := range []string{
+		// The page's control plane runs v1: an agent on v0 is marked.
+		`class="bad" title="the control plane runs v1">llmgw v0</span>`,
+		"Engines: comfyui 0.39.2, llamacpp b10991",
+	} {
+		if !strings.Contains(body, want) {
+			t.Errorf("the page lacks %q", want)
+		}
+	}
+	// GPU 1 holds the model, GPU 0 nothing.
+	rows := strings.Split(body, "<tr>")
+	var gpu0, gpu1 string
+	for _, row := range rows {
+		switch {
+		case strings.HasPrefix(row, "\n  <td class=\"num\">0</td>"):
+			gpu0 = row
+		case strings.HasPrefix(row, "\n  <td class=\"num\">1</td>"):
+			gpu1 = row
+		}
+	}
+	if !strings.Contains(gpu1, "<td>"+model+"</td>") || strings.Contains(gpu0, model) {
+		t.Errorf("GPU rows:\n0: %.300s\n1: %.300s", gpu0, gpu1)
+	}
+}

internal/web/templates/node.html

@@ -11,6 +11,7 @@
   <h1>{{.Node.ID}}</h1>
   <p class="sub"><span class="state state-{{.Node.State}}">{{t (print "dash.state." .Node.State)}}</span>
     {{with .Node.OS}} · {{.}}{{end}}{{with .Node.MgmtAddr}} · {{.}}{{end}}
+    {{with .Node.AgentVersion}} · <span{{if ne . $.Version}} class="bad" title="{{t "node.version_differs" $.Version}}"{{end}}>llmgw {{.}}</span>{{end}}
     · {{if .Node.LastSeenAgo}}{{t "node.last_seen" .Node.LastSeenAgo}}{{else}}{{t "node.never_seen"}}{{end}} · <a href="{{.Logs}}">{{t "dash.nodes.logs"}}</a></p>
   {{if .OnAdminListener}}<nav><a href="{{.Back}}">{{t "node.nav.cluster"}}</a></nav>{{else}}{{template "nav" .Nav}}{{end}}
 </header>
@@ -39,7 +40,7 @@
 {{if .Unhealthy}}<p class="note bad">{{join .Unhealthy}}</p>{{end}}
 {{with .Load}}{{if .GPUs}}
 <h2>{{t "node.gpus"}}</h2>
-<table class="rows"><tr><th class="num">GPU</th><th>{{t "node.gpu.busy"}}</th><th>{{t "node.gpu.memory_used"}}</th><th class="num">{{t "node.gpu.temp"}}</th><th class="num">{{t "node.gpu.memory_temp"}}</th><th>{{t "node.gpu.power"}}</th><th class="num">{{t "node.gpu.clock"}}</th><th>{{t "node.gpu.held_back"}}</th></tr>
+<table class="rows"><tr><th class="num">GPU</th><th>{{t "node.gpu.busy"}}</th><th>{{t "node.gpu.memory_used"}}</th><th class="num">{{t "node.gpu.temp"}}</th><th class="num">{{t "node.gpu.memory_temp"}}</th><th>{{t "node.gpu.power"}}</th><th class="num">{{t "node.gpu.clock"}}</th><th>{{t "node.gpu.models"}}</th><th>{{t "node.gpu.held_back"}}</th></tr>
 {{range .GPUs}}<tr>
   <td class="num">{{.Index}}</td>
   {{/* From the last sample; a dash where the driver or an older agent did
@@ -52,6 +53,7 @@
   <td class="num">{{if .SMClockMHz}}{{num .SMClockMHz 0}} MHz{{else}}—{{end}}</td>
   {{/* The driver's reasons and the wear are named as the driver and the
        inventory name them, in English. */}}
+  <td>{{with index $.GPUModels .Index}}{{join .}}{{else}}<span class="note">—</span>{{end}}</td>
   <td>{{if .Throttle}}<span class="bad">{{join .Throttle}}</span>{{else}}<span class="note">{{t "node.gpu.nothing"}}</span>{{end}}{{if gt .ECCUncorrected 0.0}} <span class="bad">{{t "node.gpu.ecc" (num .ECCUncorrected 0)}}</span>{{end}}{{with .Wear}}{{with .Problems}}<br><span class="bad">{{join .}}</span>{{end}}{{if gt .PCIeReplays 0}} <span class="note">{{t "node.gpu.pcie" (count .PCIeReplays)}}</span>{{end}}{{end}}</td>
 </tr>{{end}}</table>
 {{end}}{{end}}
@@ -106,16 +108,17 @@
 
 <h2>{{t "node.runs"}}</h2>
 {{if .Engines}}
-<table class="rows"><tr><th>{{t "dash.col.model"}}</th><th>{{t "dash.col.replica"}}</th><th>{{t "dash.col.state"}}</th><th>CPU</th><th class="num">{{t "node.memory"}}</th></tr>
+<table class="rows"><tr><th>{{t "dash.col.model"}}</th><th>{{t "dash.col.replica"}}</th><th>{{t "dash.col.state"}}</th><th>GPU</th><th>CPU</th><th class="num">{{t "node.memory"}}</th></tr>
 {{range .Engines}}<tr>
   <td>{{.Model}}</td>
   <td><code>{{.Replica}}</code></td>
   <td class="state state-{{.State}}">{{t (print "dash.state." .State)}}</td>
+  <td>{{if .GPUs}}{{range $i, $g := .GPUs}}{{if $i}}, {{end}}{{$g}}{{end}}{{else}}—{{end}}</td>
   <td class="load">{{template "minibar" pctbar .CPUShare}}<span class="load-v">{{t "node.cores_f" (num .CPUCores 1)}}</span></td>
   <td class="num">{{if .MemoryBytes}}{{bytes .MemoryBytes}}{{else}}—{{end}}</td>
 </tr>{{end}}</table>
 {{else}}<p class="empty">{{t "node.no_engines"}}</p>{{end}}
-<p class="note">{{if .Node.Engines}}{{t "node.engines" (join .Node.Engines)}}{{else}}{{t "node.engines_none"}}{{end}}{{if .Node.Models}} · {{t "node.model_files" (len .Node.Models)}}{{end}}.</p>
+<p class="note">{{if .EngineVersions}}{{t "node.engines" (join .EngineVersions)}}{{else if .Node.Engines}}{{t "node.engines" (join .Node.Engines)}}{{else}}{{t "node.engines_none"}}{{end}}{{if .Node.Models}} · {{t "node.model_files" (len .Node.Models)}}{{end}}.</p>
 </div>
 
 {{if .HasHistory}}{{with .Charts}}