Nemotron 3 Ultra + Miscellaneous changes

dashboard/src/lib/components/FamilyLogos.svelte

@@ -7,7 +7,14 @@
   let { family, class: className = "" }: FamilyLogoProps = $props();
 </script>
 
-{#if family === "favorites"}
+{#if family === "recommended"}
+  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
+    <path
+      d="M11 3l1.8 4.7L17.5 9.5l-4.7 1.8L11 16l-1.8-4.7L4.5 9.5l4.7-1.8L11 3z"
+    />
+    <path d="M18 13l.9 2.4 2.4.9-2.4.9-.9 2.4-.9-2.4-2.4-.9 2.4-.9.9-2.4z" />
+  </svg>
+{:else if family === "favorites"}
   <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
     <path
       d="M12 2l3.09 6.26L22 9.27l-5 4.87 1.18 6.88L12 17.77l-6.18 3.25L7 14.14 2 9.27l6.91-1.01L12 2z"

dashboard/src/lib/components/FamilySidebar.svelte

@@ -4,6 +4,7 @@
   type FamilySidebarProps = {
     families: string[];
     selectedFamily: string | null;
+    hasRecommended: boolean;
     hasFavorites: boolean;
     hasRecents: boolean;
     onSelect: (family: string | null) => void;
@@ -12,13 +13,15 @@
   let {
     families,
     selectedFamily,
+    hasRecommended,
     hasFavorites,
     hasRecents,
     onSelect,
   }: FamilySidebarProps = $props();
 
   // Family display names
   const familyNames: Record<string, string> = {
+    recommended: "Recommended",
     favorites: "Favorites",
     recents: "Recent",
     huggingface: "Hub",
@@ -45,6 +48,31 @@
 <div
   class="flex flex-col gap-1 py-2 px-1 border-r border-exo-yellow/10 bg-exo-medium-gray/30 min-w-[80px] sm:min-w-[72px] overflow-y-auto scrollbar-hide"
 >
+  <!-- Recommended (curated set) -->
+  {#if hasRecommended}
+    <button
+      type="button"
+      onclick={() => onSelect("recommended")}
+      class="group flex flex-col items-center justify-center p-2 rounded transition-all duration-200 cursor-pointer {selectedFamily ===
+      'recommended'
+        ? 'bg-exo-yellow/20 border-l-2 border-exo-yellow'
+        : 'hover:bg-white/5 border-l-2 border-transparent'}"
+      title="Recommended models"
+    >
+      <FamilyLogos
+        family="recommended"
+        class={selectedFamily === "recommended"
+          ? "text-exo-yellow"
+          : "text-white/50 group-hover:text-exo-yellow/70"}
+      />
+      <span
+        class="text-[11px] font-mono mt-0.5 {selectedFamily === 'recommended'
+          ? 'text-exo-yellow'
+          : 'text-white/40 group-hover:text-white/60'}">Rec'd</span
+      >
+    </button>
+  {/if}
+
   <!-- All models (no filter) -->
   <button
     type="button"

dashboard/src/lib/components/ModelPickerModal.svelte

@@ -22,6 +22,7 @@
     is_custom?: boolean;
     tasks?: string[];
     hugging_face_id?: string;
+    recommended?: boolean;
   }
 
   interface ModelGroup {
@@ -110,7 +111,7 @@
 
   // Local state
   let searchQuery = $state("");
-  let selectedFamily = $state<string | null>(null);
+  let selectedFamily = $state<string | null>("recommended");
   let expandedGroups = $state<Set<string>>(new Set());
   let showFilters = $state(false);
   let filters = $state<FilterState>({
@@ -210,6 +211,9 @@
       manualModelId = "";
       addModelError = null;
       justAddedModelId = null;
+      if (selectedFamily === "recommended" && !hasRecommended) {
+        selectedFamily = null;
+      }
       if (justAddedTimer) {
         clearTimeout(justAddedTimer);
         justAddedTimer = null;
@@ -242,6 +246,7 @@
       selectedFamily === "huggingface" ||
       selectedFamily === "recents" ||
       selectedFamily === "favorites" ||
+      selectedFamily === "recommended" ||
       query.length < 2 ||
       !noLocalResults
     ) {
@@ -477,7 +482,20 @@
     let result: ModelGroup[] = [...groupedModels];
 
     // Filter by family
-    if (selectedFamily === "favorites") {
+    if (selectedFamily === "recommended") {
+      result = result
+        .map((g) => {
+          const variants = g.variants.filter((v) => v.recommended);
+          if (variants.length === 0) return null;
+          return {
+            ...g,
+            variants,
+            smallestVariant: variants[0],
+            hasMultipleVariants: variants.length > 1,
+          };
+        })
+        .filter((g): g is ModelGroup => g !== null);
+    } else if (selectedFamily === "favorites") {
       result = result.filter((g) => favorites.has(g.id));
     } else if (
       selectedFamily &&
@@ -567,6 +585,10 @@
   // Check if any favorites exist
   const hasFavorites = $derived(favorites.size > 0);
 
+  const hasRecommended = $derived(
+    groupedModels.some((g) => g.variants.some((v) => v.recommended)),
+  );
+
   // Timestamp lookup for recent models
   const recentTimestamps = $derived(
     new Map(getRecentEntries().map((e) => [e.modelId, e.launchedAt])),
@@ -609,8 +631,9 @@
     );
   });
 
-  // Split filtered groups into recommended (fits_now) and others for visual separation
-  const recommendedGroups = $derived(
+  // Split filtered groups into ones that fit now and others, for visual
+  // separation (distinct from the curated "Recommended" tab).
+  const fitsGroups = $derived(
     filteredGroups.filter((g) =>
       g.variants.some((v) => getModelFitStatus(v.id) === "fits_now"),
     ),
@@ -783,6 +806,7 @@
       <FamilySidebar
         families={uniqueFamilies}
         {selectedFamily}
+        {hasRecommended}
         {hasFavorites}
         hasRecents={hasRecentsTab}
         onSelect={(family) => (selectedFamily = family)}
@@ -958,8 +982,8 @@
             {/if}
           </div>
         {:else}
-          <!-- Recommended for your cluster -->
-          {#if recommendedGroups.length > 0 && otherGroups.length > 0 && !searchQuery.trim()}
+          <!-- Fits in available memory -->
+          {#if fitsGroups.length > 0 && otherGroups.length > 0 && !searchQuery.trim()}
             <div
               class="sticky top-0 z-10 flex items-center gap-2 px-3 py-2 bg-green-950/60 border-b border-green-500/20 backdrop-blur-sm"
             >
@@ -978,14 +1002,11 @@
               </svg>
               <span
                 class="text-xs font-mono text-green-400 tracking-wider uppercase"
-                >Recommended for your cluster</span
-              >
-              <span class="text-xs font-mono text-green-400/50"
-                >— fits in available memory</span
+                >Fits in available memory</span
               >
             </div>
           {/if}
-          {#each recommendedGroups as group}
+          {#each fitsGroups as group}
             <ModelPickerGroup
               {group}
               isExpanded={expandedGroups.has(group.id)}
@@ -1004,7 +1025,7 @@
             />
           {/each}
           <!-- Other models -->
-          {#if otherGroups.length > 0 && recommendedGroups.length > 0 && !searchQuery.trim()}
+          {#if otherGroups.length > 0 && fitsGroups.length > 0 && !searchQuery.trim()}
             <div
               class="sticky top-0 z-10 flex items-center gap-2 px-3 py-2 bg-exo-dark-gray/80 border-y border-exo-medium-gray/20 backdrop-blur-sm"
             >

dashboard/src/lib/components/PrefillDecodeDisaggregation.svelte

@@ -1,5 +1,5 @@
 <script lang="ts">
-  import { onMount, onDestroy } from "svelte";
+  import { onMount } from "svelte";
   import FamilyLogos from "$lib/components/FamilyLogos.svelte";
   import {
     instances,
@@ -19,14 +19,10 @@
     VllmInstance?: Instance;
   };
 
-  let interval: ReturnType<typeof setInterval> | null = null;
-
   onMount(() => {
+    // One immediate refresh on mount; live updates ride the global /state poll
+    // in app.svelte.ts (no separate interval here — it doubled /state traffic).
     refreshState();
-    interval = setInterval(refreshState, 3000);
-  });
-  onDestroy(() => {
-    if (interval) clearInterval(interval);
   });
 
   type InstanceRow = {

dashboard/src/lib/stores/app.svelte.ts

@@ -606,9 +606,12 @@ class AppStore {
   /** Number of consecutive fetch failures. */
   private consecutiveFailures = 0;
   private static readonly CONNECTION_LOST_THRESHOLD = 3;
+  private static readonly STATE_POLL_INTERVAL_MS = 2000;
 
   private fetchInterval: ReturnType<typeof setInterval> | null = null;
   private previewsInterval: ReturnType<typeof setInterval> | null = null;
+  private stateEtag: string | null = null;
+  private visibilityListener: (() => void) | null = null;
   private lastConversationPersistTs = 0;
   private previousNodeIds: Set<string> = new Set();
 
@@ -1284,14 +1287,45 @@ class AppStore {
   startPolling() {
     this.fetchState();
     this.fetchFeatureFlags();
-    this.fetchInterval = setInterval(() => this.fetchState(), 1000);
+    this.startStateInterval();
+
+    // Pause polling while the tab is hidden — a backgrounded dashboard has no
+    // reason to keep pulling /state. Resume with an immediate fetch when the
+    // tab becomes visible again.
+    if (typeof document !== "undefined" && !this.visibilityListener) {
+      this.visibilityListener = () => {
+        if (document.hidden) {
+          this.stopStateInterval();
+        } else if (!this.fetchInterval) {
+          this.fetchState();
+          this.startStateInterval();
+        }
+      };
+      document.addEventListener("visibilitychange", this.visibilityListener);
+    }
   }
 
-  stopPolling() {
+  private startStateInterval() {
+    if (this.fetchInterval) return;
+    this.fetchInterval = setInterval(
+      () => this.fetchState(),
+      AppStore.STATE_POLL_INTERVAL_MS,
+    );
+  }
+
+  private stopStateInterval() {
     if (this.fetchInterval) {
       clearInterval(this.fetchInterval);
       this.fetchInterval = null;
     }
+  }
+
+  stopPolling() {
+    this.stopStateInterval();
+    if (this.visibilityListener && typeof document !== "undefined") {
+      document.removeEventListener("visibilitychange", this.visibilityListener);
+      this.visibilityListener = null;
+    }
     this.stopPreviewsPolling();
   }
 
@@ -1307,10 +1341,25 @@ class AppStore {
 
   async fetchState() {
     try {
-      const response = await fetch("/state");
+      const headers: Record<string, string> = {};
+      if (this.stateEtag) {
+        headers["If-None-Match"] = this.stateEtag;
+      }
+      const response = await fetch("/state", { headers });
+
+      // 304: state unchanged since our last poll — no body shipped. Keep the
+      // data we already have and treat it as a successful poll.
+      if (response.status === 304) {
+        this.lastUpdate = Date.now();
+        if (!this.isConnected) this.isConnected = true;
+        this.consecutiveFailures = 0;
+        return;
+      }
+
       if (!response.ok) {
         throw new Error(`Failed to fetch state: ${response.status}`);
       }
+      this.stateEtag = response.headers.get("ETag");
       const data: RawStateResponse = await response.json();
 
       if (data.topology) {

dashboard/src/routes/+page.svelte

@@ -783,6 +783,7 @@
       quantization?: string;
       base_model?: string;
       capabilities?: string[];
+      recommended?: boolean;
     }>
   >([]);
   type ModelMemoryFitStatus =

resources/inference_model_cards/mlx-community--DeepSeek-V4-Flash.toml

@@ -12,6 +12,7 @@ reasoning_dialect = "tool_conditional"
 
 context_length = 1048576
 backends = ["MlxMetal", "MlxCuda", "MlxCpu"]
+recommended = true
 [storage_size]
 in_bytes = 155095760030
 

resources/inference_model_cards/mlx-community--DeepSeek-V4-Pro.toml

@@ -12,6 +12,7 @@ reasoning_dialect = "tool_conditional"
 
 context_length = 1048576
 backends = ["MlxMetal", "MlxCuda", "MlxCpu"]
+recommended = true
 [storage_size]
 in_bytes = 849681803879
 

resources/inference_model_cards/mlx-community--GLM-5.1-DQ4plus-q8.toml

@@ -11,6 +11,7 @@ capabilities = ["text", "thinking"]
 reasoning_dialect = "post_last_user"
 context_length = 202752
 backends = ["MlxMetal", "MlxCuda", "MlxCpu"]
+recommended = true
 [storage_size]
 in_bytes = 465173655552
 

resources/inference_model_cards/mlx-community--GLM-5.1-MXFP4-Q8.toml

@@ -11,6 +11,7 @@ capabilities = ["text", "thinking"]
 reasoning_dialect = "post_last_user"
 context_length = 202752
 backends = ["MlxMetal", "MlxCuda", "MlxCpu"]
+recommended = true
 [storage_size]
 in_bytes = 405480321024
 

resources/inference_model_cards/mlx-community--GLM-5.1.toml

@@ -11,6 +11,7 @@ capabilities = ["text", "thinking"]
 reasoning_dialect = "post_last_user"
 context_length = 202752
 backends = ["MlxMetal", "MlxCuda", "MlxCpu"]
+recommended = true
 [storage_size]
 in_bytes = 1487822475264
 

resources/inference_model_cards/mlx-community--Kimi-K2.6-mlx-DQ3_K_M-q8.toml

@@ -11,6 +11,7 @@ capabilities = ["text", "thinking", "thinking_toggle", "vision"]
 reasoning_dialect = "suffix"
 context_length = 262144
 backends = ["MlxMetal", "MlxCuda", "MlxCpu"]
+recommended = true
 [storage_size]
 in_bytes = 470628683776
 

resources/inference_model_cards/mlx-community--Llama-3.2-1B-Instruct-4bit.toml

@@ -11,6 +11,7 @@ capabilities = ["text"]
 
 context_length = 131072
 backends = ["MlxMetal", "MlxCuda", "MlxCpu"]
+recommended = true
 [storage_size]
 in_bytes = 729808896
 

resources/inference_model_cards/mlx-community--MiniMax-M2.7-4bit-mxfp4.toml

@@ -11,6 +11,7 @@ capabilities = ["text", "thinking"]
 reasoning_dialect = "post_last_user"
 context_length = 196608
 backends = ["MlxMetal", "MlxCuda", "MlxCpu"]
+recommended = true
 [storage_size]
 in_bytes = 121537496794
 

resources/inference_model_cards/mlx-community--MiniMax-M2.7-4bit.toml

@@ -11,6 +11,7 @@ capabilities = ["text", "thinking"]
 reasoning_dialect = "post_last_user"
 context_length = 196608
 backends = ["MlxMetal", "MlxCuda", "MlxCpu"]
+recommended = true
 [storage_size]
 in_bytes = 128682598717
 

resources/inference_model_cards/mlx-community--MiniMax-M2.7-8bit.toml

@@ -11,6 +11,7 @@ capabilities = ["text", "thinking"]
 reasoning_dialect = "post_last_user"
 context_length = 196608
 backends = ["MlxMetal", "MlxCuda", "MlxCpu"]
+recommended = true
 [storage_size]
 in_bytes = 243002680786