Dashboard + LiteLLM config updates from maintenance

dashboard/dashboard.py

@@ -119,7 +119,7 @@ body { background: #0b0f17; color: #bcc3cd; font-family: -apple-system, BlinkMac
     <div class="d-flex gap-2">
       <select id="scatter-model" onchange="loadScatter()" style="font-size:10px;background:#1e293b;color:#94a3b8;border:1px solid #334155;border-radius:4px;padding:2px 6px">
         <option value="all">All Models</option>
-        <option value="qwen3.5-9b-vlm">9B VLM</option>
+        <option value="gemma-4-12b">12B VLM</option>
         <option value="qwen3.6-27B-code">27B Dense</option>
         <option value="qwen3.6-35B-A3B">35B MoE</option>
       </select>
@@ -136,9 +136,9 @@ body { background: #0b0f17; color: #bcc3cd; font-family: -apple-system, BlinkMac
 </div>
 
 <script>
-var MC={'qwen3.5-9b-vlm':'#22c55e','qwen3.6-27B-code':'#f59e0b','qwen3.6-35B-A3B':'#a78bfa'};
+var MC={'gemma-4-12b':'#22c55e','qwen3.6-27B-code':'#f59e0b','qwen3.6-35B-A3B':'#a78bfa'};
-var ML={'qwen3.5-9b-vlm':'Qwen3.5 9B VLM','qwen3.6-27B-code':'Qwen Code','qwen3.6-35B-A3B':'Qwen MoE'};
+var ML={'gemma-4-12b':'Gemma 4 12B','qwen3.6-27B-code':'Qwen Code','qwen3.6-35B-A3B':'Qwen MoE'};
-var GL={'qwen3.6-35B-A3B':'MoE - Strix Halo','qwen3.6-27B-code':'Dense - RTX 3090','qwen3.5-9b-vlm':'VLM - RTX 5070'};
+var GL={'qwen3.6-35B-A3B':'MoE - Strix Halo','qwen3.6-27B-code':'Dense - RTX 3090','gemma-4-12b':'VLM - RTX 5070'};
 function $(id){return document.getElementById(id);}
 
 function render(data){
@@ -147,7 +147,7 @@ var t=Object.values(data.route_counts||{}).reduce((a,b)=>a+b,0);
 var ta=0,tm=0;data.gpus.forEach(function(g){ta+=(g.active_requests||0);tm+=(g.max_concurrent||1)});
 $('kpi-total').textContent=t;$('kpi-active').textContent=ta+'/'+tm;$('kpi-agents').textContent=Object.keys(data.agent_counts||{}).length;
 $('update-time').textContent=new Date().toLocaleTimeString();
-var ids={'qwen3.6-35B-A3B':'gpu-moe','qwen3.6-27B-code':'gpu-dense','qwen3.5-9b-vlm':'gpu-light'};
+var ids={'qwen3.6-35B-A3B':'gpu-moe','qwen3.6-27B-code':'gpu-dense','gemma-4-12b':'gpu-light'};
 data.gpus.forEach(function(g){
 var el=$(ids[g.id]);if(!el)return;
 var a=g.active_requests||0,mx=g.max_concurrent||1;
@@ -179,14 +179,14 @@ var sc=pct>=100?'#ef4444':pct>=50?'#f59e0b':'#22c55e';
 var circ=188.5,dash=(pct/100)*circ;
 var h='<div class=\"d-inline-block position-relative mb-2\"><svg width=\"72\" height=\"72\"><circle cx=\"36\" cy=\"36\" r=\"30\" fill=\"none\" stroke=\"#1e293b\" stroke-width=\"6\"/><circle cx=\"36\" cy=\"36\" r=\"30\" fill=\"none\" stroke=\"'+sc+'\" stroke-width=\"6\" stroke-dasharray=\"'+dash+' '+(circ-dash)+'\" stroke-linecap=\"round\" transform=\"rotate(-90 36 36)\"/></svg><div style=\"position:absolute;top:50%;left:50%;transform:translate(-50%,-50%);text-align:center\"><div class=\"ring-label\" style=\"color:'+sc+'\">'+ta+'</div><div class=\"ring-sublabel\">/ '+tm+' slots</div></div></div>';
 h+='<div class=\"fw-bold mb-2 small\" style=\"color:'+sc+'\">'+st+'</div>';
-var lb={'qwen3.6-35B-A3B':'MoE','qwen3.6-27B-code':'Dense','qwen3.5-9b-vlm':'VLM'};
+var lb={'qwen3.6-35B-A3B':'MoE','qwen3.6-27B-code':'Dense','gemma-4-12b':'VLM'};
 data.gpus.forEach(function(g){var a=g.active_requests||0,mx=g.max_concurrent||1,gp=mx>0?Math.round(a/mx*100):0;h+='<div class=\"d-flex align-items-center gap-2 mb-1 justify-content-center\"><span class=\"small\" style=\"min-width:32px;text-align:right;font-size:10px\">'+(lb[g.id]||g.id)+'</span><div style=\"flex:1;max-width:70px;height:3px;background:#1e293b;border-radius:2px;overflow:hidden\"><div style=\"height:100%;width:'+gp+'%;background:'+sc+';border-radius:2px\"></div></div><span class=\"small\" style=\"min-width:22px;font-size:10px\">'+a+'/'+mx+'</span></div>'});
 el.innerHTML=h;
 }
 
 function renderGPUMetrics(data){
 var el=$('gpu-metrics-card');if(!el)return;
-var lb={'qwen3.6-35B-A3B':'MoE','qwen3.6-27B-code':'Dense','qwen3.5-9b-vlm':'VLM'};
+var lb={'qwen3.6-35B-A3B':'MoE','qwen3.6-27B-code':'Dense','gemma-4-12b':'VLM'};
 var h='';data.gpus.forEach(function(g){
 var nm=lb[g.id]||g.id,tp=g.temp_c||0,ut=g.gpu_util_pct||0,pw=g.power_w||0,pl=g.power_limit_w||0;
 var tc=tp>85?'#ef4444':tp>70?'#f59e0b':'#22c55e',uc=ut>90?'#ef4444':ut>70?'#f59e0b':'#22c55e';
@@ -219,8 +219,8 @@ function loadPerf(){fetch('/api/performance?window='+perfWindow).then(function(r
 function renderPerf(d){
 var models=d.models||[],reasons=d.reasons||[],agents=d.agents||[],sum=d.summary||{};
 // Latency bars: p50/p95/p99 per model
-var mlab={'qwen3.6-35B-A3B':'35B MoE','qwen3.6-27B-code':'27B Dense','qwen3.5-9b-vlm':'9B VLM'};
+var mlab={'qwen3.6-35B-A3B':'35B MoE','qwen3.6-27B-code':'27B Dense','gemma-4-12b':'12B VLM'};
-var mcol={'qwen3.6-35B-A3B':'#a78bfa','qwen3.6-27B-code':'#f59e0b','qwen3.5-9b-vlm':'#22c55e'};
+var mcol={'qwen3.6-35B-A3B':'#a78bfa','qwen3.6-27B-code':'#f59e0b','gemma-4-12b':'#22c55e'};
 if(!models.length){$('perf-latency').innerHTML='<div class="text-secondary small text-center py-4">Accumulating data...</div>';return;}
 var maxLat=Math.max(...models.map(function(m){return m.latency.p99||0}),1);
 var latHTML=models.map(function(m){
@@ -270,8 +270,8 @@ fetch('/api/scatter?window=24&model='+m).then(function(r){return r.json()}).then
 function renderScatter(d){
 var pts=d.points||[],el=$('scatter-plot'),lg=$('scatter-legend');
 if(!pts.length){el.innerHTML='<div class="text-secondary small text-center py-5">No data yet</div>';return;}
-var mcol={'qwen3.6-35B-A3B':'#a78bfa','qwen3.6-27B-code':'#f59e0b','qwen3.5-9b-vlm':'#22c55e','unknown':'#38bdf8'};
+var mcol={'qwen3.6-35B-A3B':'#a78bfa','qwen3.6-27B-code':'#f59e0b','gemma-4-12b':'#22c55e','unknown':'#38bdf8'};
-var mlab={'qwen3.6-35B-A3B':'35B MoE','qwen3.6-27B-code':'27B Dense','qwen3.5-9b-vlm':'9B VLM'};
+var mlab={'qwen3.6-35B-A3B':'35B MoE','qwen3.6-27B-code':'27B Dense','gemma-4-12b':'12B VLM'};
 var maxX=Math.max.apply(null,pts.map(function(p){return p.prompt_tokens||0}))||1000;
 var maxY=Math.max.apply(null,pts.map(function(p){return p.inference_ms||0}))||5000;
 // Log scale for X axis (prompt tokens vary widely)

litellm_config.yaml

@@ -11,9 +11,9 @@ model_list:
       api_base: http://192.168.68.8:8080/v1
       api_key: "not-needed"
 
-  - model_name: qwen3.5-9b-vlm
+  - model_name: gemma-4-12b
     litellm_params:
-      model: openai/qwen3.5-9b-vlm
+      model: openai/gemma-4-12b
       api_base: http://192.168.68.110:8080/v1
       api_key: "not-needed"