abiba-bot/inference-harness
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

VLM migration: qwen3.5-9b-vlm → gemma-4-12b across entire harness

Browse Source 
- router/router.py: model ID, context window (131K→262K), VRAM comment
- litellm_config.yaml: model name updated
- gpu-router.conf, gpu-router-docker.conf: pool names, comments
- dashboard/dashboard.py: MODELS array refactor for single-point config
- README.md: architecture diagram, model table
This commit is contained in:
Abiba Bot
2026-06-05 21:37:18 +00:00
parent 370f5546dd
commit dace488f93
6 changed files with 36 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files
dashboard/dashboard.py
+10 -5
View File
@@ -111,9 +111,15 @@ body { background: #0b0f17; color: #bcc3cd; font-family: -apple-system, BlinkMac
</div>
<script>
var MC={'gemma-4-12b':'#22c55e','qwen3.6-27B-code':'#f59e0b','qwen3.6-35B-A3B':'#a78bfa'};
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','gemma-4-12b':'VLM - New Backend'};
// ═══ MODEL CONFIG — Update ONLY this array for model migrations ═══
var MODELS=[
{id:'qwen3.6-35B-A3B',label:'Qwen MoE',gpu:'MoE - Strix Halo',color:'#a78bfa',short:'MoE',domId:'gpu-moe'},
{id:'qwen3.6-27B-code',label:'Qwen Code',gpu:'Dense - RTX 3090',color:'#f59e0b',short:'Dense',domId:'gpu-dense'},
{id:'gemma-4-12b',label:'Gemma 4 12B',gpu:'VLM - New Backend',color:'#22c55e',short:'VLM',domId:'gpu-light'}
];
// Auto-derived lookups — DO NOT EDIT below
var MC={},ML={},GL={},ids={},lb={};
MODELS.forEach(function(m){MC[m.id]=m.color;ML[m.id]=m.label;GL[m.id]=m.gpu;ids[m.id]=m.domId;lb[m.id]=m.short;});
function $(id){return document.getElementById(id);}
function render(data){
@@ -122,7 +128,6 @@ 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;
$('update-time').textContent=new Date().toLocaleTimeString();
var ids={'qwen3.6-35B-A3B':'gpu-moe','qwen3.6-27B-code':'gpu-dense','gemma-4-12b':'gpu-light'};
data.gpus.forEach(function(g){
var el=$(ids[g.id]);if(!el)return;
var a=g.active_requests||0,mx=g.max_concurrent||1;
@@ -161,7 +166,7 @@ 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','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';