michael/AI-Profile-Router
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Document unified Medium slots and dashboard capacity

Browse Source
This commit is contained in:
Mikei386
2026-09-20 18:52:07 +02:00
parent 9af719674b
commit 53320fa6c3
9 changed files with 94 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files
platform/llama-dashboard/app.py
+16 -4
View File
@@ -270,6 +270,7 @@ def llama_runtime() -> dict[str, Any]:
flags = {
"--flash-attn": "flash_attention",
"--cache-prompt": "prompt_cache",
"--kv-unified": "kv_unified",
"--mmproj-offload": "vision_offload",
}
try:
@@ -843,10 +844,20 @@ function stableLiveRate(kind,tokensTotal,secondsTotal,gauge,active){
if(state.value!=null&&(active||now-state.seen<8000)) return {text:`${deNum(state.value)} tok/s`,fresh:now-state.seen<2500};
return {text:active?'misst …':'–',fresh:false};
}
function slotHtml(s){
let used=s.context_used||0,total=s.n_ctx||0,p=total?Math.min(100,used/total*100):0;
function sharedSlotPool(slots,unified){
if(!unified||!Array.isArray(slots)||slots.length<2)return null;
const total=Math.max(0,...slots.map(s=>Number(s.n_ctx)||0));
const used=slots.reduce((sum,s)=>sum+Math.max(0,Number(s.context_used)||0),0);
return total?{total,used,free:Math.max(0,total-used)}:null;
}
function slotHtml(s,pool){
let used=Math.max(0,Number(s.context_used)||0),total=Math.max(0,Number(s.n_ctx)||0);
let available=pool?Math.min(total,used+pool.free):total;
let p=available?Math.min(100,used/available*100):0;
let state=s.processing?'arbeitet':'frei';
return `<div class="slot"><div class="slot-head"><b>Slot ${s.id??'–'} · ${state}</b><span class="badge">${s.speculative?'MTP aktiv':'Standard'}</span></div><div class="bar-label"><span>${deNum(used)} / ${deNum(total)} Token</span><span>${p.toFixed(1)} %</span></div><div class="bar"><div class="fill" style="width:${p}%"></div></div><div class="metrics">${metric(deNum(s.prompt_tokens),'Prompt')}${metric(deNum(s.prompt_cached),'Cache-Token')}${metric(deNum(s.decoded_tokens),'generiert')}${metric(deNum(s.remaining_generation),'Ausgabe übrig')}${metric(s.task_id??'–','Task-ID')}${metric(s.temperature??'–','Temperatur')}${metric(boolLabel(s.stream),'Streaming')}${metric(deNum(s.max_tokens),'Ausgabelimit')}</div></div>`;
let capacity=pool?`${deNum(used)} / ${deNum(available)} Token aktuell möglich`:`${deNum(used)} / ${deNum(total)} Token`;
let shared=pool?`<span>Gemeinsamer Pool: ${deNum(pool.free)} Token frei</span>`:'';
return `<div class="slot"><div class="slot-head"><b>Slot ${s.id??'–'} · ${state}</b><span class="badge">${s.speculative?'MTP aktiv':'Standard'}</span></div><div class="bar-label"><span>${capacity}</span><span>${p.toFixed(1)} %</span></div><div class="bar"><div class="fill" style="width:${p}%"></div></div>${shared?`<div class="sub">${shared}</div>`:''}<div class="metrics">${metric(deNum(s.prompt_tokens),'Prompt')}${metric(deNum(s.prompt_cached),'Cache-Token')}${metric(deNum(s.decoded_tokens),'generiert')}${metric(deNum(s.remaining_generation),'Ausgabe übrig')}${metric(s.task_id??'–','Task-ID')}${metric(s.temperature??'–','Temperatur')}${metric(boolLabel(s.stream),'Streaming')}${metric(deNum(s.max_tokens),'Ausgabelimit')}</div></div>`;
}
async function refreshFull(){
try{
@@ -866,7 +877,8 @@ async function refreshFull(){
$('cacheSub').textContent=hit==null?'Keine Cache-Metrik':`${deNum(cached)} wiederverwendet · ${deNum(processed)} neu`;
$('requestState').textContent=`${running} aktiv · ${waiting} wartet`;
$('requestSub').textContent=`${(lt.slots||[]).filter(s=>!s.processing).length} freie Slots`;
$('slotCards').innerHTML=(lt.slots||[]).map(slotHtml).join('')||'<div class="sub">Slot-Telemetrie momentan nicht verfügbar</div>';
let slots=lt.slots||[],slotPool=sharedSlotPool(slots,lr.kv_unified===true);
$('slotCards').innerHTML=slots.map(s=>slotHtml(s,slotPool)).join('')||'<div class="sub">Slot-Telemetrie momentan nicht verfügbar</div>';
let drafted=Number(met.spec_decode_num_draft_tokens_total||0),accepted=Number(met.spec_decode_num_accepted_tokens_total||0),acceptance=drafted?accepted/drafted*100:null;
$('mtpAcceptance').textContent=acceptance==null?'–':`${acceptance.toFixed(1)} % akzeptiert`;$('mtpBar').style.width=`${acceptance||0}%`;
$('mtpDrafted').textContent=deNum(drafted);$('mtpAccepted').textContent=deNum(accepted);$('mtpSteps').textContent=deNum(met.spec_decode_num_drafts_total);$('mtpDepth').textContent=lr.mtp_draft_tokens??'–';