50 lines
4.1 KiB
HTML
50 lines
4.1 KiB
HTML
<!doctype html>
|
||
<meta charset="utf-8">
|
||
<title>R4 推理延迟探针</title>
|
||
<!-- 2026-10-18 第五轮：由 ml/eval/r4_probe.py 在无头浏览器里打开，测部署形态的单次推理（1 行特征 + K=8 条候选）。
|
||
参数：model= 模型 URL；ep=wasm|webgpu；threads=auto|N；proxy=0|1；n= 次数；ortLocal=1 用 vendor/ort/。
|
||
结果 POST 到 /r4/result；同时记录 20 ms 节拍的最大间隔（推理是否卡主线程）。也可手动打开看页面上的结果。 -->
|
||
<pre id="o">运行中…</pre>
|
||
<script>
|
||
(async () => {
|
||
const qs = new URLSearchParams(location.search), o = document.getElementById('o');
|
||
const res = { ep: qs.get('ep') || 'wasm', threadsArg: qs.get('threads') || 'auto', hc: navigator.hardwareConcurrency, coi: self.crossOriginIsolated, ua: navigator.userAgent };
|
||
const post = async () => { o.textContent = JSON.stringify(res, null, 1); try { await fetch('/r4/result', { method: 'POST', body: JSON.stringify(res) }); } catch (e) {} };
|
||
try {
|
||
const MODEL = qs.get('model'), N = +qs.get('n') || 150, K = 8, F = 83, H = 16;
|
||
/* 2026-10-18 第六轮：本地前缀用绝对 URL（ORT 以 import() 加载 .mjs，相对前缀会被当成裸模块名）；WebGPU 后端只在 ort.webgpu.min.js 里 */
|
||
const BASE = qs.get('ortLocal') === '1' ? new URL('/webapp/vendor/ort/', location.href).href : 'https://cdn.jsdelivr.net/npm/onnxruntime-web@1.20.1/dist/';
|
||
res.ortBase = BASE;
|
||
if (res.ep === 'webgpu') { // 先看浏览器给不给适配器，区分"没有 GPU"与"ort 包不含 WebGPU"
|
||
res.hasGpu = !!navigator.gpu;
|
||
try { const ad = navigator.gpu && await navigator.gpu.requestAdapter(); res.adapter = ad ? ((ad.info && (ad.info.vendor + ' ' + ad.info.architecture)) || 'ok') : null; } catch (e) { res.adapter = 'error: ' + e; }
|
||
}
|
||
await new Promise((ok, no) => { const s = document.createElement('script'); s.src = BASE + (res.ep === 'webgpu' ? 'ort.webgpu.min.js' : 'ort.min.js'); s.onload = ok; s.onerror = () => no(new Error('加载 ort 失败：' + s.src)); document.head.appendChild(s); });
|
||
const meta = await (await fetch(MODEL.replace('.onnx', '.meta.json'))).json();
|
||
ort.env.wasm.wasmPaths = BASE;
|
||
// 与 ik-policy-glue.js 同一套默认值
|
||
ort.env.wasm.numThreads = !self.crossOriginIsolated ? 1 : (res.threadsArg === 'auto' ? Math.max(1, Math.min(16, Math.floor(res.hc * 0.6))) : +res.threadsArg);
|
||
res.threads = ort.env.wasm.numThreads;
|
||
res.proxy = res.ep === 'wasm' && qs.get('proxy') !== '0';
|
||
const opts = { executionProviders: res.ep === 'webgpu' ? ['webgpu'] : ['wasm'], graphOptimizationLevel: 'all' };
|
||
let sess = null;
|
||
if (res.proxy) { ort.env.wasm.proxy = true; try { sess = await ort.InferenceSession.create(MODEL, opts); } catch (e) { res.proxyError = String(e); res.proxy = false; ort.env.wasm.proxy = false; } }
|
||
if (!sess) sess = await ort.InferenceSession.create(MODEL, opts);
|
||
res.encOnce = !!meta.enc_once;
|
||
const z = () => new Float32Array(K * H * 6).map(() => Math.random() * 2 - 1);
|
||
/* proxy 模式下 ORT 会把输入 buffer 转移给 Worker（detach），feat 必须每次新建 */
|
||
const run = () => { const feat = new Float32Array((res.encOnce ? 1 : K) * F).map(() => Math.random() - 0.5);
|
||
return sess.run({ feat: new ort.Tensor('float32', feat, [res.encOnce ? 1 : K, F]), z: new ort.Tensor('float32', z(), [K, H, 6]) }); };
|
||
for (let i = 0; i < 10; i++) await run();
|
||
let last = performance.now(); const gaps = [];
|
||
const tk = setInterval(() => { const t = performance.now(); gaps.push(t - last); last = t; }, 20);
|
||
const ts = [];
|
||
for (let i = 0; i < N; i++) { const t = performance.now(); await run(); ts.push(performance.now() - t); await new Promise(r => setTimeout(r, 40)); }
|
||
clearInterval(tk);
|
||
const p = (a, x) => { const s = a.slice().sort((u, v) => u - v); return +s[Math.min(s.length - 1, Math.floor(s.length * x))].toFixed(2); };
|
||
Object.assign(res, { n: N, K, p50: p(ts, .5), p95: p(ts, .95), p99: p(ts, .99), tickGapP99: p(gaps, .99), tickGapMax: +Math.max(...gaps).toFixed(1) });
|
||
} catch (e) { res.error = String(e && e.message || e); }
|
||
await post();
|
||
})();
|
||
</script>
|