第五轮：锁/续跑/超时/自动分支/R4 探针与 encode-once/控制台加固；阶段内断点续跑（gen 按条、prep 按 shard、训练与 APG 定时原子存档+体面停止）；分歧以实现方意见为准

2026-10-17 18:57:48 +00:00
parent e3bb78388d
commit a5e779c515
36 changed files with 1199 additions and 285 deletions
@@ -0,0 +1,42 @@
+<!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;
+    const BASE = qs.get('ortLocal') === '1' ? '/webapp/vendor/ort/' : 'https://cdn.jsdelivr.net/npm/onnxruntime-web@1.20.1/dist/';
+    await new Promise((ok, no) => { const s = document.createElement('script'); s.src = BASE + '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 feat = new Float32Array((res.encOnce ? 1 : K) * F).map(() => Math.random() - 0.5);
+    const z = () => new Float32Array(K * H * 6).map(() => Math.random() * 2 - 1);
+    const run = () => 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>