feat: add evaluation and safety chapter

This commit is contained in:
wuyang
2026-07-29 09:33:59 +08:00
parent 1683e19b16
commit cfd2367e88
26 changed files with 4031 additions and 52 deletions
+3 -3
View File
@@ -251,7 +251,7 @@ if (overview.sections !== 31 || overview.tocLinks !== 31) failures.push("章节/
if (overview.paperLinks !== 62) failures.push("正式论文链不是 62 个节点");
if (overview.ledgers !== 18) failures.push("十八本服务账结构异常");
if (overview.labTabs !== 4 || overview.labPanels !== 4) failures.push("四联实验结构异常");
if (overview.navLinks !== 18 || home.navLinks !== 18 || mobile.mobileLinks !== 18) failures.push("全站导航未同步推理服务专题");
if (overview.navLinks !== 19 || home.navLinks !== 19 || mobile.mobileLinks !== 19) failures.push("全站导航未同步评测专题");
if (overview.documentOverflow > 1 || mobile.documentOverflow > 1) failures.push("桌面或移动端存在横向溢出");
if (!memory.initial.weight.includes("32.6") || !memory.initial.perToken.includes("128") || memory.initial.visible !== "memory") failures.push("GQA 默认显存账异常");
if (!memory.exploded.status.includes("OOM") || !memory.exploded.fit.includes("over")) failures.push("极端 MHA 配置没有触发 OOM");
@@ -264,8 +264,8 @@ if (!fleet.k3.avoided.includes("320K") || fleet.k3.shortSlo !== "PROTECTED") fai
if (!fleet.failed.state.includes("SECONDARY RE-PREFILL") || !fleet.failed.recompute.includes("FAILED PRIMARY")) failures.push("缓存故障没有触发原子失效后的重算");
if (fleet.bursty.shortSlo !== "VIOLATED") failures.push("平均并发阈值没有暴露长请求突发");
if (fleet.keyboardSelected !== "phase" || fleet.keyboardVisible !== "phase") failures.push("实验键盘 tab 导航异常");
if (home.releaseCards !== 13 || !home.firstRelease.includes("推理优化") || home.firstHref !== "/systems/inference/") failures.push("首页推理服务首发入口异常");
if (home.paperCount !== "400" || papers.total !== 400 || !papers.hasFilter || papers.visible !== 45) failures.push("论文库推理服务标签或总数异常");
if (home.releaseCards !== 14 || !home.firstRelease.includes("榜单不是体检单") || home.firstHref !== "/evaluation/") failures.push("首页评测首发入口异常");
if (home.paperCount !== "450" || papers.total !== 450 || !papers.hasFilter || papers.visible !== 45) failures.push("论文库推理服务标签或总数异常");
if (!mobile.menuVisible || mobile.menuOpen !== "true" || mobile.tabs !== 4) failures.push("移动端导航或实验异常");
if (mobile.offenders.length) failures.push(`移动端越界元素:${JSON.stringify(mobile.offenders)}`);
if (exceptions.length) failures.push(`浏览器异常:${exceptions.join(" | ")}`);