wuyang/llm-atlas
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: execute FlashKDA on RTX 5090

Browse Source
This commit is contained in:
wuyang
2026-07-29 13:36:49 +08:00
parent 1146208b5e
commit 2ef846f751
16 changed files with 1189 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/check-k3-browser.mjs
+13 -2
View File
@@ -221,15 +221,24 @@ const artifacts = await evaluate(`(() => {
flash: text("[data-benchmark-flash]"),
fla: text("[data-benchmark-fla]"),
speedup: text("[data-benchmark-speedup]"),
localMean: text("[data-local-mean]"),
localP95: text("[data-local-p95]"),
localThroughput: text("[data-local-throughput]"),
exactSuite: root.textContent.includes("6 / 6 PASS") && root.textContent.includes("MAX ABS ERROR"),
cv: text("[data-router-cv]"),
zero: text("[data-router-zero]"),
};
input("[data-benchmark-device]", "gb200");
input("[data-benchmark-case]", "Varlen, \\\`seq_lens\\\`=\\\`1024 x 8\\\`");
input("[data-local-case]", "k3_varlen_shape");
input("[data-local-state]", "fp32_state");
input("[data-router-mode]", "bias");
const reproductionChanged = {
flash: text("[data-benchmark-flash]"),
speedup: text("[data-benchmark-speedup]"),
localMean: text("[data-local-mean]"),
localP95: text("[data-local-p95]"),
localMode: text("[data-local-mode-copy]"),
cv: text("[data-router-cv]"),
zero: text("[data-router-zero]"),
};
@@ -253,6 +262,7 @@ await pause(180);
await screenshot("/tmp/llm-atlas-k3-lab-desktop.png");
await evaluate(`(() => {
document.querySelector("[data-k3-artifact-lab]").scrollIntoView({ block: "start", behavior: "instant" });
document.querySelector('[data-artifact-tab="reproduction"]')?.click();
window.scrollBy(0, -82);
})()`);
await pause(180);
@@ -297,6 +307,7 @@ await pause(180);
await screenshot("/tmp/llm-atlas-k3-mobile.png");
await evaluate(`(() => {
document.querySelector("[data-k3-artifact-lab]").scrollIntoView({ block: "start", behavior: "instant" });
document.querySelector('[data-artifact-tab="reproduction"]')?.click();
window.scrollBy(0, -64);
})()`);
await pause(180);
@@ -334,8 +345,8 @@ if (artifacts.tensors.panel !== "tensors" || artifacts.tensors.groups !== 3 || a
if (!artifacts.mla.visible || artifacts.mla.rows !== 5 || !artifacts.mla.has576) failures.push("MLA header shape 视图异常");
if (artifacts.parameterInitial.panel !== "parameters" || artifacts.parameterInitial.shape !== "[128] F32" || !artifacts.parameterInitial.conflict) failures.push("A_log 工件冲突审计异常");
if (artifacts.parameterChanged.shape !== "[96,128] F32" || !artifacts.parameterChanged.count.includes("12,288")) failures.push("真实 dt_bias 参数切换异常");
if (artifacts.reproductionInitial.panel !== "reproduction" || numeric(artifacts.reproductionInitial.speedup) !== 1.85 || numeric(artifacts.reproductionInitial.cv) < 2) failures.push("FlashKDA H20 或 router 初始探针异常");
if (numeric(artifacts.reproductionChanged.speedup) !== 3.27 || numeric(artifacts.reproductionChanged.flash) !== 0.7064 || numeric(artifacts.reproductionChanged.cv) <= numeric(artifacts.reproductionInitial.cv) || numeric(artifacts.reproductionChanged.zero) <= numeric(artifacts.reproductionInitial.zero)) failures.push("GB200 benchmark 或 synthetic router counterexample 未更新");
if (artifacts.reproductionInitial.panel !== "reproduction" || numeric(artifacts.reproductionInitial.speedup) !== 1.85 || numeric(artifacts.reproductionInitial.localMean) < 2.6 || !artifacts.reproductionInitial.exactSuite || numeric(artifacts.reproductionInitial.cv) < 2) failures.push("FlashKDA H20、本机 exact suite 或 router 初始探针异常");
if (numeric(artifacts.reproductionChanged.speedup) !== 3.27 || numeric(artifacts.reproductionChanged.flash) !== 0.7064 || numeric(artifacts.reproductionChanged.localMean) >= numeric(artifacts.reproductionInitial.localMean) || !artifacts.reproductionChanged.localMode.includes("FP32 state") || numeric(artifacts.reproductionChanged.cv) <= numeric(artifacts.reproductionInitial.cv) || numeric(artifacts.reproductionChanged.zero) <= numeric(artifacts.reproductionInitial.zero)) failures.push("GB200 benchmark、本机 varlen/state 或 synthetic router counterexample 未更新");
if (artifacts.keyboardSelected !== "tensors" || artifacts.keyboardVisible !== "tensors") failures.push("开放工件键盘 tab 导航异常");
if (!mobile.menuVisible || mobile.menuOpen !== "true" || mobile.tabs !== 8 || mobile.artifactTabs !== 4 || mobile.artifactLayers !== 93) 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)}`);