papers/kai/tables/speed.tex

% speed.tex: written by `bench tex` (hanzoai/decision); Kai runs/a7, encoder 768 wide, 22 layers; timed ROCm, BF16; harness a1a4a73; benchmarks 039fbfe
% Kai and Laya on this runtime (hanzo-ml), same device and dtype, their calls interleaved; the last row names each checkpoint and its encoder. Jev is one network run, the same cells in every block.
\begin{tabular}{@{}r@{\quad}cc@{\quad}cc@{\quad}cc@{\quad}ccc@{}}
\toprule
 & \multicolumn{2}{c}{Kai} & \multicolumn{2}{c}{Laya} & \multicolumn{2}{c}{Jev, network} & \multicolumn{3}{c}{Questions/s} \\
$N$ & p50 & p95 & p50 & p95 & p50 & p95 & Kai & Laya & Jev \\
\midrule
\multicolumn{10}{@{}l}{\emph{ROCm, BF16}} \\
1 & 19.8 & 29.0 & 16.5 & 18.3 & 133 & 546 & 43.2 & 61.0 & 5.72 \\
10 & 44.7 & 105 & 116 & 173 & 155 & 221 & 195 & 82.7 & 62.9 \\
50 & 139 & 214 & 576 & 592 & 202 & 275 & 316 & 87.6 & 233 \\
100 & 314 & 333 & 1{,}168 & 1{,}222 & 343 & 556 & 323 & 85.7 & 267 \\
500 & 1{,}050 & 1{,}173 & 5{,}027 & 5{,}386 & 515 & 2{,}193 & 468 & 99.0 & 726 \\
1{,}000 & 1{,}981 & 2{,}014 & 9{,}772 & 10{,}375 & 602 & 1{,}077 & 508 & 101 & 1{,}489 \\
\bottomrule
\multicolumn{10}{@{}l@{}}{\footnotesize\begin{tabular}[t]{@{}l@{}}Kai runs/a7, encoder 768 wide, 22 layers \\ harness a1a4a73, benchmarks 039fbfe \\ timed ROCm, BF16 \\ Laya laya-multilingual: hanzoai/kai-1-multilingual@3119843b, encoder 768 wide, 22 layers \\ timed calls per N: ROCm, BF16 10 \\ evo (AMD Strix Halo, Radeon 8060S, ROCm)\end{tabular}} \\
\end{tabular}