mirror of
https://github.com/hanzoai/papers.git
synced 2026-10-29 07:34:31 +00:00
zeekayandHanzo Dev
2de2cfdad9
Three defects an audit found in published sources, each fixed at the source. A control-plane IP was printed in a paper the site serves — hanzo-platform's deployment section named the cluster's address, and the unified-harness paper named two. A reader does not need our addresses to follow the argument, and an attacker does not need to scan for them. Two defense papers carried 'Approved for public release; distribution unlimited'. That is a Department of Defense distribution statement, issued by a review office after a review we have not requested and did not undergo. We may publish these papers because they are ours; we may not claim a marking that asserts a federal authority reviewed them. refutation-driven-perf reported a ROCm decode win of 1.07x. That comparison was refuted on 2026-07-20: the llama-HIP build it beat was a weak one, and against a properly built llama on the same gfx1151 box we lose both phases — decode 0.91x, prefill 0.72x. Both are now in the table, marked open, and the two prose restatements of the win are gone. A paper about refutation cannot be the last place a refuted number survives. Co-authored-by: Hanzo Dev <[email protected]>
59 lines
1.5 KiB
TeX
59 lines
1.5 KiB
TeX
\section{Production Deployment}
|
|
|
|
\label{sec:production}
|
|
|
|
\subsection{Infrastructure}
|
|
|
|
Hanzo Platform runs on two DOKS (DigitalOcean Kubernetes Service) clusters:
|
|
|
|
\begin{itemize}[leftmargin=1.1em]
|
|
\item \textbf{hanzo-k8s}: Control plane, databases, core services.
|
|
\item \textbf{GPU pool}: 8x A100 GPU nodes for inference workloads, expandable to 32.
|
|
\item \textbf{Edge nodes}: 12 PoPs globally for CDN and edge compute.
|
|
\end{itemize}
|
|
|
|
\subsection{Usage Statistics (14 Months)}
|
|
|
|
\begin{table}[H]
|
|
\centering
|
|
\begin{tabular}{lr}
|
|
\toprule
|
|
\textbf{Metric} & \textbf{Value} \\
|
|
\midrule
|
|
Applications deployed & 2,847 \\
|
|
Total deployments & 41,293 \\
|
|
Active organizations & 891 \\
|
|
Inference requests served & 47.2M \\
|
|
Tokens processed & 18.7B \\
|
|
Total LLM cost facilitated & \$2.1M \\
|
|
Avg. deployment time & 3.4 min \\
|
|
Platform uptime & 99.97\% \\
|
|
Avg. cost savings vs. AWS & 34\% \\
|
|
\bottomrule
|
|
\end{tabular}
|
|
\caption{Production statistics (Dec 2024 -- Feb 2026).}
|
|
\label{tab:prod_stats}
|
|
\end{table}
|
|
|
|
\subsection{Application Distribution}
|
|
|
|
\begin{table}[H]
|
|
\centering
|
|
\small
|
|
\begin{tabular}{lcc}
|
|
\toprule
|
|
\textbf{App Category} & \textbf{Count} & \textbf{Avg. Monthly Cost} \\
|
|
\midrule
|
|
Chat/conversational & 34.2\% & \$127 \\
|
|
RAG/search & 21.7\% & \$234 \\
|
|
API services & 18.3\% & \$89 \\
|
|
Model serving & 12.1\% & \$412 \\
|
|
Data pipelines & 8.4\% & \$187 \\
|
|
Other & 5.3\% & \$156 \\
|
|
\bottomrule
|
|
\end{tabular}
|
|
\caption{Application category distribution in production.}
|
|
\label{tab:app_dist}
|
|
\end{table}
|
|
|