Research
Work we publish
Hanzo builds infrastructure that has to hold up under audit, regulation and adversaries. The reasoning behind it is published rather than kept internal.
Papers
Each one links to its page on papers.hanzo.ai, where the PDF and the LaTeX live.
Cloud Economics of a Sovereign OSS StackJun 2026
A Regulated Capital-Markets Migration Case StudyOne Native Stack for Private, Continuously-Learning AIJun 2026
Inference at the Bandwidth Wall, On-Device QLoRA, One EngineNative ROCm Inference on a Consumer RDNA3.5 APUJun 2026
Reaching llama.cpp Decode Parity via a Unified 1-bit-to-Full Quant CoreEdge LLM Inference Across Commodity AcceleratorsJun 2026
Measured AMD, NVIDIA, and Apple PerformanceNative Training in the Hanzo EngineJun 2026
One Engine, One Quant Format, One BackendContinuously-Learning Private AIJun 2026
Self-Improvement and Privacy in the Hanzo Native StackEconomical Serving and the hanzo.ai PlatformJun 2026
A Bandwidth-Optimal Unified Train-and-Serve RuntimeThe Unified Sovereign-Tenant CloudJul 2026
Linear Shared-Nothing Scaling via Per-Tenant SQLite and In-Process CompositionRefutation-Driven Performance EngineeringJul 2026
An Empirical Study of a Multi-Week GPU Kernel CampaignEvolutionary Schedule Search in a One-Source Kernel DSLJul 2026
And the Continual-Improvement Loop It AnchorsHanzo RouterJul 2026
Memory-Aware, Local-First LLM Routing with a Learned SLO-Constrained PolicyHanzo Network WhitepaperOct 2024
L1 Blockchain for Decentralized AI ComputeOpen source
The systems described in these papers are open source. The cloud, the gateway, the agent runtime and the infrastructure around them are developed in the open at github.com/hanzoai, and the platform pays the open-source authors whose work runs on it.