Files

1 line
5.6 KiB
JSON

{"text":["Research","Work we publish","Hanzo builds infrastructure that has to hold up under audit, regulation and adversaries.","Explore papers.hanzo.ai ↗","Specifications (HIPs) ↗","Benchmarks","papers.hanzo.ai","01 / 06","Zen 6: Subquadratic Ultra-Long Context via Hierarchical Latent Sparse Attention","Nov 2026. Distilled & Native Latent Sparse Attention (D-LSA / N-LSA) on 27B Dense Transformers","Kai: Calibrated Discrete Decision Intelligence for Autonomous Agent Loops","Oct 2026. Factorized Discrete Choice, Calibrated Distributions, and Deterministic Policy Governance","Linkage, Not Similarity","Sep 2026. What long-term agent memory has to retrieve, and how it is measured","Hanzo AI Chain (AIVM)","Aug 2026. Useful-Work Mining, the Native AI Coin, and Post-Quantum Omnichain Settlement","Cloud Economics of a Sovereign OSS Stack","Jun 2026. A Regulated Capital-Markets Migration Case Study","One Native Stack for Private, Continuously-Learning AI","Jun 2026. Inference at the Bandwidth Wall, On-Device QLoRA, One Engine","Papers","Each one links to its page on papers.hanzo.ai, where the PDF and the LaTeX live.","Nov 2026","Distilled & Native Latent Sparse Attention (D-LSA / N-LSA) on 27B Dense Transformers","Oct 2026","Factorized Discrete Choice, Calibrated Distributions, and Deterministic Policy Governance","Sep 2026","What long-term agent memory has to retrieve, and how it is measured","Aug 2026","Useful-Work Mining, the Native AI Coin, and Post-Quantum Omnichain Settlement","Jun 2026","A Regulated Capital-Markets Migration Case Study","Inference at the Bandwidth Wall, On-Device QLoRA, One Engine","Native ROCm Inference on a Consumer RDNA3.5 APU","Reaching llama.cpp Decode Parity via a Unified 1-bit-to-Full Quant Core","Edge LLM Inference Across Commodity Accelerators","Measured AMD, NVIDIA, and Apple Performance","Native Training in the Hanzo Engine","One Engine, One Quant Format, One Backend","Continuously-Learning Private AI","Self-Improvement and Privacy in the Hanzo Native Stack","Economical Serving and the hanzo.ai Platform","A Bandwidth-Optimal Unified Train-and-Serve Runtime","The Unified Sovereign-Tenant Cloud","Jul 2026","Linear Shared-Nothing Scaling via Per-Tenant SQLite and In-Process Composition","Refutation-Driven Performance Engineering","An Empirical Study of a Multi-Week GPU Kernel Campaign","Evolutionary Schedule Search in a One-Source Kernel DSL","And the Continual-Improvement Loop It Anchors","Hanzo Router","Memory-Aware, Local-First LLM Routing with a Learned SLO-Constrained Policy","What a Dormant Agent Costs","State, Execution and Isolation Measured Separately at a Fleet of One Million","Hops Do Not Fix Multi-Hop Retrieval","A Negative Result on Long-Horizon Conversational Memory, and What the Failure Actually Is","Retrieval Scoped by Subject","A factorial measurement of conversational memory on LoCoMo, and the negative controls that locate the effect","Hanzo Network Whitepaper","Oct 2024","L1 Blockchain for Decentralized AI Compute","Specifications","HIPs. The index is hips.hanzo.ai. These are the ones the families are written against.","All HIPs","The specification index.","HIP-0000","The architecture framework.","HIP-0510","Enso, the learned router.","HIP-1332","Kai, the decision model.","HIP-0039","Zen model architecture.","HIP-1334","The research runtime.","HIP-1145","How an experiment is recorded.","Standards","The standards the runtime, the gateway, and the benchmark arena are built to.","HIP-0043","The inference engine.","HIP-1211","The model API.","HIP-0004","The gateway.","HIP-0019","Tensor operations.","HIP-1105","The benchmark arena.","Open 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",", and the platform pays the open-source authors whose work runs on it.","github.com/hanzoai","02 / 06","03 / 06","04 / 06","05 / 06","06 / 06"],"links":["https://papers.hanzo.ai","https://hips.hanzo.ai","/benchmarks","https://papers.hanzo.ai/zen6-latent-sparse-attention/","https://papers.hanzo.ai/kai-decision-model/","https://papers.hanzo.ai/hanzo-context-memory/","https://papers.hanzo.ai/hanzo-ai-chain/","https://papers.hanzo.ai/hanzo-cloud-economics/","https://papers.hanzo.ai/hanzo-native-stack-thesis/","https://papers.hanzo.ai/hanzo-rocm-inference/","https://papers.hanzo.ai/hanzo-cross-backend-inference/","https://papers.hanzo.ai/hanzo-native-training/","https://papers.hanzo.ai/hanzo-continuous-learning-privacy/","https://papers.hanzo.ai/hanzo-platform-infra-desktop/","https://papers.hanzo.ai/hanzo-unified-tenant-cloud/","https://papers.hanzo.ai/refutation-driven-perf/","https://papers.hanzo.ai/evolutionary-schedule-search/","https://papers.hanzo.ai/hanzo-router/","https://papers.hanzo.ai/hanzo-dormant-agents/","https://papers.hanzo.ai/hanzo-multi-hop-retrieval/","https://papers.hanzo.ai/locomo-subject-scope/","https://papers.hanzo.ai/network-whitepaper/","https://hips.hanzo.ai/docs/hip-0000-hanzo-ai-architecture-framework","https://hips.hanzo.ai/docs/hip-0510-enso-learned-router","https://hips.hanzo.ai/docs/hip-1332-kai-the-decision-model","https://hips.hanzo.ai/docs/hip-0039-zen-model-architecture","https://hips.hanzo.ai/docs/hip-1334-research-unified-runtime","https://hips.hanzo.ai/docs/hip-1145-research-experiment-record","https://hips.hanzo.ai/docs/hip-0043-llm-inference-engine-standard","https://hips.hanzo.ai/docs/hip-1211-ai-the-model-api","https://hips.hanzo.ai/docs/hip-0004-llm-gateway-unified-ai-provider-interface","https://hips.hanzo.ai/docs/hip-0019-tensor-operations-standard","https://hips.hanzo.ai/docs/hip-1105-benchmark-measurement-arena","https://github.com/hanzoai"]}