A Compute Center Anyone Can Join: A Peer-to-Peer System for AI Inference
cs.AI, cs.CR, cs.DC, cs.GT
Submitted: 2026-11-01
Updated: 2026-11-01
Terminology
Sources
- Non-Determinism of "Deterministic" LLM Settings
- A Taxonomy for Blockchain-based Decentralized Physical Infrastructure Networks (DePIN)
- Petals: Collaborative Inference and Fine-tuning of Large Models
- Distributed Inference and Fine-tuning of Large Language Models Over The Internet
- Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs
- opML: Optimistic Machine Learning on Blockchain
- DiLoCo: Distributed Low-Communication Training of Language Models
- INTELLECT-1 Technical Report
- HexGen: Generative Inference of Large Language Model over Heterogeneous Environment
- DiFR: Inference Verification Despite Nondeterminism
- Efficient Memory Management for Large Language Model Serving with PagedAttention
- Decentralized Physical Infrastructure Network (DePIN): Challenges and Opportunities
- TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference
- BitTensor: A Peer-to-Peer Intelligence Market
- Repeated-Game Security for Restaking-Based Verifiable Inference
- FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU
- PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU
- zkLLM: Zero Knowledge Proofs for Large Language Models
- A scalable verification solution for blockchains
- Parallax: Efficient LLM Inference Service over Decentralized Environment
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents