用定点数替代浮点数，让AI系统内存结果跨平台完全一致。
Valori: A Deterministic Memory Substrate for AI Systems
- 用Q16.16定点数替代浮点数，确保内存操作确定性。
- 在x86与ARM架构上实现比特级一致的内存状态和检索结果。
- 适合需要可复现、可审计的可信AI系统部署场景。
现代AI系统依赖浮点数存储和搜索向量嵌入，虽适用于近似相似性检索，但引入了根本性的非确定性：相同模型、输入和代码在不同硬件（如x86与ARM）上可能产生不同的内存状态和检索结果。这导致无法复现，阻碍安全部署，引发无声数据偏差，影响受监管领域的后验验证与审计追踪。本文提出Valori，一种确定性AI内存底座，将浮点内存操作替换为定点数运算（Q16.16），并把内存建模为可回放的状态机。Valori确保跨平台比特级一致的内存状态、快照与搜索结果。我们证明非确定性出现在索引或检索之前，并展示如何在内存边界强制确定性。结果表明，确定性内存是可信AI系统的必要基础。参考实现已开源，地址：https://github.com/varshith-Git/Valori-Kernel（存档于https://zenodo.org/records/18022660）。
原文摘要 · Abstract (English)
Modern AI systems rely on vector embeddings stored and searched using floating-point arithmetic. While effective for approximate similarity search, this design introduces fundamental non-determinism: identical models, inputs, and code can produce different memory states and retrieval results across hardware architectures (e.g., x86 vs. ARM). This prevents replayability and safe deployment, leading to silent data divergence that prevents post-hoc verification and compromises audit trails in regulated sectors. We present Valori, a deterministic AI memory substrate that replaces floating-point memory operations with fixed-point arithmetic (Q16.16) and models memory as a replayable state machine. Valori guarantees bit-identical memory states, snapshots, and search results across platforms. We demonstrate that non-determinism arises before indexing or retrieval and show how Valori enforces determinism at the memory boundary. Our results suggest that deterministic memory is a necessary primitive for trustworthy AI systems. The reference implementation is open-source and available at https://github.com/varshith-Git/Valori-Kernel (archived at https://zenodo.org/records/18022660).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。