Valori:一种用于人工智能系统的确定性内存基质
Valori: A Deterministic Memory Substrate for AI Systems
AI总结:
Valori通过使用固定点算术和可重放状态机,为人工智能系统提供确定性内存解决方案,解决浮点运算导致的非确定性问题。
摘要:
现代人工智能系统依赖于使用浮点运算存储和搜索向量嵌入。虽然在近似相似性搜索中有效,但这种设计引入了根本的非确定性:相同模型、输入和代码在不同硬件架构(如x86与ARM)上会产生不同的内存状态和检索结果。这阻止了可重放性和安全部署,导致无声的数据分歧,阻碍了事后验证,并在受监管领域破坏了审计追踪。我们提出了Valori,一种确定性的人工智能内存基质,用固定点算术(Q16.16)取代浮点内存操作,并将内存建模为可重放的状态机。Valori保证在不同平台上内存状态、快照和搜索结果的位级一致性。我们证明非确定性在索引或检索之前就已经出现,并展示了Valori如何在内存边界强制确定性。我们的结果表明,确定性内存是可信人工智能系统必不可少的原始构件。参考实现是开源的,并可在https://github.com/varshith-Git/Valori-Kernel(存档于https://zenodo.org/records/18022660)获得。
英文摘要:
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).
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。