arXiv cs.AI· Tomer Solberg·· 10 小时前AI 评分38
Sable：面向大语言模型位精确推理的小域 Sumcheck 论证系统
Sable: A Small-Field Sumcheck Argument for Bit-Exact Inference of Large Language Models
AI 导读
Sable 是一个论证系统与单 GPU 证明器，可证明已承诺的整数量化 Transformer 对给定提示词逐位生成了指定 token 序列。
正文 · 原文
Abstract:We present Sable, an argument system and single-GPU prover for the statement that a committed, integer-quantized transformer produced a given token sequence from a given prompt, bit for bit. Sable fixes an integer function F_O with no floating-point step, in which every rounding, normalization, softmax and sampling decision is determined by its inputs, and proves it with a constraint system whose relations provably never wrap modulo the 31-bit KoalaBear prime. The proof batches zerochecks and LogUp-GKR lookups into one sumcheck per domain, and commits to every witness tensor and weight in one multilinear commitment built from Reed-Solomon codes, BLAKE3 Merkle trees and a mixed-length BaseFold opening. The prover streams the model layer by layer on one GPU. On one NVIDIA RTX PRO 6000 Blackwell GPU, Sable proves all 64 layers of Qwen2.5-32B in 92.5 s for 4,096 tokens and 398 s for 16,384 tokens, and covers Qwen3-32B and the mixture-of-experts Qwen3-30B-A3B (4,096 tokens in 121.8 and 84.7 s). A proof costs 41 to 50 times the serving time, or 6.4 cents per 4,096-token request at public GPU prices, and 40 to 64 times less time per parameter and token than zkLLM. On WikiText-2, F_O's greedy token matches the BF16 model's at 86.3% of positions; on Qwen3, F_O is within 1.6 points of BF16 on MMLU and 1.7 points on GSM8K. A verifier with a compiled core checks a proof on one CPU core in 19 to 56 s. In the random-oracle model, the interactive proof has round-by-round soundness error 2^-103. The proof is not zero-knowledge, so the system targets open-weight models. Code: this https URL
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2611.14083 [cs.CR] |
| (or arXiv:2611.14083v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2611.14083 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Tomer Solberg PhD [view email]
[v1]
Tue, 10 Nov 2026 13:47:29 UTC (82 KB)
来源：arXiv cs.AI · arxiv.org