投机解码引擎中处理器契约的测试
原标题:Testing Processor Contracts in Speculative Decoding Engines
AI 摘要
论文提出 Badc(分支感知差分一致性测试)方法,用于检验投机解码引擎中 logits processor 是否遵守「处理器-前缀契约」。作者在 5 个固定版本的 Transformers 和 llama-cpp-python 构建上测试了 26 种配置,确认两类缺陷:处理器读取未验证的草稿 token,以及状态推进后不回滚。在一个训练好的 checkpoint 上,普通解码与 prompt-lookup 解码在预定义首 token 事件概率上的差异下界达 60.26 个百分点。
正文节选
marginparsep has been altered. topmargin has been altered. marginparwidth has been altered. marginparpush has been altered. The page layout violates the ICML style. Please do not change the page layout, or include packages like geometry, savetrees, or fullpage, which change it for you. We’re not able to reliably undo arbitrary changes to the style. Please remove the offending package(s), or layout-changing commands and try again. Testing Processor Contracts in Speculative Decoding Engines Tianyu