LATIDIA · Investigación

Dios no juega a los dados: imponiendo la invariancia de lotes en la generación de núcleos agénticos

arXiv: 2610.36623v1Announce Type: new Abstract: Large language model (LLM) que atiende dinámicamente las solicitudes de los usuarios por lotes para la ejecución de la GPU, por lo que la misma solicitud puede procesarse junto con diferentes solicitudes en todas las ejecuciones.

La noticia

arXiv:2610.36623v1 Announce Type: new Abstract: Large language model (LLM) serving systems dynamically batch user requests for GPU execution, so the same request may be processed alongside different requests across runs. If the GPU kernels lack batch invariance (BI), this changing batch context can alter the numerical output for an unchanged input, undermining reproducibility. Existing kernel generation agents focus on correctness and efficiency but \emph{overlook BI}. We find 19 confirmed BI violations among 83 batch-applicable released artifacts. To address this limitation, we propose \tool, which combines contract-guided static dependency analysis with dynamic validation of bitwise consistency across batch contexts. \tool is designed as a plug-in component for general kernel agents, allowing