RGSQ: Riemannian Geometry-Sensitive Quantization for Large Vision-Language Models

T1Covered by 1 source · first reported by arXiv at 24 Sept, 04:00 UTC

arXiv:2609.25492v1 Announce Type: cross Abstract: Large vision-language models (VLMs) can be efficiently deployed under stringent memory and latency constraints through post training quantization (PTQ). However, most PTQ methods are designed for unimodal large language models (LLMs). These methods…

aiscience

Sources

• T1RGSQ: Riemannian Geometry-Sensitive Quantization for Large Vision-Language ModelsarXiv24 Sept, 04:00