VectorLiteRAG: Latency-Aware and Fine-Grained Resource Partitioning for Efficient RAG
Abstract
This package contains artifacts from the paper “VectorLiteRAG: Latency-Aware and Fine-Grained Resource Partitioning for Efficient RAG,” published at HPCA 2026. It includes a Python-based runtime system and a C++ submodule implementing a modified FAISS library. In addition, the package provides scripts for building indexes, running end-to-end evaluations and generating figures (plots) reported in the paper.
Fields of Study & Subjects
Parallel Computing and Optimization Techniques
Advanced Database Systems and Queries
Topic Modeling
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 9 January 2026