Impact of LoRA Injection in Attention versus Feed-Forward Networks on Latency-Throughput Trade-offs in Llama-3.2-3B RAG Inference

We study quality-latency-resource trade-offs in a documentation-grounded retrieval-augmented generation (RAG) system that uses Low-Rank Adaptation (LoRA) of the generator. We build a manually verified benchmark of 5,144 question-answer pairs over the official Kubernetes documentation and combine it with a fixed hybrid-retrieval pipeline (BGE-M3 dense, BGE-M3 native sparse, Reciprocal Rank Fusion, cross-encoder reranking). Over this benchmark we ablate 20 LoRA configurations on Llama-3.2-3B-Instruct and Llama-3.1-8B-Instruct across rank and target-module choices, and evaluate each on token-leve

Research goal: What is the impact of injecting LoRA adapters exclusively into attention mechanisms versus feed-forward networks in Llama-3.2-3B on the latency-throughput trade-off during hybrid-retrieval RAG inference?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 7.5/10.