TriCalRAG is a reproducible benchmark for on-premise log-anomaly detection and root-cause analysis, evaluating Qwen2.5-14B and Mistral-Small-22B on vLLM with one NVIDIA RTX PRO 6000 GPU across BGL, HDFS, Thunderbird, and OpenStack. It…

#TriCalRAG #AIOps #RAG #vLLM
https://arxiv.org/abs/2609.14762