Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
ELANAgithub.comElana is a lightweight, academic-friendly profiler for analyzing the memory footprint, prefilling latency (TTFT), generation latency (TPOT), and end-to-end latency (TTLT) of large language models on multi-GPU and edge GPU platforms. It provides a simple command-line interface, optional GPU energy consumption logging, and supports models from HuggingFace's AutoModelForCausalLM as well as custom model classes.
Parse Score
Sources
arxiv.org shapes more of what AI says about ELANA than any other source, at 100% of its citations.
