5 papers
Attention to Detail: Evaluating Energy, Performance, and Accuracy Trade-offs Across vLLM Configurations
Nada Zine, Tristan Coignion, Vincenzo Stoico +4
Large Language Models are reshaping how software is developed and maintained. They are typically deployed in production using inference engines such as vLLM, which can efficiently…
Pimp My LLM: Leveraging Variability Modeling to Tune Inference Hyperparameters
Nada Zine, Clément Quinton, Romain Rouvoy
Large Language Models (LLMs) are being increasingly used across a wide range of tasks. However, their substantial computational demands raise concerns about the energy efficiency a…
Imperfect Visual Verification for Code Edition : A Case Study on TikZ
Charly Reux, Mathieu Acher, Djamel Eddine Khelladi +2
LLMs have significantly advanced code generation, enabling the synthesis of functional programs. While recent systems achieve strong performance on many coding benchmarks, tasks in…
LLM Code Customization with Visual Results: A Benchmark on TikZ
Charly Reux, Mathieu Acher, Djamel Eddine Khelladi +2
With the rise of AI-based code generation, customizing existing code out of natural language instructions to modify visual results -such as figures or images -has become possible,…
Green My LLM: Studying the key factors affecting the energy consumption of code assistants
Tristan Coignion, Clément Quinton, Romain Rouvoy
In recent years,Large Language Models (LLMs) have significantly improved in generating high-quality code, enabling their integration into developers' Integrated Development Environ…