EUVIMEDEUVIMED entdecken
Crossref

Generative AI for Performance Engineering: Tailoring Llama-3 for Bottleneck Classification and Optimization Recommendations

A. V. Dovbysh, V. I. Alieksieiev

Mathematical Modeling and Computing · 2026 · 13 (1) · 321-328

DOI: 10.23939/mmc2026.01.321 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematical Modeling and Computing, 2026. Verfasst von A. V. Dovbysh und 1 weiteren Autor:innen. Die Arbeit nennt 13 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents a novel approach to software performance analysis by integrating traditional profiling techniques with a fine-tuned large language model (LLM), based on the Llama-3 model. Addressing the challenges of manual profiling – such as overwhelming data volumes and the high expertise required to interpret performance metrics – the study introduces a lightweight AI-powered profiler trained on structured JSON-based profiling logs and code samples. The model is fine-tuned using parameter-efficient methods (LoRA and QLoRA) to classify performance bottlenecks (e.g., N+1 queries, blocking I/O, recursion) and generate actionable recommendations. The article provides a comprehensive methodology, from dataset preparation and model training to inference and integration, enabling local deployment even without access to high-end GPUs. This fusion of performance engineering and generative AI showcases a scalable, accessible solution for developers, enhancing the speed and precision of bottleneck detection and representing a step toward more automated software optimization.

Zitieren

APA

Dovbysh, A. V., & Alieksieiev, V. I. (2026). Generative AI for Performance Engineering: Tailoring Llama-3 for Bottleneck Classification and Optimization Recommendations. Mathematical Modeling and Computing, 13(1), 321-328. https://doi.org/10.23939/mmc2026.01.321

Vancouver

Dovbysh AV, Alieksieiev VI. Generative AI for Performance Engineering: Tailoring Llama-3 for Bottleneck Classification and Optimization Recommendations. Mathematical Modeling and Computing. 2026;13(1):321-328. doi:10.23939/mmc2026.01.321

BibTeX
@article{Dovbysh2026,
  author = {Dovbysh, A. V. and Alieksieiev, V. I.},
  title = {Generative AI for Performance Engineering: Tailoring Llama-3 for Bottleneck Classification and Optimization Recommendations},
  journal = {Mathematical Modeling and Computing},
  year = {2026},
  volume = {13},
  number = {1},
  pages = {321--328},
  doi = {10.23939/mmc2026.01.321}
}
Kostenlos starten →