Preprint

Fine-tuning LLaMA 2 interference: a comparative study of language implementations for optimal efficiency

Md. Sazzad HossainSeyam, Touhidul AlamDepartment of Computer Science and Engineering , BGC Trust University , Chattogram , BangladeshChowdhury, AvijitDepartment of Mechanical Engineering , Chittagong University of Engineering and Technology , Chattogram , BangladeshMunis XamidovGhose, RajibMilitary Institute of Science and Technology (MIST)Pathak, AbhijitDepartment of Computer Science and Engineering , Sonargaon University , Dhaka , Bangladesh

2025en

Ochiq kirishYashil

Litsenziya: cc-by

ABI

Annotatsiya

This paper presents a comparative study aimed at optimizing Llama2 inference, a critical aspect of machine learning and natural language processing (NLP). We evaluate various programming languages and frameworks, including TensorFlow, PyTorch, Python, Mojo, C++, and Java, analyzing their performance in terms of speed, memory consumption, and ease of implementation through extensive benchmarking. Strengths and limitations of each approach are highlighted, along with proposed optimization strategies for parallel processing and hardware utilization. Furthermore, we investigate the Mojo SDK, a novel framework designed for large language model (LLM) inference on Apple Silicon, benchmarking its performance against implementations in C, C++, Rust, Zig, Go, and Julia. Our experiments, conducted on an Apple M1 Max, demonstrate Mojo SDK's competitive performance, ease of use, and seamless Python compatibility, positioning it as a strong alternative for LLM inference on Apple Silicon. We also discuss broader implications for LLM deployment on resource-constrained hardware and identify potential directions for future research.

Hali tarjima qilinmagan

Identifikatorlar

DOI: 10.48550/arxiv.2502.01651

Iqtiboslar va manbalar

0 ta iqtibos0 ta foydalanilgan manba