29516

LLM-Inference-Bench: Inference Benchmarking of Large Language Models on AI Accelerators

Krishna Teja Chitty-Venkata, Siddhisanket Raskar, Bharat Kale, Farah Ferdaus, Aditya Tanikanti, Ken Raffenetti, Valerie Taylor, Murali Emani, Venkatram Vishwanath
Argonne National Laboratory
arXiv:2411.00136 [cs.LG], (31 Oct 2024)

@misc{chittyvenkata2024llminferencebenchinferencebenchmarkinglarge,

   title={LLM-Inference-Bench: Inference Benchmarking of Large Language Models on AI Accelerators},

   author={Krishna Teja Chitty-Venkata and Siddhisanket Raskar and Bharat Kale and Farah Ferdaus and Aditya Tanikanti and Ken Raffenetti and Valerie Taylor and Murali Emani and Venkatram Vishwanath},

   year={2024},

   eprint={2411.00136},

   archivePrefix={arXiv},

   primaryClass={cs.LG},

   url={https://arxiv.org/abs/2411.00136}

}

Download Download (PDF)   View View   Source Source   Source codes Source codes

389

views

Large Language Models (LLMs) have propelled groundbreaking advancements across several domains and are commonly used for text generation applications. However, the computational demands of these complex models pose significant challenges, requiring efficient hardware acceleration. Benchmarking the performance of LLMs across diverse hardware platforms is crucial to understanding their scalability and throughput characteristics. We introduce LLM-Inference-Bench, a comprehensive benchmarking suite to evaluate the hardware inference performance of LLMs. We thoroughly analyze diverse hardware platforms, including GPUs from Nvidia and AMD and specialized AI accelerators, Intel Habana and SambaNova. Our evaluation includes several LLM inference frameworks and models from LLaMA, Mistral, and Qwen families with 7B and 70B parameters. Our benchmarking results reveal the strengths and limitations of various models, hardware platforms, and inference frameworks. We provide an interactive dashboard to help identify configurations for optimal performance for a given hardware platform.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: