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

2024/10/31 by Krishna Teja Chitty-Venkata, Siddhisanket Raskar, Chitty-Venkata, Krishna Teja +15 · 11 citations
Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2411.00136

openalex publication_date 2024/10/31 · openalex created_date 2024/11/14 · openalex updated_date 2026/07/30

Abstract

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.

Cited by

• Viability and Performance of a Private LLM Server for SMBs: A Benchmark Analysis of Qwen3-30B on Consumer-Grade Hardware
• Bench360: Benchmarking Local LLM Inference from 360°
• Understanding Inference Scaling for LLMs: Bottlenecks, Trade-offs, and Performance Principles
• Streaming Tensor Program: A streaming abstraction for dynamic parallelism
• FIRST: Federated Inference Resource Scheduling Toolkit for Scientific AI Model Access
• A Case for Declarative LLM-friendly Interfaces for Improved Efficiency of Computer-Use Agents
• Gyges: Dynamic Cross-Instance Parallelism Transformation for Efficient LLM Inference
• Semantic-Aware Fuzzing: An Empirical Framework for LLM-Guided, Reasoning-Driven Input Mutation
• MoE-Inference-Bench: Performance Evaluation of Mixture of Expert Large Language and Vision Models
• Meta-Metrics and Best Practices for System-Level Inference Performance Benchmarking
• On the Sustainability of AI Inferences in the Edge

Related

• Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective
• A Hardware Evaluation Framework for Large Language Model Inference
• Demystifying AI Platform Design for Distributed Inference of Next-Generation LLM models
• LLM-Pilot: Characterize and Optimize Performance of your LLM Inference Services
• From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference