mlsanityData to 7 Oct 2026

Comparative Analysis of Large Language Model Inference Serving Systems: A Performance Study of vLLM and HuggingFace TGI

arXiv 2511.17593 ↗First posted 17 Nov 2025cs.LG cs.DC cs.PFcited by 1

On the map: Efficient LLM inference and serving → Serving systems and request scheduling

Abstract (arXiv)

The deployment of Large Language Models (LLMs) in production environments requires efficient inference serving systems that balance throughput, latency, and resource utilization. This paper presents a comprehensive empirical evaluation of two prominent open-source LLM serving frameworks: vLLM and HuggingFace Text Generation Inference (TGI). We benchmark these systems across multiple dimensions including throughput performance, end-to-end latency, GPU memory utilization, and scalability characteristics using LLaMA-2 models ranging from 7B to 70B parameters. Our experiments reveal that vLLM achieves up to 24x higher throughput than TGI under high-concurrency workloads through its novel PagedAttention mechanism, while TGI demonstrates lower tail latencies for interactive single-user scenarios. We provide detailed performance profiles for different deployment scenarios and offer practical recommendations for system selection based on workload characteristics. Our findings indicate that the choice between these frameworks should be guided by specific use-case requirements: vLLM excels in high-throughput batch processing scenarios, while TGI is better suited for latency-sensitive interactive applications with moderate concurrency.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Serving systems and request scheduling, one of 12 directions in Efficient LLM inference and serving. Builds on 8 of its 19 references that are in the map. First posted on arXiv 17 Nov 2025.

Builds on

8 of 19 references.

References · 8

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  4. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  5. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  6. 2023FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPUcited by 567
  7. 2022Efficiently Scaling Transformer Inferencecited by 529
  8. 2022DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scalecited by 403

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026The Illusion of Power Capping in LLM Decode: A Phase-Aware Energy Characterisation Across Attention Architecturescited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024GUIDE: A Global Unified Inference Engine for Deploying Large Language Models in Heterogeneous Environments
  2. 2025ServeGen: Workload Characterization and Generation of Large Language Model Serving in Production
  3. 2024ScaleLLM: A Resource-Frugal LLM Serving Framework by Optimizing End-to-End Efficiency
  4. 2023Efficient LLM Inference on CPUs
  5. 2024Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective
  6. 2025Seesaw: High-throughput LLM Inference via Model Re-sharding
  7. 2024LLM Inference Unveiled: Survey and Roofline Model Insights
  8. 2026From Inference Engine to Inference Control Plane: Connecting vLLM, llm-d, and the Evolution of Efficient Distributed LLM Serving