Metraipolis › archive › dc_f26ecffbe497

Benchmarking LLM Serving Systems for Agentic AI Workloads with XPerf — arXiv:2608.20370

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.20370
License (as archived): CC0-1.0
Archived: 2026-10-18T10:22:10.389Z
SHA-256 of the archived text: 90711a6b7cae4872b8cfb8dfd81728feb4fafdad10b4103e83e016e1ff47f19c
Stable URL of this page: https://metraipolis.com/documento/dc_f26ecffbe497

How to cite

Benchmarking LLM Serving Systems for Agentic AI Workloads with XPerf — arXiv:2608.20370 — arXiv (en), https://arxiv.org/abs/2608.20370 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f26ecffbe497 (Metraipolis archive dc_f26ecffbe497, sha256 90711a6b7cae4872b8cfb8dfd81728feb4fafdad10b4103e83e016e1ff47f19c)

BibTeX

@misc{dcf26ecffbe497,
  title = {Benchmarking LLM Serving Systems for Agentic AI Workloads with XPerf — arXiv:2608.20370},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.20370},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f26ecffbe497; sha256 90711a6b7cae4872b8cfb8dfd81728feb4fafdad10b4103e83e016e1ff47f19c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20370. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present XPerf, a benchmarking framework that load-tests LLM serving systems with diverse agentic AI workloads. It provides detailed profiling of the serving system and hardware, enabling users to identify performance bottlenecks introduced by agentic workloads. Benchmarking LLM serving systems under agentic workloads is challenging - agentic applications rely on nondeterministic LLM outputs to guide their control flow; therefore, workload patterns vary unpredictably from run to run. XPerf minimizes this workload variation with a fine-grained trace replay approach: it enables users to easily collect traces from real agentic applications, synthesize new workloads with various patterns if needed, and reproducibly replay them on different LLM serving systems. XPerf includes eight agentic applications across diverse use cases (e.g., coding, deep research, and Q&A) by default. Our empirical study using these workloads shows that XPerf accurately replays agentic workloads, provides detailed performance breakdowns, scales to larger serving systems, and assists in serving system debugging. We will open-source XPerf on GitHub.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-24 in cs.DC).
Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC) ; Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2608.20370 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T10:18:05.590Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).