@inproceedings{yang-etal-2026-opendc,
title = "{O}pen{DC}-Infer-{LC}: Benchmarking Production-Valid Long-Context and {RAG} {LLM} Serving",
author = "Yang, Yue and
Twelftree, Maxwell and
Collette, Jared and
He, An-Chi and
Borgnolo, Luke and
Lemphers, David",
editor = "Atanasova, Pepa and
Haffari, Gholamreza and
Wang, Minghan",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-industry.64/",
pages = "1070--1090",
ISBN = "979-8-89176-460-6",
abstract = "Long-context and RAG workloads expose production bottlenecks that raw tokens/s and offline accuracy do not capture, including prefill cost, KV-cache pressure, prefix reuse, routing, and latency SLOs. We introduce OpenDC-Infer-LC, a hardware- and backend-neutral benchmark for evaluating complete data-center LLM serving stacks under long-context and retrieved-context workloads. The benchmark ranks systems by SLO-qualified, quality-preserving goodput: valid output-token throughput at the highest load satisfying p95 TTFT, p95 TPOT, p95 end-to-end latency, and success-rate targets. Because RAG and LongBench quality depends on model ability, retrieval difficulty, and task difficulty, OpenDC-Infer-LC uses a relative quality guardrail against a low-load reference run for the same model and workload, while reporting absolute quality separately. Pilot results on AMD MI355X and NVIDIA B200 show that deployable capacity depends strongly on backend scheduling, cache reuse, context length, routing, quantization, and runtime maturity."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2026-opendc">
<titleInfo>
<title>OpenDC-Infer-LC: Benchmarking Production-Valid Long-Context and RAG LLM Serving</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maxwell</namePart>
<namePart type="family">Twelftree</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jared</namePart>
<namePart type="family">Collette</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">An-Chi</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Borgnolo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Lemphers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pepa</namePart>
<namePart type="family">Atanasova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-460-6</identifier>
</relatedItem>
<abstract>Long-context and RAG workloads expose production bottlenecks that raw tokens/s and offline accuracy do not capture, including prefill cost, KV-cache pressure, prefix reuse, routing, and latency SLOs. We introduce OpenDC-Infer-LC, a hardware- and backend-neutral benchmark for evaluating complete data-center LLM serving stacks under long-context and retrieved-context workloads. The benchmark ranks systems by SLO-qualified, quality-preserving goodput: valid output-token throughput at the highest load satisfying p95 TTFT, p95 TPOT, p95 end-to-end latency, and success-rate targets. Because RAG and LongBench quality depends on model ability, retrieval difficulty, and task difficulty, OpenDC-Infer-LC uses a relative quality guardrail against a low-load reference run for the same model and workload, while reporting absolute quality separately. Pilot results on AMD MI355X and NVIDIA B200 show that deployable capacity depends strongly on backend scheduling, cache reuse, context length, routing, quantization, and runtime maturity.</abstract>
<identifier type="citekey">yang-etal-2026-opendc</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.64/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1070</start>
<end>1090</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OpenDC-Infer-LC: Benchmarking Production-Valid Long-Context and RAG LLM Serving
%A Yang, Yue
%A Twelftree, Maxwell
%A Collette, Jared
%A He, An-Chi
%A Borgnolo, Luke
%A Lemphers, David
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F yang-etal-2026-opendc
%X Long-context and RAG workloads expose production bottlenecks that raw tokens/s and offline accuracy do not capture, including prefill cost, KV-cache pressure, prefix reuse, routing, and latency SLOs. We introduce OpenDC-Infer-LC, a hardware- and backend-neutral benchmark for evaluating complete data-center LLM serving stacks under long-context and retrieved-context workloads. The benchmark ranks systems by SLO-qualified, quality-preserving goodput: valid output-token throughput at the highest load satisfying p95 TTFT, p95 TPOT, p95 end-to-end latency, and success-rate targets. Because RAG and LongBench quality depends on model ability, retrieval difficulty, and task difficulty, OpenDC-Infer-LC uses a relative quality guardrail against a low-load reference run for the same model and workload, while reporting absolute quality separately. Pilot results on AMD MI355X and NVIDIA B200 show that deployable capacity depends strongly on backend scheduling, cache reuse, context length, routing, quantization, and runtime maturity.
%U https://aclanthology.org/2026.emnlp-industry.64/
%P 1070-1090
Markdown (Informal)
[OpenDC-Infer-LC: Benchmarking Production-Valid Long-Context and RAG LLM Serving](https://aclanthology.org/2026.emnlp-industry.64/) (Yang et al., EMNLP 2026)
ACL