# Cornfigurator: Automated Planning for Any-to-Any Multimodal Model Serving

arXiv: https://arxiv.org/abs/2512.14098 · HTML: https://mlsanity.com/paper/2512.14098/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 42 references that are in the map.
- First posted on arXiv 16 Dec 2025.

## Builds on (most cited first, 30 of 30)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling](https://mlsanity.com/paper/2501.17811/) (2025)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM](https://mlsanity.com/paper/2104.04473/) (2021)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation](https://mlsanity.com/paper/2410.13848/) (2024)
- [DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models](https://mlsanity.com/paper/2210.14896/) (2022)
- [GSPMD: General and Scalable Parallelization for ML Computation Graphs](https://mlsanity.com/paper/2105.04663/) (2021)
- [xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism](https://mlsanity.com/paper/2411.01738/) (2024)
- [Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow](https://mlsanity.com/paper/2406.01566/) (2024)
- [Andes: Defining and Enhancing Quality-of-Experience in LLM-Based Text Streaming Services](https://mlsanity.com/paper/2404.16283/) (2024)
- [Oobleck: Resilient Distributed Training of Large Models Using Pipeline Templates](https://mlsanity.com/paper/2309.08125/) (2023)
- [ServeGen: Workload Characterization and Generation of Large Language Model Serving in Production](https://mlsanity.com/paper/2505.09999/) (2025)
- [Jenga: Effective Memory Management for Serving LLM with Heterogeneity](https://mlsanity.com/paper/2503.18292/) (2025)
- [PrefillOnly: An Inference Engine for Prefill-only Workloads in Large Language Model Applications](https://mlsanity.com/paper/2505.07203/) (2025)
- [Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning](https://mlsanity.com/paper/2201.12023/) (2022)
- [ModServe: Modality- and Stage-Aware Resource Disaggregation for Scalable Multimodal Model Serving](https://mlsanity.com/paper/2502.00937/) (2025)
- [WLB-LLM: Workload-Balanced 4D Parallelism for Large Language Model Training](https://mlsanity.com/paper/2503.17924/) (2025)
- [Efficiently Serving Large Multimodal Models Using EPD Disaggregation](https://mlsanity.com/paper/2501.05460/) (2024)
- [Sailor: Automating Distributed Training over Dynamic, Heterogeneous, and Geo-distributed Clusters](https://mlsanity.com/paper/2504.17096/) (2025)
- [On Evaluating Performance of LLM Inference Serving Systems](https://mlsanity.com/paper/2507.09019/) (2025)
- [DCP: Addressing Input Dynamism In Long-Context Training via Dynamic Context Parallelism](https://mlsanity.com/paper/2510.10620/) (2025)
- [Efficient Distributed MLLM Training with Cornstarch](https://mlsanity.com/paper/2503.11367/) (2025)
- [TetriServe: Efficiently Serving Mixed DiT Workloads](https://mlsanity.com/paper/2510.01565/) (2025)

## Built on by (most cited first, 4 of 4)

- [VoxServe: Streaming-Centric Serving System for Speech Language Models](https://mlsanity.com/paper/2602.00269/) (2026)
- [Cornserve: A Distributed Serving System for Any-to-Any Multimodal Models](https://mlsanity.com/paper/2603.12118/) (2026)
- [Cost-Efficient Multimodal LLM Inference via Cross-Tier GPU Heterogeneity](https://mlsanity.com/paper/2603.12707/) (2026)
- [The Language-Energy Divide: Measuring Energy Costs of Multilingual LLM Inference](https://mlsanity.com/paper/2606.21869/) (2026)

## Abstract (arXiv)

Any-to-Any models are an emerging class of multimodal models that accept combinations of text and multimodal data as input and generate them as output, introducing heterogeneous computation paths and component scaling characteristics. There are existing mechanisms for deploying Any-to-Any models--or special cases of them--for inference serving, but they either require manual effort and expertise to tune, or do not generalize to generic Any-to-Any models. We present Cornfigurator, the first deployment planner for generic Any-to-Any model inference serving. The goal of Cornfigurator is to maximize the overall goodput of serving the model, defined as the throughput of requests meeting their latency targets. To do so, based on model and workload characteristics, Cornfigurator explores the full spectrum of deployment strategies, from colocation to disaggregation and mixing different strategies. Cornfigurator performs coarse-to-fine statistical evaluation to efficiently navigate the large space of candidate plans. Plans generated by Cornfigurator either match or deliver 1.12×-6.32× higher goodput compared to existing systems and expert-tuned deployment plans.