mlsanityData to 14 Oct 2026

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

arXiv 2512.14098 ↗First posted 16 Dec 2025cs.LG cs.DCcited by 4

Not on the map. Why?

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.

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

30 of 42 references.

References · 30

  1. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  2. 2025Qwen2.5-VL Technical Reportcited by 5,587
  3. 2025Qwen3-VL Technical Reportcited by 2,793
  4. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,834
  5. 2023SGLang: Efficient Execution of Structured Language Model Programscited by 1,141
  6. 2025Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scalingcited by 812
  7. 2025Qwen2.5-Omni Technical Reportcited by 736
  8. 2021Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LMcited by 632
  9. 2024DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Servingcited by 617
  10. 2023Splitwise: Efficient generative LLM inference using phase splittingcited by 558
  11. 2025Qwen3-Omni Technical Reportcited by 497
  12. 2024Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generationcited by 457
18 more
  1. 2022DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Modelscited by 379
  2. 2021GSPMD: General and Scalable Parallelization for ML Computation Graphscited by 111
  3. 2024xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelismcited by 56
  4. 2024Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flowcited by 55
  5. 2024Andes: Defining and Enhancing Quality-of-Experience in LLM-Based Text Streaming Servicescited by 45
  6. 2023Oobleck: Resilient Distributed Training of Large Models Using Pipeline Templatescited by 40
  7. 2025ServeGen: Workload Characterization and Generation of Large Language Model Serving in Productioncited by 29
  8. 2025Jenga: Effective Memory Management for Serving LLM with Heterogeneitycited by 25
  9. 2025PrefillOnly: An Inference Engine for Prefill-only Workloads in Large Language Model Applicationscited by 21
  10. 2022Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learningcited by 20
  11. 2025ModServe: Modality- and Stage-Aware Resource Disaggregation for Scalable Multimodal Model Servingcited by 18
  12. 2025WLB-LLM: Workload-Balanced 4D Parallelism for Large Language Model Trainingcited by 17
  13. 2024Efficiently Serving Large Multimodal Models Using EPD Disaggregationcited by 16
  14. 2025Sailor: Automating Distributed Training over Dynamic, Heterogeneous, and Geo-distributed Clusterscited by 13
  15. 2025On Evaluating Performance of LLM Inference Serving Systemscited by 10
  16. 2025DCP: Addressing Input Dynamism In Long-Context Training via Dynamic Context Parallelismcited by 7
  17. 2025Efficient Distributed MLLM Training with Cornstarchcited by 4
  18. 2025TetriServe: Efficiently Serving Mixed DiT Workloadscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026VoxServe: Streaming-Centric Serving System for Speech Language Modelscited by 3
  2. 2026Cornserve: A Distributed Serving System for Any-to-Any Multimodal Modelscited by 1
  3. 2026Cost-Efficient Multimodal LLM Inference via Cross-Tier GPU Heterogeneitycited by 0
  4. 2026The Language-Energy Divide: Measuring Energy Costs of Multilingual LLM Inferencecited by 0