mlsanityData to 7 Oct 2026

DiLaServe: High SLO Attainment Serving for Diffusion Language Models

arXiv 2606.29094 ↗First posted 27 Jun 2026cs.LGcited by 1

On the map: Diffusion models → Discrete and text diffusion

Abstract (arXiv)

Diffusion language models (DLMs) have recently emerged as a promising alternative to conventional autoregressive language models. By generating multiple tokens in parallel during each denoising step, they offer higher inference throughput while maintaining competitive quality. However, realizing these throughput gains while meeting latency SLOs in a serving system requires addressing challenges introduced by DLMs' unique characteristics. These include navigating the speed-quality tradeoff created by confidence-based denoising, choosing appropriate parallelization levels across model instances under fluctuating load, and coordinating approximate KV caching mechanisms that introduce non-uniform per-step costs. To address these challenges, we present TeDiServe, a cluster-level serving system for DLMs. TeDiServe enables deadline-aware scheduling and adaptive load control through confidence-threshold adjustment, and dynamically reconfigures the cluster by solving a quality-aware optimization problem, while explicitly modeling the step-level heterogeneity introduced by approximate KV caching. Across multiple benchmarks and real-world traces, TeDiServe improves SLO attainment by up to 56.6 percentage points and reduces end-to-end request latency by up to 46% while incurring less than 1% accuracy drop.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Discrete and text diffusion, one of 14 directions in Diffusion models. Builds on 35 of its 60 references that are in the map. First posted on arXiv 27 Jun 2026.

Builds on

35 of 60 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation7 Oct
  2. 2025LLaDA-MoE: A Sparse MoE Diffusion Language Model29 Sep
  3. 2025Dream 7B: Diffusion Large Language Models21 Aug
  4. 2023Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution25 Oct
  5. 2022DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models28 Nov

Other references · 30

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  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. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  6. 2021Program Synthesis with Large Language Modelscited by 3,509
  7. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,758
  8. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
  9. 2024DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Servingcited by 595
  10. 2023Splitwise: Efficient generative LLM inference using phase splittingcited by 536
  11. 2017Ray: A Distributed Framework for Emerging AI Applicationscited by 516
  12. 2025Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decodingcited by 404
18 more
  1. 2023The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"cited by 399
  2. 2025LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Modelscited by 273
  3. 2016Clipper: A Low-Latency Online Prediction Serving Systemcited by 191
  4. 2025dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Cachingcited by 168
  5. 2024Llumnix: Dynamic Scheduling for Large Language Model Servingcited by 167
  6. 2024Learning-to-Cache: Accelerating Diffusion Transformer via Layer Cachingcited by 138
  7. 2025Fast-dLLM v2: Efficient Block-Diffusion LLMcited by 128
  8. 2020Serving DNNs like Clockwork: Performance Predictability from the Bottom Upcited by 119
  9. 2024NanoFlow: Towards Optimal Large Language Model Serving Throughputcited by 85
  10. 2024BurstGPT: A Real-world Workload Dataset to Optimize LLM Serving Systemscited by 84
  11. 2024D'ej`aVu: KV-cache Streaming for Fast, Fault-tolerant Generative LLM Servingcited by 48
  12. 2023AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Servingcited by 31
  13. 2025DeepServe: Serverless Large Language Model Serving at Scalecited by 17
  14. 2023Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Servingcited by 15
  15. 2025MoDM: Efficient Serving for Image Generation via Mixture-of-Diffusion Modelscited by 11
  16. 2025Quake: Adaptive Indexing for Vector Searchcited by 8
  17. 2024DiffServe: Efficiently Serving Text-to-Image Diffusion Models with Query-Aware Model Scalingcited by 4
  18. 2025Eva: Cost-Efficient Cloud-Based Cluster Schedulingcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Serving Masked Diffusion LLMs: Characterization and Design Principles from Real Hardwarecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Accelerating Masked Diffusion Large Language Models: A Survey of Efficient Inference Techniques
  2. 2026Not All Denoising Steps Are Equal: Model Scheduling for Faster Masked Diffusion Language Models
  3. 2026CAI-DLLM: Convergence Aware Inference for Diffusion Language Models
  4. 2025FlashDLM: Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided Diffusion
  5. 2026Denoising Surface: Modeling and Predicting Inference Cost for Diffusion LLM Serving
  6. 2025dInfer: An Efficient Inference Framework for Diffusion Language Models
  7. 2025Esoteric Language Models: A Family of Any-Order Diffusion LLMs
  8. 2025A Survey on Diffusion Language Models