mlsanityData to 7 Oct 2026

dInfer: An Efficient Inference Framework for Diffusion Language Models

arXiv 2510.08666 ↗First posted 9 Oct 2025cs.CL cs.AIcited by 33

On the map: Diffusion models → Discrete and text diffusion

Abstract (arXiv)

Diffusion-based large language models (dLLMs) have emerged as a promising alternative to autoregressive (AR) LLMs, leveraging denoising-based generation to enable inherent parallelism. Even more and more open-sourced dLLM models emerge, yet their widespread adoption remains constrained by the lack of a standardized and efficient inference framework. We present dInfer, an efficient and extensible framework for dLLM inference. dInfer decomposes the inference pipeline into four modular components--model, diffusion iteration manager, decoding strategy, and KV-cache manager--and integrates novel algorithms for each component alongside system-level optimizations. Through this combination of algorithmic innovations and system enhancements, dInfer achieves substantial efficiency gains without compromising output quality on LLaDA-MoE. At batch size 1, it surpasses 1,100 tokens per second on HumanEval and averages over 800 tokens per second across six benchmarks on 8× H800 GPUs. Compared to prior systems, dInfer delivers a 10× speedup over Fast-dLLM while maintaining similar model performance. Even compared to the AR model (with a comparable number of activation parameters and performance) QWen2.5-3B, which is highly optimized with the latest vLLM inference engine, dInfer still delivers a 2-3× speedup. The implementation of dInfer is open-sourced at https://github.com/inclusionAI/dInfer.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Placed in Discrete and text diffusion, one of 14 directions in Diffusion models. Builds on 11 of its 11 references that are in the map. First posted on arXiv 9 Oct 2025.

Builds on

11 of 11 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference4 Aug
  2. 2025Large Language Diffusion Models14 Feb

Other references · 9

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  4. 2024Qwen2.5 Technical Reportcited by 4,713
  5. 2021Program Synthesis with Large Language Modelscited by 3,509
  6. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 1,906
  7. 2023Instruction-Following Evaluation for Large Language Modelscited by 1,143
  8. 2025Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decodingcited by 404
  9. 2024CRUXEval: A Benchmark for Code Reasoning, Understanding and Executioncited by 294

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 9; 2026: 24.

33 papers.

Sort:

By area:

  1. 2025LLaDA2.0: Scaling Up Diffusion Language Models to 100Bcited by 154
  2. 2026LLaDA2.1: Speeding Up Text Diffusion via Token Editingcited by 48
  3. 2025WeDLM: Reconciling Diffusion Language Models with Standard Causal Attention for Fast Inferencecited by 38
  4. 2026d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillationcited by 34
  5. 2025Learning Unmasking Policies for Diffusion Language Modelscited by 29
  6. 2025Diffusion LLM with Native Variable Generation Lengths: Let [EOS] Lead the Waycited by 22
  7. 2025CDLM: Consistency Diffusion Language Models For Faster Samplingcited by 20
  8. 2025Soft-Masked Diffusion Language Modelscited by 15
  9. 2026Stable-DiffCoder: Pushing the Frontier of Code Diffusion Large Language Modelcited by 12
  10. 2025How Efficient Are Diffusion Language Models? A Critical Examination of Efficiency Evaluation Practicescited by 10
  11. 2025DEER: Draft with Diffusion, Verify with Autoregressive Modelscited by 9
  12. 2026TEAM: Temporal-Spatial Consistency Guided Expert Activation for MoE Diffusion Language Model Accelerationcited by 8
21 more
  1. 2026Streaming-dLLM: Accelerating Diffusion LLMs via Suffix Pruning and Dynamic Decodingcited by 6
  2. 2026Dynamic Expert Sharing: Decoupling Memory from Parallelism in Mixture-of-Experts Diffusion LLMscited by 4
  3. 2026NPU Design for Diffusion Language Model Inferencecited by 3
  4. 2026Swordsman: Entropy-Driven Adaptive Block Partition for Efficient Diffusion Language Modelscited by 3
  5. 2025Reasoning in Diffusion Large Language Models is Concentrated in Dynamic Confusion Zonescited by 2
  6. 2026Mosaic: Unlocking Long-Context Inference for Diffusion LLMs via Global Memory Planning and Dynamic Peak Tamingcited by 2
  7. 2026TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offloadcited by 2
  8. 2026Not All Denoising Steps Are Equal: Model Scheduling for Faster Masked Diffusion Language Modelscited by 1
  9. 2026Remask, Don't Replace: Token-to-Mask Refinement in Diffusion Language Modelscited by 1
  10. 2026Layer Collapse in Diffusion Language Modelscited by 1
  11. 2026Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Modelscited by 1
  12. 2026Efficient Diffusion LLMs via Temporal-Spatial Parallel Decoding and Confidence Extrapolationcited by 1
  13. 2026Accelerating Masked Diffusion Large Language Models: A Survey of Efficient Inference Techniquescited by 1
  14. 2026Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Modelscited by 0
  15. 2026PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decodingcited by 0
  16. 2026Serving Masked Diffusion LLMs: Characterization and Design Principles from Real Hardwarecited by 0
  17. 2026Affix Cache for Diffusion Large Language Modelscited by 0
  18. 2026Dynin-Robotics: Omnimodal Unified Diffusion Vision-Language-Action Modelcited by 0
  19. 2026Early-Bird Decoding: Accelerating Diffusion LLMs with Learnable Block Sizes and Parallel Samplingcited by 0
  20. 2026OLED-MoE: Accelerating MoE-Based dLLM Inference via Inter-Iteration Locality-Aware Expert Offloadingcited by 0
  21. 2026Denoising Surface: Modeling and Predicting Inference Cost for Diffusion LLM Servingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026ES-dLLM: Efficient Inference for Diffusion Large Language Models by Early-Skipping
  2. 2026CAI-DLLM: Convergence Aware Inference for Diffusion Language Models
  3. 2025A Survey on Diffusion Language Models
  4. 2025FlashDLM: Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided Diffusion
  5. 2026Diffusion Language Models: An Experimental Analysis
  6. 2025Esoteric Language Models: A Family of Any-Order Diffusion LLMs
  7. 2025Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing
  8. 2026Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLM