# dInfer: An Efficient Inference Framework for Diffusion Language Models

arXiv: https://arxiv.org/abs/2510.08666 · HTML: https://mlsanity.com/paper/2510.08666/

## Key facts

- Cited by 37 papers in the map (data through 14 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.

## Placed in

- Diffusion models / [Discrete and text diffusion](https://mlsanity.com/diffusion/discrete-and-text-diffusion/)

## Builds on (most cited first, 11 of 11)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [Large Language Diffusion Models](https://mlsanity.com/paper/2502.09992/) (2025)
- [Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding](https://mlsanity.com/paper/2505.22618/) (2025)
- [CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution](https://mlsanity.com/paper/2401.03065/) (2024)
- [Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference](https://mlsanity.com/paper/2508.02193/) (2025)

## Built on by (most cited first, 30 of 37)

- [LLaDA2.0: Scaling Up Diffusion Language Models to 100B](https://mlsanity.com/paper/2512.15745/) (2025)
- [LLaDA2.1: Speeding Up Text Diffusion via Token Editing](https://mlsanity.com/paper/2602.08676/) (2026)
- [WeDLM: Reconciling Diffusion Language Models with Standard Causal Attention for Fast Inference](https://mlsanity.com/paper/2512.22737/) (2025)
- [d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation](https://mlsanity.com/paper/2601.07568/) (2026)
- [Learning Unmasking Policies for Diffusion Language Models](https://mlsanity.com/paper/2512.09106/) (2025)
- [Diffusion LLM with Native Variable Generation Lengths: Let [EOS] Lead the Way](https://mlsanity.com/paper/2510.24605/) (2025)
- [CDLM: Consistency Diffusion Language Models For Faster Sampling](https://mlsanity.com/paper/2511.19269/) (2025)
- [Soft-Masked Diffusion Language Models](https://mlsanity.com/paper/2510.17206/) (2025)
- [Stable-DiffCoder: Pushing the Frontier of Code Diffusion Large Language Model](https://mlsanity.com/paper/2601.15892/) (2026)
- [How Efficient Are Diffusion Language Models? A Critical Examination of Efficiency Evaluation Practices](https://mlsanity.com/paper/2510.18480/) (2025)
- [DEER: Draft with Diffusion, Verify with Autoregressive Models](https://mlsanity.com/paper/2512.15176/) (2025)
- [TEAM: Temporal-Spatial Consistency Guided Expert Activation for MoE Diffusion Language Model Acceleration](https://mlsanity.com/paper/2602.08404/) (2026)
- [Streaming-dLLM: Accelerating Diffusion LLMs via Suffix Pruning and Dynamic Decoding](https://mlsanity.com/paper/2601.17917/) (2026)
- [Dynamic Expert Sharing: Decoupling Memory from Parallelism in Mixture-of-Experts Diffusion LLMs](https://mlsanity.com/paper/2602.00879/) (2026)
- [AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters](https://mlsanity.com/paper/2607.19223/) (2026)
- [Reasoning in Diffusion Large Language Models is Concentrated in Dynamic Confusion Zones](https://mlsanity.com/paper/2511.15208/) (2025)
- [NPU Design for Diffusion Language Model Inference](https://mlsanity.com/paper/2601.20706/) (2026)
- [Swordsman: Entropy-Driven Adaptive Block Partition for Efficient Diffusion Language Models](https://mlsanity.com/paper/2602.04399/) (2026)
- [Mosaic: Unlocking Long-Context Inference for Diffusion LLMs via Global Memory Planning and Dynamic Peak Taming](https://mlsanity.com/paper/2601.06562/) (2026)
- [Layer Collapse in Diffusion Language Models](https://mlsanity.com/paper/2605.06366/) (2026)
- [TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload](https://mlsanity.com/paper/2605.20179/) (2026)
- [Not All Denoising Steps Are Equal: Model Scheduling for Faster Masked Diffusion Language Models](https://mlsanity.com/paper/2604.02340/) (2026)
- [Remask, Don't Replace: Token-to-Mask Refinement in Diffusion Language Models](https://mlsanity.com/paper/2604.18738/) (2026)
- [Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models](https://mlsanity.com/paper/2605.11854/) (2026)
- [PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding](https://mlsanity.com/paper/2605.15609/) (2026)
- [Efficient Diffusion LLMs via Temporal-Spatial Parallel Decoding and Confidence Extrapolation](https://mlsanity.com/paper/2605.30753/) (2026)
- [Accelerating Masked Diffusion Large Language Models: A Survey of Efficient Inference Techniques](https://mlsanity.com/paper/2607.12829/) (2026)
- [Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models](https://mlsanity.com/paper/2605.11726/) (2026)
- [Serving Masked Diffusion LLMs: Characterization and Design Principles from Real Hardware](https://mlsanity.com/paper/2608.23807/) (2026)
- [Affix Cache for Diffusion Large Language Models](https://mlsanity.com/paper/2608.26140/) (2026)

## 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.