# d2Cache: Accelerating Diffusion-Based LLMs via Dual Adaptive Caching

arXiv: https://arxiv.org/abs/2509.23094 · HTML: https://mlsanity.com/paper/2509.23094/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion LLM and MoE inference, one of 12 directions in Efficient LLM inference and serving.
- Builds on 32 of its 35 references that are in the map.
- First posted on arXiv 27 Sep 2025.

## Placed in

- Efficient LLM inference and serving / [Diffusion LLM and MoE inference](https://mlsanity.com/inference/diffusion-llm-and-moe-inference/)

## Builds on (most cited first, 30 of 32)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [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)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [Diffusion Models: A Comprehensive Survey of Methods and Applications](https://mlsanity.com/paper/2209.00796/) (2022)
- [Large Language Diffusion Models](https://mlsanity.com/paper/2502.09992/) (2025)
- [Simple and Effective Masked Diffusion Language Models](https://mlsanity.com/paper/2406.07524/) (2024)
- [Quantifying Attention Flow in Transformers](https://mlsanity.com/paper/2005.00928/) (2020)
- [Simplified and Generalized Masked Diffusion for Discrete Data](https://mlsanity.com/paper/2406.04329/) (2024)
- [Dream 7B: Diffusion Large Language Models](https://mlsanity.com/paper/2508.15487/) (2025)
- [PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling](https://mlsanity.com/paper/2406.02069/) (2024)
- [Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding](https://mlsanity.com/paper/2505.22618/) (2025)
- [Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models](https://mlsanity.com/paper/2503.09573/) (2025)
- [The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"](https://mlsanity.com/paper/2309.12288/) (2023)
- [Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference](https://mlsanity.com/paper/2407.11550/) (2024)
- [Scaling up Masked Diffusion Models on Text](https://mlsanity.com/paper/2410.18514/) (2024)
- [dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching](https://mlsanity.com/paper/2506.06295/) (2025)
- [dKV-Cache: The Cache for Diffusion Language Models](https://mlsanity.com/paper/2505.15781/) (2025)
- [A Survey on Large Language Model Acceleration based on KV Cache Management](https://mlsanity.com/paper/2412.19442/) (2024)
- [A Survey on Diffusion Language Models](https://mlsanity.com/paper/2508.10875/) (2025)
- [FlashDLM: Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided Diffusion](https://mlsanity.com/paper/2505.21467/) (2025)
- [Diffusion Language Models Know the Answer Before Decoding](https://mlsanity.com/paper/2508.19982/) (2025)
- [Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction](https://mlsanity.com/paper/2504.15266/) (2025)
- [Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Masking](https://mlsanity.com/paper/2505.20199/) (2025)

## Built on by (most cited first, 25 of 25)

- [Learning Unmasking Policies for Diffusion Language Models](https://mlsanity.com/paper/2512.09106/) (2025)
- [Encoder-Decoder Diffusion Language Models for Efficient Training and Inference](https://mlsanity.com/paper/2510.22852/) (2025)
- [Diffusion LLM with Native Variable Generation Lengths: Let [EOS] Lead the Way](https://mlsanity.com/paper/2510.24605/) (2025)
- [Fast-Decoding Diffusion Language Models via Progress-Aware Confidence Schedules](https://mlsanity.com/paper/2512.02892/) (2025)
- [TEAM: Temporal-Spatial Consistency Guided Expert Activation for MoE Diffusion Language Model Acceleration](https://mlsanity.com/paper/2602.08404/) (2026)
- [Orchestrating Dual-Boundaries: An Arithmetic Intensity Inspired Acceleration Framework for Diffusion Language Models](https://mlsanity.com/paper/2511.21759/) (2025)
- [FOCUS: DLLMs Know How to Tame Their Compute Bound](https://mlsanity.com/paper/2601.23278/) (2026)
- [DyLLM: Efficient Diffusion LLM Inference via Saliency-based Token Selection and Partial Attention](https://mlsanity.com/paper/2603.08026/) (2026)
- [EntropyCache: Decoded Token Entropy Guided KV Caching for Diffusion Language Models](https://mlsanity.com/paper/2603.18489/) (2026)
- [MM-CondChain: A Programmatically Verified Benchmark for Visually Grounded Deep Compositional Reasoning](https://mlsanity.com/paper/2603.12266/) (2026)
- [TAD: Temporal-Aware Trajectory Self-Distillation for Fast and Accurate Diffusion LLM](https://mlsanity.com/paper/2605.09536/) (2026)
- [Reversible Diffusion Decoding for Diffusion Language Models](https://mlsanity.com/paper/2602.00150/) (2026)
- [SPA-Cache: Singular Proxies for Adaptive Caching in Diffusion Language Models](https://mlsanity.com/paper/2602.02544/) (2026)
- [DepCap: Adaptive Block-Wise Parallel Decoding for Efficient Diffusion LM Inference](https://mlsanity.com/paper/2604.15750/) (2026)
- [Stability-Weighted Decoding for Diffusion Language Models](https://mlsanity.com/paper/2604.17068/) (2026)
- [Elastic-dLLM: Position Preserving Context Compression and Augmentation of Diffusion LLMs](https://mlsanity.com/paper/2605.18165/) (2026)
- [The Path Matters: Learning a Token-Commitment Policy for Diffusion Language Models](https://mlsanity.com/paper/2605.24697/) (2026)
- [WaveFilter: Enhancing the Long-Context Capability of Diffusion LLMs via Wavelet-Guided KV Cache Filtering](https://mlsanity.com/paper/2606.00724/) (2026)
- [Polestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs](https://mlsanity.com/paper/2607.14107/) (2026)
- [AsyncLane: Decoupling Refinement from Advancement in Diffusion Language Model Decoding](https://mlsanity.com/paper/2606.08411/) (2026)
- [LESS Is More: Mutual-Stability Sampling for Diffusion Language Models](https://mlsanity.com/paper/2606.16908/) (2026)
- [Understanding Evaluation Illusion in Diffusion Large Language Models](https://mlsanity.com/paper/2606.29228/) (2026)
- [Affix Cache for Diffusion Large Language Models](https://mlsanity.com/paper/2608.26140/) (2026)
- [What does FFN compression change downstream? Same-state causal restoration in diffusion language models](https://mlsanity.com/paper/2609.31685/) (2026)
- [Time-Anchored Diffusion Language Models: Latent-Space Caching for Fast Generation](https://mlsanity.com/paper/2609.37924/) (2026)

## Abstract (arXiv)

Diffusion-based large language models (dLLMs), despite their promising performance, still suffer from inferior inference efficiency. This is because dLLMs rely on bidirectional attention and cannot directly benefit from the standard key-value (KV) cache as autoregressive models (ARMs) do. To tackle this issue, we introduce textitDual aDaptive Cache (d2Cache), which is a training-free approximate KV cache framework for accelerating dLLM inference. d2Cache features a two-stage fine-grained selection strategy to identify tokens and adaptively update their KV states at each decoding step, while caching the KV states of the remaining tokens for reuse. Furthermore, d2Cache naturally offers a more reliable decoding alternative, which can enable quasi left-to-right generation and mitigate premature overconfidence in tokens at the end of the sequence. Extensive experimental results on two representative dLLMs (ie, LLaDA and Dream) demonstrate that d2Cache not only achieves substantial inference speedups, but also yields consistent improvements in generation quality. The code is available at https://github.com/Kamichanw/d2Cache.