dKV-Cache: The Cache for Diffusion Language Models

• URL: http://arxiv.org/abs/2505.15781v1
• Date: Wed, 21 May 2025 17:32:10 GMT
• Title: dKV-Cache: The Cache for Diffusion Language Models
• Abstract summary: Diffusion Language Models (DLMs) have been seen as a promising competitor for autoregressive language models.<n>We propose a KV-cache-like mechanism, delayed KV-Cache, for the denoising process of DLMs.<n>Our approach is motivated by the observation that different tokens have distinct representation dynamics throughout the diffusion process.
• Score: 53.85291644298835
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion Language Models (DLMs) have been seen as a promising competitor for autoregressive language models. However, diffusion language models have long been constrained by slow inference. A core challenge is that their non-autoregressive architecture and bidirectional attention preclude the key-value cache that accelerates decoding. We address this bottleneck by proposing a KV-cache-like mechanism, delayed KV-Cache, for the denoising process of DLMs. Our approach is motivated by the observation that different tokens have distinct representation dynamics throughout the diffusion process. Accordingly, we propose a delayed and conditioned caching strategy for key and value states. We design two complementary variants to cache key and value step-by-step: (1) dKV-Cache-Decode, which provides almost lossless acceleration, and even improves performance on long sequences, suggesting that existing DLMs may under-utilise contextual information during inference. (2) dKV-Cache-Greedy, which has aggressive caching with reduced lifespan, achieving higher speed-ups with quadratic time complexity at the cost of some performance degradation. dKV-Cache, in final, achieves from 2-10x speedup in inference, largely narrowing the gap between ARs and DLMs. We evaluate our dKV-Cache on several benchmarks, delivering acceleration across general language understanding, mathematical, and code-generation benchmarks. Experiments demonstrate that cache can also be used in DLMs, even in a training-free manner from current DLMs.

Related papers

• VisCache: Visual KV Cache Pruning for Efficient Vision Large Language Model Inference [17.932004205808486]
  VisCache is a framework for coarse-to-fine textbfVisual KV textbfCache pruning without training.<n>PruneKV is a surgical KV compression algorithm tailored to the attention dynamics of Vision Large Language Models.<n>VisCache consistently outperforms existing baselines.
  arXiv  Detail & Related papers  (2026-08-25T04:52:05Z)
• Enabling KV Caching of Shared Prefix for Diffusion Language Models [0.2740273306918099]
  Key-value (KV) caching for shared prefixes is essential for high- throughput large language models (LLM) serving.<n>We propose bicache, the first KV caching technique for shared prefixes in diffusion language models (DLMs)<n>We show that bicache significantly improves serving throughput by 36.3%-98.3% compared to existing techniques without accuracy collapse.
  arXiv  Detail & Related papers  (2026-05-26T05:27:57Z)
• Decouple and Cache: KV Cache Construction for Streaming Video Understanding [53.55135022958052]
  Streaming video understanding requires processing unbounded video streams with limited memory and computation.<n>We propose Decoupled Streaming Cache(DSCache), a training-free cache construction mechanism that adapts pretrained offline models to streaming settings.<n> Experiments on Streaming Video QA benchmarks demonstrate DSCache's state-of-the-art performance, with an average 2.5% accuracy gains over prior methods.
  arXiv  Detail & Related papers  (2026-05-03T13:02:44Z)
• Flow caching for autoregressive video generation [72.10021661412364]
  We present FlowCache, the first caching framework specifically designed for autoregressive video generation.<n>Our method achieves remarkable speedups of 2.38 times on MAGI-1 and 6.7 times on SkyReels-V2, with negligible quality degradation.
  arXiv  Detail & Related papers  (2026-02-11T13:11:04Z)
• VidLaDA: Bidirectional Diffusion Large Language Models for Efficient Video Understanding [52.69880888587866]
  Current Video Large Language Models (Video LLMs) typically encode frames via a encoder vision and employ an autoregressive (AR) LLM for understanding and generation.<n>We propose VidLaDA, a Diffusion Video LLM based on Language Models (DLMs) that leverages bidirectional attention to unlock comprehensive modeling and decode tokens in parallel.<n>Experiments show VidLaDA rivals state-of-the-art AR baselines and outperforms DLM baselines, with MARS-Cache delivering over 12x speedup without compromising accuracy.
  arXiv  Detail & Related papers  (2026-01-25T15:02:01Z)
• Joint Encoding of KV-Cache Blocks for Scalable LLM Serving [3.3230675313521716]
  Existing KV-cache compression methods rely on rigids, disrupt tensor layouts, or require specialized compute.<n>We propose joint encoding of KV-cache blocks, which fuses similar blocks across requests and input chunks into shared representations.<n>This alleviates the KV-cache memory bottleneck, supporting high-concurrency serving without specialized hardware.
  arXiv  Detail & Related papers  (2026-01-06T14:50:58Z)
• LightCache: Memory-Efficient, Training-Free Acceleration for Video Generation [40.968338980157846]
  Training-free acceleration has emerged as an advanced research area in video generation based on diffusion models.<n>In this paper, we decompose the inference process into the encoding, denoising, and decoding stages.<n>We propose stage-specific strategies for reducing memory consumption.
  arXiv  Detail & Related papers  (2025-10-06T20:54:44Z)
• d$^2$Cache: Accelerating Diffusion-Based LLMs via Dual Adaptive Caching [7.004421957218099]
  Diffusion-based large language models (dLLMs) suffer from inferior inference efficiency.<n>We introduce d$2$Cache, which is a training-free approximate KV cache framework for accelerating dLLM inference.
  arXiv  Detail & Related papers  (2025-09-27T04:07:23Z)
• LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models [52.56008278458534]
  LaCache is a training-free method for efficient and accurate generative inference of Large Language Models.<n>LaCache enables LLMs to address both of the critical challenges in long-range modeling: robust long-range capabilities and continuous generation without running out-of-memory.
  arXiv  Detail & Related papers  (2025-07-14T19:09:57Z)
• QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache [67.84112700032007]
  Large Language Models (LLMs) are increasingly being deployed on edge devices for long-context settings.<n>In these scenarios, the Key-Value ( KV) cache is the primary bottleneck in terms of both GPU memory and latency.<n>We propose a novel self-speculative decoding framework, QuantSpec, where the draft model shares the architecture of the target model but employs a hierarchical 4-bit quantized KV cache and 4-bit quantized weights for acceleration.
  arXiv  Detail & Related papers  (2025-02-05T20:43:48Z)
• VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference Acceleration [7.463830743649754]
  Vision-Language Models (VLMs) have demonstrated impressive performance across a versatile set of tasks. Key-Value (KV) cache encodes long visual contexts, such as images or videos. Existing KV cache compression methods are effective for Large Language Models (LLMs) We propose a novel KV cache compression recipe tailored for accelerating VLM inference.
  arXiv  Detail & Related papers  (2024-10-29T20:04:34Z)
• FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality [58.80996741843102]
  FasterCache is a training-free strategy designed to accelerate the inference of video diffusion models with high-quality generation.<n>We show that FasterCache can significantly accelerate video generation while keeping video quality comparable to the baseline.
  arXiv  Detail & Related papers  (2024-10-25T07:24:38Z)
• ThinK: Thinner Key Cache by Query-Driven Pruning [63.13363917871414]
  Large Language Models (LLMs) have revolutionized the field of natural language processing, achieving unprecedented performance across a variety of applications.<n>This paper focuses on the long-context scenario, addressing the inefficiencies in KV cache memory consumption during inference.<n>We propose ThinK, a novel query-dependent KV cache pruning method designed to minimize attention weight loss while selectively pruning the least significant channels.
  arXiv  Detail & Related papers  (2024-07-30T17:59:08Z)
• Efficient Inference of Vision Instruction-Following Models with Elastic Cache [76.44955111634545]
  We introduce Elastic Cache, a novel strategy for efficient deployment of instruction-following large vision-language models. We propose an importance-driven cache merging strategy to prune redundancy caches. For instruction encoding, we utilize the frequency to evaluate the importance of caches. Results on a range of LVLMs demonstrate that Elastic Cache not only boosts efficiency but also notably outperforms existing pruning methods in language generation.
  arXiv  Detail & Related papers  (2024-07-25T15:29:05Z)
• Efficient LLM Inference with Kcache [3.945956673130761]
  Large Language Models (LLMs) have had a profound impact on AI applications. KV Cache technology is one of the most widely used techniques in the industry. We propose a novel KCache technique to alleviate the memory bottleneck issue during the LLMs inference process.
  arXiv  Detail & Related papers  (2024-04-28T03:11:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.