arXiv AI
Jun 3
dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching
arXiv:2506. 06295v2 Announce Type: replace-cross Abstract: Autoregressive Models (ARMs) have long dominated the landscape of Large Language Models.
Archer: Adaptive Reuse of Cached Hidden States for Efficient Rollback in Diffusion Language Models
The paper introduces Archer, a training‑free caching method that enables efficient rollback in diffusion language models by reusing cached hidden states within a bounded neighborhood. Archer recomputes mutable responses at each update while reusing prompt key/value pairs, thereby amortizing prompt computation without limiting rollback capability. Experiments on code‑generation and non‑code benchmarks show significant speedups—up to 4.33× over LLaDA‑Confidence—while maintaining or improving accuracy.
Related stories
arXiv AI
Oct 12
ReplaySSM: Cache SSM Inputs, Not State
ReplaySSM is a technique that redefines how state-space models (SSMs) handle their recurrent state by caching SSM inputs instead of the state itself. It unrolls the recurrence into a checkpoint plus a buffer of recent inputs, reducing state memory traffic by about half and enabling efficient speculative rollback. The method also allows separate precision levels for checkpoints, improving output accuracy while accelerating decoding in hybrid models such as Mamba-2 and Gated DeltaNet.
arXiv Machine Learning
Jul 31
Back from the Future: Key-Value Cache Management by Counter-Causal Surprise
arXiv:2607. 27600v1 Announce Type: new Abstract: Key-value (KV) cache management through compression and eviction strategies has emerged as an important research direction in recent years.
Hugging Face Trending Papers
Jul 5
Sangam: Efficiently Serving Diffusion LLMs with the AR Stack
Diffusion language models (dLLMs) generate text by iteratively denoising a masked response and can commit multiple output positions per model invocation. Their bidirectional attention prevents exact autoregressive-style KV caching, since committing one position shifts the KV activations of all others.
arXiv Machine Learning
Sep 29
CacheReforge: Bounded Recovery for Stale KV Caches under Evolving Adapters
CacheReforge is a method for recovering stale key‑value (KV) caches in large language models when lightweight adapters evolve. It represents stale caches as layer‑wise mixed‑version objects and uses adapter anchors, sensitivity calibration, drift accumulation, and restart boundaries to decide between direct reuse, bounded recomputation, or full suffix recovery. Experiments on Qwen2.5 models with continual LoRA updates show a 92.4% reduction in mean KL divergence while only recomputing 5.44% of layers and cutting cache‑maintenance time by 93.2% compared to full prefill.
arXiv Computation and Language
Sep 23
Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs
Flash-dLLM is a training‑free inference acceleration framework that improves the speed and memory efficiency of Diffusion Large Language Models (dLLMs). It tackles GPU memory I/O bottlenecks by introducing an I/O‑aware fused KV‑cache kernel and then employs a draft‑and‑verify decoding strategy that uses the dLLM itself as both drafter and verifier. Experiments on mathematical reasoning and code‑generation tasks show Flash‑dLLM outperforms existing acceleration methods, achieving up to 11.0× speedups over the Elastic‑Cache baseline.
arXiv Machine Learning
Aug 3
OnlineCache: Learning Dynamic Caching Policies with Error Correction for Efficient Diffusion Inference
arXiv:2607. 29398v1 Announce Type: new Abstract: Diffusion models have revolutionized generative tasks but incur high latency due to iterative denoising.
arXiv Machine Learning
Jun 26
Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLM
arXiv:2606. 26120v1 Announce Type: cross Abstract: Diffusion Large Language Models (dLLMs) offer a promising alternative to autoregressive models, excelling in text generation tasks due to their bidirectional attention mechanisms.
arXiv AI
Sep 1
DASC: Decay-Aware State Compression for Hybrid Linear-Attention Serving
arXiv:2608.30386v1 Announce Type: cross Abstract: Hybrid linear-attention architectures have recently scaled to large open-weight models, offering quality competitive with full attention while substa...
arXiv Machine Learning
Aug 28
Affix Cache for Diffusion Large Language Models
The paper introduces ACache, an affix-oriented cache reuse mechanism for Diffusion Large Language Models (DLLMs). ACache identifies a small set of critical affix tokens, called Anchor Tokens, and selectively recomputes their key-value states while reusing the rest of the affix cache. Experiments on Fast-dLLM and Nano-vLLM show that recomputing about 20% of affix tokens restores accuracy and can reduce recompute latency by up to 55.7% while improving throughput by up to 1.68×.
arXiv Machine Learning
Jul 7
Sangam: Efficiently Serving Diffusion LLMs with the AR Stack
arXiv:2607. 04206v1 Announce Type: cross Abstract: Diffusion language models (dLLMs) generate text by iteratively denoising a masked response and can commit multiple output positions per model invocation.
arXiv AI
Jun 9
Enabling KV Caching of Shared Prefix for Diffusion Language Models
arXiv:2606. 07571v1 Announce Type: cross Abstract: Key-value (KV) caching for shared prefixes is essential for high-throughput large language model (LLM) serving, but it faces critical challenges in emerging diffusion language models (DLMs).