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: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).
arXiv:2506. 06295v2 Announce Type: replace-cross Abstract: Autoregressive Models (ARMs) have long dominated the landscape of Large Language Models.
arXiv:2607. 19957v1 Announce Type: cross Abstract: Key-Value (KV) cache reduces inference latency in large language models (LLMs).
arXiv:2610.23290v1 Announce Type: new Abstract: Diffusion-based multimodal large language models (dMLLMs) decode by iterative denoising with bidirectional attention, which precludes the standard auto...
The paper introduces Window-Diffusion, a method that accelerates diffusion language model inference by pruning and caching tokens within a sliding window. It categorizes undecoded tokens into active, buffer, and far-field groups, computing only the first two while discarding the rest. Experiments on LLaDA and Dream demonstrate up to 99× speedup with minimal loss in generation quality.
arXiv:2607. 14107v1 Announce Type: cross Abstract: The inference efficiency of diffusion large language models (dLLMs) is constrained by two challenges: bidirectional attention precludes efficient KV-cache reuse, while increasing decoding parallelism with static confidence thresholds can compromise generation quality.
KV-Repurpose is an open‑source, vLLM‑based system that enables segment‑wise KV‑cache reuse beyond exact prompt prefixes in large language model serving. It integrates cache‑aware segment scheduling, prompt construction, capacity management, workload generation, and runtime monitoring to evaluate non‑prefix KV‑cache reuse. Experiments show that naive segment reuse maintains output quality for single‑document QA and summarization, while significantly improving cache hit rates and reducing time‑to‑first‑token compared to prefix caching, especially under Zipfian RAG‑style workloads.
arXiv:2608.21362v1 Announce Type: new Abstract: Transformer-based large language models (LLMs) incur high prefill latency because key-value (KV) tensors must be recomputed for each request. Existing...
arXiv:2608.30310v1 Announce Type: cross Abstract: Hybrid large language models interleave full-attention layers with linear-attention layers to reduce the cost of long-context inference. This structu...
DropKV introduces a new KV‑cache eviction framework that decouples residual‑output perturbation into independent per‑token scores, avoiding the NP‑hard combinatorial optimization of prior methods. The approach offers a provable constant‑factor approximation under a cone condition verified on three long‑context LLMs, and a high‑performance Triton‑based implementation that yields a 19.8× speedup in scoring kernels and up to 9.9% end‑to‑end prefill speedup. Benchmarks on RULER and LongBench show DropKV consistently outperforms state‑of‑the‑art baselines at the same cache budgets, achieving the lowest inference latency among eviction strategies while remaining faster than dynamic cache baselines.
arXiv:2606. 29563v1 Announce Type: cross Abstract: Large language models (LLMs) excel at complex tasks like question answering and summarization, thanks to their ability to handle long-context inputs.
arXiv:2606. 17872v1 Announce Type: cross Abstract: Large language models (LLMs) outperform earlier architectures on generative inference and long-context tasks, but their large size introduces significant challenges in memory usage, energy cost, and on-device deployment.