TeDiServe is a cluster‑level serving system designed for diffusion language models (DLMs). It addresses DLM‑specific challenges such as the speed‑quality tradeoff from confidence‑based denoising, variable parallelization under fluctuating load, and non‑uniform per‑step costs from approximate KV caching. By employing deadline‑aware scheduling, adaptive load control, and a quality‑aware optimization for cluster reconfiguration, TeDiServe achieves up to 56.6 percentage points higher SLO attainment and reduces end‑to‑end latency by up to 46% with less than 1% accuracy loss.
arXiv:2606. 29094v1 Announce Type: new Abstract: Diffusion language models (DLMs) have recently emerged as a promising alternative to conventional autoregressive language models.
arXiv:2607. 12829v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) offer a theoretical advantage in parallel generation over standard autoregressive models.
The paper introduces the Denoising Workload Surface (DWS), a two‑dimensional probability surface that captures the block‑autoregressive generation structure of diffusion large language models (dLLMs). By preserving both output block and within‑block denoising step information, DWS enables a lightweight, prompt‑only predictor to estimate per‑request inference cost accurately, even on a single CPU core. In real‑world serving experiments, DWS reduces cost‑prediction error by up to 2.5× and improves end‑to‑end latency for online chatbots by up to 1.92×.
arXiv:2608. 06557v1 Announce Type: cross Abstract: The reasoning and agentic capabilities of large language models have expanded the range of applications they support, from short interactive exchanges to long, compute-heavy requests.
arXiv:2607. 08930v1 Announce Type: new Abstract: Efficient serving of diffusion large language models (dLLMs) is hindered by convergence heterogeneity: when batching multiple requests, different sequences converge at different rates, causing faster requests to stall behind slower stragglers and introducing compute bubbles and tail latency.
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: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.
GroupKV is a lightweight hierarchical KV cache management system designed for long‑context diffusion large language model (dLLM) inference. It partitions the context into contiguous groups and uses coarse‑to‑fine sparse selection, cross‑layer consistency for predictive prefetching, and a staleness correction mechanism to keep the cache coherent amid dynamic KV updates. The approach also incorporates streaming prefill to lower peak memory usage, achieving up to 48× longer serviceable context, 3.73× faster inference in offload‑based settings, and competitive task accuracy.
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:2607. 19349v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as always-on online services, making efficient LLM serving a critical systems challenge.
arXiv:2506. 06295v2 Announce Type: replace-cross Abstract: Autoregressive Models (ARMs) have long dominated the landscape of Large Language Models.
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.