arXiv AI June 30, 2026 By Meixuan Wang, Yinyu Ye, Zijie Zhou

LLM Serving Optimization with Variable Prefill and Decode Lengths

arXiv:2508. 06133v4 Announce Type: replace-cross Abstract: We study offline scheduling for large language model (LLM) serving under a fixed KV-cache memory budget, where requests have heterogeneous prompt (prefill) and response (decode) lengths.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jun 29

Ranking Before Serving: Low-Latency LLM Serving via Pairwise Learning-to-Rank

arXiv:2510. 03243v3 Announce Type: replace-cross Abstract: Efficient scheduling of large language model (LLM) inference tasks is critical for achieving low latency and high throughput, a challenge that is becoming increasingly acute with the rise of reasoning-capable LLMs whose generation lengths are highly variable.

By Yiheng Tao, Yihe Zhang, Matthew Dearing, Xin Wang, Yuping Fan, Michael E. Papka, Zhiling Lan

llms efficiency benchmarks

arXiv AI

Jun 16

Optimizing LLM Inference: Fluid-Guided Online Scheduling with Memory Constraints

arXiv:2504. 11320v4 Announce Type: replace-cross Abstract: Large language models now serve millions of users daily, with providers incurring costs exceeding $700,000 per day.

By Ruicheng Ao, Gan Luo, David Simchi-Levi, Xinshang Wang

llms benchmarks safety

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.

llms diffusion

arXiv Machine Learning

Aug 10

Cascade: Exploiting SLO-Aware latency budget for fair and high goodput LLM inference serving

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.

By Muhammad Adnan, Rohan Mahapatra, Prashant J. Nair, Daniel Berger, Pantea Zardoshti, Rodrigo Fonseca, Esha Choukse

llms agents safety

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.

By Nitin Kedia, Saurabh Agarwal, Myungjin Lee, Aditya Akella

llms diffusion

arXiv Machine Learning

Sep 17

GroupKV: Hierarchical KV Cache Management for Long-Context Diffusion LLM Inference

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.

By Jinhao Wang, Zhexin Hu, Kangjie Zhou, Xin Zhou, Fangfang Liu

llms diffusion efficiency

One email a morning, machine-written

Related stories

Ranking Before Serving: Low-Latency LLM Serving via Pairwise Learning-to-Rank

Optimizing LLM Inference: Fluid-Guided Online Scheduling with Memory Constraints

Sangam: Efficiently Serving Diffusion LLMs with the AR Stack

Cascade: Exploiting SLO-Aware latency budget for fair and high goodput LLM inference serving

Sangam: Efficiently Serving Diffusion LLMs with the AR Stack

GroupKV: Hierarchical KV Cache Management for Long-Context Diffusion LLM Inference