arXiv:2606. 18431v1 Announce Type: new Abstract: LLM serving exhibits extreme length variability, making size-based scheduling difficult in practice.
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.
MAPS is a Memory-Aware Predictive Scheduling framework designed for disaggregated large language model (LLM) serving. It uses device-assisted speculative output length prediction and uncertainty-aware calibration to establish safe output-length upper bounds, which inform a hierarchical global-local scheduling strategy that reduces queue buildup and head-of-line blocking. Experiments on real-world workloads and two LLMs demonstrate that MAPS lowers average end-to-end latency by 42.6% and tail latency by up to 84.8% compared to three state-of-the-art systems.
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.
arXiv:2412. 04504v2 Announce Type: replace-cross Abstract: As large language models (LLMs) grow in popularity for their diverse capabilities, improving the efficiency of their inference systems has become increasingly critical.
arXiv:2607. 05147v1 Announce Type: new Abstract: Speculative decoding accelerates Large Language Model (LLM) inference by decoupling draft generation from target verification.
arXiv:2606. 01839v1 Announce Type: cross Abstract: LLM-based agents resolve a user task through many turns of dependent inference and tool calls, producing a workload whose total cost is unknown when the task arrives.
arXiv:2608. 15592v1 Announce Type: new Abstract: Efficient LLM serving is often bottlenecked by the need to pad sequences to a fixed maximum length, and this wastes compute and degrades throughput.
arXiv:2609.01068v1 Announce Type: new Abstract: The heavy-tailed distribution of output lengths in Large Language Model (LLM) serving poses major challenges for resource provisioning and cluster sche...
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.
TIDE (Temporal Incremental Draft Engine) is a serving‑engine‑native framework that integrates online draft adaptation into high‑performance LLM inference. By reusing intermediate hidden states from the target model as training signals, TIDE avoids extra target model computation and serving‑time overhead, activating speculation and draft training only when beneficial. On heterogeneous GPU clusters, TIDE achieves up to 1.66× higher throughput than no‑speculation baselines, reduces training time by up to 3.02×, cuts storage needs by 24×, and improves system throughput by up to 1.22×.
arXiv:2607. 28848v1 Announce Type: cross Abstract: LLM serving systems are provisioned for peak load to meet strict latency targets, leaving substantial GPU compute idle whenever traffic falls below peak.
arXiv:2609.38090v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models are a compelling architecture for scaling model capacity, making them especially attractive for deployment on resource-...