arXiv:2606. 02982v1 Announce Type: cross Abstract: The rapid growth of large language model (LLM) inference services has increased the demand for efficient multi-tenant GPU scheduling.
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.
arXiv:2602. 24044v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) adapters enable low-cost model specialization, but introduce complex caching and scheduling challenges in distributed serving systems where hundreds of adapters must be hosted concurrently.
arXiv:2606. 00735v1 Announce Type: cross Abstract: In distributed Mixture-of-Experts (MoE) inference, input-dependent token routing interacts with GPU performance variability to create persistent stragglers under synchronized execution, where the slowest GPU determines layer latency.
arXiv:2606. 28565v1 Announce Type: cross Abstract: As large language models (LLMs) move into production serving, practitioners must rapidly evaluate inference performance across diverse hardware, models, and serving parameters to meet cost and latency targets.
arXiv:2411. 07447v5 Announce Type: replace-cross Abstract: LLMs are increasingly used world-wide from daily tasks to agentic systems and data analytics, requiring significant GPU resources.
arXiv:2606. 00946v1 Announce Type: cross Abstract: Efficiently serving large language model (LLM) inference tasks is crucial both for user-perceived latency such as time-to-first-token (TTFT) and for GPU utilization.
arXiv:2606. 18431v1 Announce Type: new Abstract: LLM serving exhibits extreme length variability, making size-based scheduling difficult in practice.
arXiv:2608. 08382v1 Announce Type: new Abstract: As LLM inference shifts to multi-tenant GPU clusters, co-batching improves throughput but obscures per-tenant usage and limits control.
arXiv:2604. 07472v2 Announce Type: replace Abstract: Serving large language model (LLM) inference in cloud environments requires jointly optimizing model selection, GPU provisioning, parallelism configuration, and workload routing under latency, accuracy, memory, and budget constraints.
arXiv:2608. 15762v1 Announce Type: cross Abstract: Container-granularity scheduling leaves abundant short-lived idle slices within containers unexploited.
arXiv:2606. 09200v1 Announce Type: cross Abstract: The rapid growth of large-scale machine learning (ML) has made distributed training across multiple GPUs a fundamental component of modern ML systems.
arXiv:2604. 26968v2 Announce Type: replace-cross Abstract: Key-value (KV) cache memory management is the primary bottleneck limiting throughput and cost-efficiency in large-scale GPU inference serving.