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:2608.28044v1 Announce Type: cross Abstract: Large language model (LLM) inference serving is priced by tokens, but GPU energy is consumed over inference windows. This accounting mismatch makes t...
arXiv:2609.08307v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as backends for intelligent web services, but serving them across the edge continuum requires bala...
The paper introduces FairInference, a system that guarantees token-level latency isolation for well-behaved clients in multi-tenant LLM serving. It provides a δ-token fairness guarantee, ensuring that a token generated in isolation within time d will be produced within d + δ in a shared environment. The approach enforces per-token deadlines, bounds GPU compute sharing delays, and accounts for shared KV cache overhead, leading to reduced latency spikes and higher overall throughput compared to existing LLM serving systems.
LLM serving is typically offered as a shared, multi-tenant service, where high-demand workloads from one client can cause latency SLO violations for others. Existing solutions for performance isolatio...
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: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-...
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:2609.17193v1 Announce Type: new Abstract: Large language model (LLM)-powered agentic AI services increasingly demand low-latency inference, motivating the deployment of LLMs across distributed...