Related papers: DualMap: Enabling Both Cache Affinity and Load Bal…
Production data centers operate under various workload sizes ranging from latency-sensitive mice flows to long-lived elephant flows. However, the predominant load balancing scheme in data center networks, equal-cost multi-path (ECMP), is…
On the Internet, sub-millisecond queueing delay and capacity-seeking have traditionally been considered mutually exclusive. We introduce a service that offers both: Low Latency Low Loss Scalable throughput (L4S). When tested under a wide…
In this paper, we consider the problem of scheduling an application on a parallel computational platform. The application is a particular task graph, either a linear chain of tasks, or a set of independent tasks. The platform is made of…
Consistent hashing is fundamental to distributed systems, but ring-based schemes can exhibit high peak-to-average load ratios unless they use many virtual nodes, while multi-probe methods improve balance at the cost of scattered memory…
LLM inference must meet strict latency SLOs (e.g., 100 ms P99 time-between-tokens) while maximizing goodput. Yet, real-world variability in prompt and response lengths skews compute-intensive prefill and memory-bound decode phases, making…
Mobility-on-demand systems are transforming the way we think about the transportation of people and goods. Most research effort has been placed on scalability issues for systems with a large number of agents and simple pick-up/drop-off…
Real-time LLM interactions demand streamed token generations, where text tokens are progressively generated and delivered to users while balancing two objectives: responsiveness (i.e., low time-to-first-token) and steady generation…
We study an one-hop device-to-device (D2D) assisted wireless caching network, where popular files are randomly and independently cached in the memory of end-users. Each user may obtain the requested files from its own memory without any…
Extract-Transform-Load (ETL) handles large amount of data and manages workload through dataflows. ETL dataflows are widely regarded as complex and expensive operations in terms of time and system resources. In order to minimize the time and…
We consider load balancing in large-scale heterogeneous server systems in the presence of data locality that imposes constraints on which tasks can be assigned to which servers. The constraints are naturally captured by a bipartite graph…
Similarity search queries in high-dimensional spaces are an important type of queries in many domains such as image processing, machine learning, etc. Since exact similarity search indexing techniques suffer from the well-known curse of…
Recent advancements in Large Language Model (LLM) agents have enabled complex multi-turn agentic tasks requiring extensive tool calling, where conversations can span dozens of API calls with increasingly large context windows. However,…
In-network caching is recognized as an effective solution to offload content servers and the network. A cache service provider (SP) always has incentives to better utilize its cache resources by taking into account diverse roles that…
Multi-agent systems increasingly orchestrate multiple specialized language models to solve complex real-world problems, often invoking them over a shared context. This execution pattern repeatedly processes the same prompt prefix across…
We investigate an optimal scheduling problem in a discrete-time system of L parallel queues that are served by K identical, randomly connected servers. Each queue may be connected to a subset of the K servers during any given time slot.…
With the rapid development of DNN applications, multi-tenant execution, where multiple DNNs are co-located on a single SoC, is becoming a prevailing trend. Although many methods are proposed in prior works to improve multi-tenant…
Large language model (LLM) serving is becoming an increasingly critical workload for cloud providers. Existing LLM serving systems focus on interactive requests, such as chatbots and coding assistants, with tight latency SLO requirements.…
Multimodal Large Language Models (MLLMs) power platforms like ChatGPT, Gemini, and Copilot, enabling richer interactions with text, images, and videos. These heterogeneous workloads introduce additional inference stages, such as vision…
In a multihop wireless network, it is crucial but challenging to schedule transmissions in an efficient and fair manner. In this paper, a novel distributed node scheduling algorithm, called Local Voting, is proposed. This algorithm tries to…
High throughput serving of large language models (LLMs) requires batching sufficiently many requests at a time. However, existing systems struggle because the key-value cache (KV cache) memory for each request is huge and grows and shrinks…