Related papers: Efficient Orchestration of Host and Remote Shared …
University campuses host abundant but fragmented GPU resources whose voluntary sharing is blocked by a mismatch between revocable, autonomous ownership and migration mechanisms that assume stationary failure hazards, homogeneous…
This paper studies the resource allocation algorithm design for multiuser coordinated multipoint (CoMP) networks with simultaneous wireless information and power transfer (SWIPT). In particular, remote radio heads (RRHs) are connected to a…
As deep learning models continue to increase in size, the memory requirements for training have surged. While high-level techniques like offloading, recomputation, and compression can alleviate memory pressure, they also introduce…
KV caching is a fundamental technique for accelerating Large Language Model (LLM) inference by reusing key-value (KV) pairs from previous queries, but its effectiveness under limited memory is highly sensitive to the eviction policy. The…
Transformer-based language models such as BERT provide significant accuracy improvement for a multitude of natural language processing (NLP) tasks. However, their hefty computational and memory demands make them challenging to deploy to…
Scheduling virtual machines (VMs) on hosts in cloud data centers dictates efficiency and is an NP-hard problem with incomplete information. Prior work improved VM scheduling with predicted VM lifetimes. Our work further improves…
We introduce Cortex, a prototype workflow-aware serving platform designed for agentic workloads. The core principle of Cortex is stage isolation: it provisions dedicated resource pools for each distinct stage of an agentic workflow. This…
Reinforcement learning with verifiable rewards (RLVR) has recently unlocked strong reasoning capabilities in large language models (LLMs), triggering rapid exploration of new algorithms and data. However, RLVR training is notoriously…
IoT applications increasingly rely on on-device AI accelerators to ensure high performance, especially in low-connectivity and safety-critical scenarios. However, the limited on-chip memory of these accelerators forces inference runtimes to…
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…
Serverless computing abstracts away server management, enabling automatic scaling, efficient resource utilization, and cost-effective pricing models. However, despite these advantages, it faces the significant challenge of cold-start…
In LLM serving, reusing the KV cache of prompts across requests is critical for reducing TTFT and serving costs. Cache-affinity scheduling, which co-locates requests with the same prompt prefix to maximize KV cache reuse, often conflicts…
Non-volatile random access memory (NVRAM) offers byte-addressable persistence at speeds comparable to DRAM. However, with caches remaining volatile, automatic cache evictions can reorder updates to memory, potentially leaving persistent…
We give a more space-efficient implementation of adaptive mergesort: Virtual-Memory Powersort. Using internal buffering techniques, we significantly reduce the memory consumption of the algorithm; specifically, for sorting $n$ objects the…
Fault-tolerant distributed applications require mechanisms to recover data lost via a process failure. On modern cluster systems it is typically impractical to request replacement resources after such a failure. Therefore, applications have…
Tiered memory systems consisting of fast small memory and slow large memory have emerged to provide high capacity memory in a cost-effective way. The effectiveness of tiered memory systems relies on how many memory accesses can be absorbed…
Byte-addressable non-volatile main memory (NVM) demands transactional mechanisms to access and manipulate data on NVM atomically. Those transaction mechanisms often employ a logging mechanism (undo logging or redo logging). However, the…
Modern networked systems are increasingly reconfigurable, enabling demand-aware infrastructures whose resources can be adjusted according to the workload they currently serve. Such dynamic adjustments can be exploited to improve network…
Synchronization is likely the most critical performance killer in shared-memory parallel programs. With the rise of multi-core and many-core processors, the relative impact on performance and energy overhead of synchronization is bound to…
Meta computing is a new computing paradigm that aims to efficiently utilize all network computing resources to provide fault-tolerant, personalized services with strong security and privacy guarantees. It also seeks to virtualize the…