Related papers: Memory at Your Service: Fast Memory Allocation for…
Large language models (LLMs) are increasingly deployed under the Model-as-a-Service (MaaS) paradigm. To meet stringent quality-of-service (QoS) requirements, existing LLM serving systems disaggregate the prefill and decode phases of…
Personalized recommendation is an important class of deep-learning applications that powers a large collection of internet services and consumes a considerable amount of datacenter resources. As the scale of production-grade recommendation…
Large-scale cloud security platforms must continuously query millions of structured cloud resource records distributed across thousands of tenant accounts. Broad, account-spanning queries saturate database infrastructure, producing P95…
This paper summarizes our work on characterizing application memory error vulnerability to optimize datacenter cost via Heterogeneous-Reliability Memory (HRM), which was published in DSN 2014, and examines the work's significance and future…
Systems for processing big data---e.g., Hadoop, Spark, and massively parallel databases---need to run workloads on behalf of multiple tenants simultaneously. The abundant disk-based storage in these systems is usually complemented by a…
With relentless CMOS technology downsizing Networks-on-Chips (NoCs) are inescapably experiencing escalating susceptibility to wearout and reduced reliability. While faults in processors and memories may be masked via redundancy, or…
Emerging applications, such as big data analytics and machine learning, require increasingly large amounts of main memory, often exceeding the capacity of current commodity processors built on DRAM technology. To address this, recent…
Modern online large language model (LLM) services, such as Retrieval-Augmented Generation (RAG) and agent systems, increasingly expose two prominent characteristics: prompt segmentation (e.g., system instructions, retrieved passages, tool…
The billion-scale Large Language Models (LLMs) need deployment on expensive server-grade GPUs with large-storage HBMs and abundant computation capability. As LLM-assisted services become popular, achieving cost-effective LLM inference on…
Existing memory management mechanisms used in commodity computing machines typically adopt hardware based address interleaving and OS directed random memory allocation to service generic application requests. These conventional memory…
Serverless computing has emerged as a market-dominant paradigm in modern cloud computing, benefiting both cloud providers and tenants. While service providers can optimize their machine utilization, tenants only need to pay for the…
With the growing demand for latency-critical and computation-intensive Internet of Things (IoT) services, the IoT-oriented network architecture, mobile edge computing (MEC), has emerged as a promising technique to reinforce the computation…
When multiple processor cores (CPUs) and a GPU integrated together on the same chip share the off-chip DRAM, requests from the GPU can heavily interfere with requests from the CPUs, leading to low system performance and starvation of cores.…
Industry demands are growing for hyper-distributed applications that span from the cloud to the edge in domains such as smart manufacturing, transportation, and agriculture. Yet today's solutions struggle to meet these demands due to…
This work elaborates on a High performance computing (HPC) architecture based on Simple Linux Utility for Resource Management (SLURM) [1] for deploying heterogeneous Large Language Models (LLMs) into a scalable inference engine. Dynamic…
Modern deployment of large language models (LLMs) frequently involves both inference serving and continuous retraining to stay aligned with evolving data and user feedback. Common practices separate these workloads onto distinct servers in…
In modern distributed systems, efficient resource allocation is a vital aspect to maintain scalability, reduce operational costs, and ensure fast execution even across heterogeneous workloads. Predictive models for resource usage are…
Serving long-context LLMs is costly because attention computation grows linearly with context length. Dynamic sparse attention algorithms (DSAs) mitigate this by attending only to the key-value (KV) cache of critical tokens. However, with…
The latest trends in high-performance computing systems show an increasing demand on the use of a large scale multicore systems in a efficient way, so that high compute-intensive applications can be executed reasonably well. However, the…
Deep learning recommendation models have grown to the terabyte scale. Traditional serving schemes--that load entire models to a single server--are unable to support this scale. One approach to support this scale is with distributed serving,…