Related papers: TrEnv-X: Transparently Share Serverless Execution …
The power and flexibility of software-defined networks lead to a programmable network infrastructure in which in-network computation can help accelerating the performance of applications. This can be achieved by offloading some…
This paper presents a system called NetKernel that decouples the network stack from the guest virtual machine and offers it as an independent module. NetKernel represents a new paradigm where network stack can be managed as part of the…
Large model inference is shifting from cloud to edge due to concerns about the privacy of user interaction data. However, edge devices often struggle with limited computing power, memory, and bandwidth, requiring collaboration across…
The transition of Large Language Models (LLMs) from passive code generators to autonomous agents introduces significant safety risks, specifically regarding destructive commands and inconsistent system states. Existing commercial solutions…
We present MaxMem, a tiered main memory management system that aims to maximize Big Data application colocation and performance. MaxMem uses an application-agnostic and lightweight memory occupancy control mechanism based on fast memory…
Designing efficient and scalable sparse linear algebra kernels on modern multi-GPU based HPC systems is a daunting task due to significant irregular memory references and workload imbalance across the GPUs. This is particularly the case for…
Cross-core communication is increasingly a bottleneck as the number of processing elements increase per system-on-chip. Typical hardware solutions to cross-core communication are often inflexible; while software solutions are flexible, they…
Memory disaggregation via CXL enables multi-host resource sharing. However, existing CXL sharing mechanisms enforce coarse-grained, host-level permissions only, leaving isolation to the operating system. Today, virtual memory enables…
Large language model (LLM) serving has transformed from stateless to stateful systems, utilizing techniques like context caching and disaggregated inference. These optimizations extend the lifespan and domain of the KV cache, necessitating…
Serverless computing offers attractive scalability, elasticity and cost-effectiveness. However, constraints on memory, CPU and function runtime have hindered its adoption for data-intensive applications and machine learning (ML) workloads.…
Finetuning large language models (LLMs) is essential for task adaptation, yet today's serving stacks isolate inference and finetuning on separate GPU clusters -- wasting resources and under-utilizing hardware. We introduce FlexLLM, the…
Virtualization, after having found widespread adoption in the server and desktop arena, is poised to change the architecture of embedded systems as well. The benefits afforded by virtualization - enhanced isolation, manageability,…
Stateful tool-using LLM agents treat the context window as working memory, yet today's agent harnesses manage residency and durability as best-effort, causing recurring failures: lost state after compaction, bypassed flushes on reset, and…
Serverless computing is an emerging cloud paradigm that offers an elastic and scalable allocation of computing resources with pay-as-you-go billing. In the Function-as-a-Service (FaaS) programming model, applications comprise short-lived…
Serverless cloud is an innovative cloud service model that frees customers from most cloud management duties. It also offers the same advantages as other cloud models but at much lower costs. As a result, the serverless cloud has been…
Cloud service provider propose services to insensitive customers to use their platform. Different services can achieve the same result at different cost. In this paper, we study the efficiency of a serverless architecture for running highly…
Large language models (LLMs) with different architectures and sizes have been developed. Serving each LLM with dedicated GPUs leads to resource waste and service inefficiency due to the varying demand of LLM requests. A common practice is…
The growing demands in the training and inference of Large Language Models (LLMs) are accelerating the adoption of scale-up systems that extend server shared memory through the use of Compute Express Link (CXL)-based load/store…
Serverless computing is increasingly popular because of its lower cost and easier deployment. Several cloud service providers (CSPs) offer serverless computing on their public clouds, but it may bring the vendor lock-in risk. To avoid this…
Production LLM serving must simultaneously deliver high throughput, low latency, and sufficient context capacity under non-stationary traffic and mixed request requirements. Data parallelism (DP) maximizes throughput by running independent…