相关论文: The .serva Standard: One Primitive for All AI Cost…

Large language models show promise as autonomous decision-making agents, yet their deployment in high-stakes domains remains fraught with risk. Without architectural safeguards, LLM agents exhibit catastrophic brittleness: identical…

Nowadays, we are witnessing an Artificial Intelligence revolution that dominates the technology landscape in various application domains, such as healthcare, robotics, automotive, security, and defense. Massive-scale AI models, which mimic…

As Large Language Models (LLMs) scale to handle massive concurrent traffic, optimizing the infrastructure required for inference has become a primary challenge. To manage the high cost of GPU resources while ensuring strict service-level…

Deploying expressive learning models directly on programmable dataplanes promises line-rate, low-latency traffic analysis but remains hindered by strict hardware constraints and the need for predictable, auditable behavior. Chimera…

Large language models (LLMs) are typically served from clusters of GPUs/NPUs that consist of large number of devices. Unfortunately, communication between these devices incurs significant overhead, increasing the inference latency and cost…

In this paper, we propose DEEPSERVE, a scalable and serverless AI platform designed to efficiently serve large language models (LLMs) at scale in cloud environments. DEEPSERVE addresses key challenges such as resource allocation, serving…

Neuroimaging open-data initiatives have led to increased availability of large scientific datasets. While these datasets are shifting the processing bottleneck from compute-intensive to data-intensive, current standardized analysis tools…

Multi-agent applications often execute complex tasks as multi-stage workflows, where each stage is an LLM call whose output becomes part of context for subsequent steps. Existing LLM serving systems largely assume homogeneous clusters with…

Recent research has demonstrated that artificial intelligence (AI) can assist electronic design automation (EDA) in improving both the quality and efficiency of chip design. But current AI for EDA (AI-EDA) infrastructures remain fragmented,…

Cloud platforms are increasingly relied upon to host diverse, resource-intensive workloads due to their scalability, flexibility, and cost-efficiency. In multi-tenant cloud environments, virtual machines are consolidated on shared physical…

Large-scale scientific collaborations like ATLAS, Belle II, CMS, DUNE, and others involve hundreds of research institutes and thousands of researchers spread across the globe. These experiments generate petabytes of data, with volumes soon…

Transformers have revolutionized deep learning and generative modeling, enabling advancements in natural language processing tasks. However, the size of transformer models is increasing continuously, driven by enhanced capabilities across…

Training large AI models such as LLMs and DLRMs costs massive GPUs and computing time. The high training cost has become only affordable to big tech companies, meanwhile also causing increasing concerns about the environmental impact. This…

Today's computing systems require moving data back-and-forth between computing resources (e.g., CPUs, GPUs, accelerators) and off-chip main memory so that computation can take place on the data. Unfortunately, this data movement is a major…

Development and operation of commercially viable fusion energy reactors such as tokamaks require accurate predictions of plasma dynamics from sparse, noisy, and incomplete sensors readings. The complexity of the underlying physics and the…

Neuro-symbolic AI is gaining traction in domains such as large language models, scientific discovery, and autonomous systems due to its ability to combine perception with structured reasoning. However, its deployment is often constrained by…

Tensor is the most basic and essential data structure of nowadays artificial intelligence (AI) system. The natural properties of Tensor, especially the memory-continuity and slice-independence, make it feasible for training system to…

The deployment of Large Language Models (LLMs) on consumer edge devices is throttled by the "Memory Wall" -- the prohibitive bandwidth and energy cost of fetching gigabytes of model weights from DRAM for every token generated. Current…

The increasing demand for artificial intelligence (AI) workloads across diverse computing environments has driven the need for more efficient data management strategies. Traditional cloud-based architectures struggle to handle the sheer…

Future networks must meet stringent requirements while operating within tight energy and carbon constraints. Current autoscaling mechanisms remain workload-centric and infrastructure-siloed, and are largely unaware of their environmental…