Related papers: Taurus: A Data Plane Architecture for Per-Packet M…
The inference of ML models composed of diverse structures, types, and sizes boils down to the execution of different dataflows (i.e. different tiling, ordering, parallelism, and shapes). Using the optimal dataflow for every layer of…
The advent of Programmable Data Planes represents an outstanding evolution and complete revolution of the Software- Defined Networking paradigm. The capacity to define the entire behavior of forwarding devices by controlling the packet…
Hybrid cloud-edge infrastructures now support latency-critical workloads ranging from autonomous vehicles and surgical robotics to immersive AR/VR. However, they continue to experience crippling long-tail latency spikes whenever bursty…
Traditional ML inference is evolving toward modeless inference, which abstracts the complexity of model selection from users, allowing the system to automatically choose the most appropriate model for each request based on accuracy and…
With the emergence of Cloud-RAN as one of the dominant architectural solutions for next-generation mobile networks, the reliability and latency on the fronthaul (FH) segment become critical performance metrics for applications such as the…
Neural-networks-driven intelligent data-plane (NN-driven IDP) is becoming an emerging topic for excellent accuracy and high performance. Meanwhile we argue that NN-driven IDP should satisfy three design goals: the flexibility to support…
Data-parallel (DP) load balancing has emerged as a first-order bottleneck in large-scale LLM serving. When a model is sharded across devices via tensor parallelism (TP) or expert parallelism (EP) and replicated across many DP workers, every…
The rapid urbanization growth has underscored the need for innovative solutions to enhance transportation efficiency and safety. Intelligent Transportation Systems (ITS) have emerged as a promising solution in this context. However,…
A variety of computing platform like Field Programmable Gate Array (FPGA), Graphics Processing Unit (GPU) and multicore Central Processing Unit (CPU) in data centers are suitable for acceleration of data-intensive workloads. Especially,…
Recent years have seen massive time-series data generated in many areas. This different scenario brings new challenges, particularly in terms of data ingestion, where existing technologies struggle to handle such massive time-series data,…
Forward Error Correction (FEC) remains essential for protecting video streaming against packet loss, yet most real deployments still rely on static, coarse-grained configurations that cannot react to rapid shifts in loss rate, goodput, or…
For safe and efficient planning and control in autonomous driving, we need a driving policy which can achieve desirable driving quality in long-term horizon with guaranteed safety and feasibility. Optimization-based approaches, such as…
Distributed inference of large language models (LLMs) using tensor parallelism can introduce communication overheads of $20$% even over GPUs connected via NVLink, a high-speed GPU interconnect. Several techniques have been proposed to…
Large-scale pre-trained language models such as BERT have contributed significantly to the development of NLP. However, those models require large computational resources, making it difficult to be applied to mobile devices where computing…
Emergency communications networks require in-network intelligence for timely traffic handling under dynamic demands and runtime constraints. In these environments, packets may need different inference behaviors, and conventional model…
Dynamic computation has emerged as a promising avenue to enhance the inference efficiency of deep networks. It allows selective activation of computational units, leading to a reduction in unnecessary computations for each input sample.…
We present the design of a new large scale orchestration layer for accelerators. Our system, Pathways, is explicitly designed to enable exploration of new systems and ML research ideas, while retaining state of the art performance for…
Large language models have high compute, latency, and memory requirements. While specialized accelerators such as GPUs and TPUs typically run these workloads, CPUs are more widely available and consume less energy. Accelerating LLMs with…
Achieving high availability and robust security in Kubernetes requires more than reactive scaling and standard perimeter firewalls. Traditional autoscalers, such as HPA, often fail to react quickly to traffic spikes and cannot distinguish…
Detecting Internet routing instability is a critical yet challenging task, particularly when relying solely on endpoint active measurements. This study introduces TRACE, a MachineLearning (ML)pipeline designed to identify route changes…