Related papers: Mitigating the Double-Reallocation Issue for IPv6 …
Production vLLM fleets provision every instance for worst-case context length, wasting 4-8x concurrency on the 80-95% of requests that are short and simultaneously triggering KV-cache failures -- OOM crashes, preemption storms, and request…
Segment Routing over IPv6 (SRv6 in short) is a networking solution for IP backbones and datacenters. The SRv6 standardization, implementation and research are actively progressing and SRv6 has already been adopted in a number of large scale…
In optical WDM networks, since each lightpath can carry a huge mount of traffic, failures may seriously damage the end user applications. Hence fault tolerance becomes an important issue on these networks. The light path which carries…
The efficacy of a communication network hinges upon both its physical architecture and the protocols that are employed within it. In the context of quantum communications, there exists a fundamental rate-loss tradeoff for point-to-point…
Today's Cloud applications are dominated by composite applications comprising multiple computing and data components with strong communication correlations among them. Although Cloud providers are deploying large number of computing and…
Recent workload measurements in Google data centers provide an opportunity to challenge existing models and, more broadly, to enhance the understanding of dispatching policies in computing clusters. Through extensive data-driven…
MmWave communications, one of the cornerstones of future 5G mobile networks, are characterized at the same time by a potential multi-gigabit capacity and by a very dynamic channel, sensitive to blockage, wide fluctuations in the received…
Parallel transmission, as defined in high-speed Ethernet standards, enables to use less expensive optoelectronics and offers backwards compatibility with legacy Optical Transport Network (OTN) infrastructure. However, optimal parallel…
Load Balancing is a fundamental technology for scaling cloud infrastructure. It enables systems to distribute incoming traffic across backend servers using predefined algorithms such as round robin, weighted round robin, least connections,…
In many application areas such as large-scale disaster detection, IoT networks connote the characteristics of LLN (Low power and Lossy Network). With few exceptions, prior work on RPL(Routing Protocol for LLN), a standard routing protocol…
Quantum computing promises to solve previously intractable problems, with neutral atoms emerging as a promising technology. Zoned neutral atom architectures allow for immense parallelism and higher coherence times by shielding idling atoms…
In this work we introduce Lean Point Networks (LPNs) to train deeper and more accurate point processing networks by relying on three novel point processing blocks that improve memory consumption, inference time, and accuracy: a…
A key challenge for ultra-low-power (ULP) devices is handling peripheral linking, where the main central processing unit (CPU) periodically mediates the interaction among multiple peripherals following wake-up events. Current solutions…
We study Latent Recurrent Transformer (LRT), a lightweight augmentation of autoregressive transformers that reuses a high-level source-layer hidden state from the previous token as recurrent memory for the next token. Because this source…
Multicore processors constitute the main architecture choice for modern computing systems in different market segments. Despite their benefits, the contention that naturally appears when multiple applications compete for the use of shared…
Cost of serving large language models (LLM) is high, but the expensive and scarce GPUs are poorly efficient when generating tokens sequentially, unless the batch of sequences is enlarged. However, the batch size is limited by some…
Protected user-level libraries have been proposed as a way to allow mutually distrusting applications to safely share kernel-bypass services. In this paper, we identify and solve several previously unaddressed obstacles to realizing this…
With the increasing demands for real-time applications traffic in net- works such as video and voice a high convergence time for the existing routing protocols when failure occurred is required. These applications can be very sensitive to…
Traditional network resident functions (e.g., firewalls, network address translation) and middleboxes (caches, load balancers) have moved from purpose-built appliances to software-based components. However, L2/L3 network functions (NFs) are…
Despite encryption, the packet size is still visible, enabling observers to infer private information in the Internet of Things (IoT) environment (e.g., IoT device identification). Packet padding obfuscates packet-length characteristics…