Related papers: HotStuff-1: Linear Consensus with One-Phase Specul…
Should LLM reasoning live in a separate module, or within a single model's forward pass and representational space? We study dual-architecture latent reasoning, where a fluent Base exchanges latent messages with a Coprocessor, and test two…
As large language models (LLMs) scale up, accuracy improves, but the autoregressive (AR) nature of decoding increases latency since each token requires a serial forward pass. Speculative decoding addresses this by employing a fast drafter…
The demand for large language model inference is rapidly increasing. Pipeline parallelism offers a cost-effective deployment strategy for distributed inference but suffers from high service latency. While incorporating speculative decoding…
Fueled by the growing popularity of proof-of-stake blockchains, there has been increasing interest and progress in permissioned consensus protocols, which could provide a simpler alternative to existing protocols, such as Paxos and PBFT. In…
Large language models (LLMs) have revolutionized natural language processing, yet their high computational demands pose significant challenges for real-time inference, especially in multi-user server speculative decoding and…
In this paper, we investigate the architecture of an optimal controller that maximizes the convergence speed of a consensus protocol with single-integrator dynamics. Under the assumption that communication delays increase with the number of…
In this paper, we present the first snap-stabilizing message forwarding protocol that uses a number of buffers per node being inde- pendent of any global parameter, that is 4 buffers per link. The protocol works on a linear chain of nodes,…
This work addresses the design of multi-agent coordination through high-order consensus protocols. While first-order consensus strategies are well-studied -- with known robustness to uncertainties such as time delays, time-varying weights,…
Optimistic responsiveness -- the ability of a consensus protocol to operate at the speed of the network -- is widely used in consensus protocol design to optimize latency and throughput. However, blockchain applications incentivize…
The leader-following consensus of multiple linear time invariant (LTI) systems under switching topology is considered. The leader-following consensus problem consists of designing for each agent a distributed protocol to make all agents…
Large Language Models (LLMs) have demonstrated remarkable performance across various tasks by effectively utilizing a prompting strategy. However, they are highly sensitive to input perturbations, such as typographical errors or slight…
In this work, we analyze the performance of a simple majority-rule protocol solving a fundamental coordination problem in distributed systems - \emph{binary majority consensus}, in the presence of probabilistic message loss. Using…
We consider the problem of solving consensus using deterministic algorithms in a synchronous dynamic network with unreliable, directional point-to-point links, which are under the control of a message adversary. In contrast to a large body…
We present the first wireless protocol that scales to hundreds of concurrent transmissions from backscatter devices. Our key innovation is a distributed coding mechanism that works below the noise floor, operates on backscatter devices and…
Speculative decoding accelerates autoregressive generation by separating token proposal from verification, but most existing approaches are designed for single-node execution and do not scale well to multi-accelerator clusters used for…
DAG-Rider popularized a new paradigm of DAG-BFT protocols, separating dissemination from consensus: all nodes disseminate transactions as blocks that reference previously known blocks, while consensus is reached by electing certain blocks…
Consensus, state-machine replication (SMR) and total order broadcast (TOB) protocols are notorious for being poorly scalable with the number of participating nodes. Despite the recent race to reduce overall message complexity of…
While speculative decoding has recently appeared as a promising direction for accelerating the inference of large language models (LLMs), the speedup and scalability are strongly bounded by the token acceptance rate. Prevalent methods…
This paper presents LinSBFT, a Byzantine Fault Tolerance (BFT) protocol with the capacity of processing over 2000 smart contract transactions per second in production. LinSBFT applies to a permissionless, public blockchain system, in which…
In recent years, content recommendation systems in large websites (or \emph{content providers}) capture an increased focus. While the type of content varies, e.g.\ movies, articles, music, advertisements, etc., the high level problem…