Related papers: Locality-aware Fair Scheduling in LLM Serving

Algorithm performance in supervised learning is a combination of memorization, generalization, and luck. By estimating how much information an algorithm can memorize from a dataset, we can set a lower bound on the amount of performance due…

Large Language Models (LLMs) have presented impressive performance across several transformative tasks. However, it is non-trivial to efficiently utilize large-scale cluster resources to develop LLMs, often riddled with numerous challenges…

Fairness-aware learning mainly focuses on single task learning (STL). The fairness implications of multi-task learning (MTL) have only recently been considered and a seminal approach has been proposed that considers the fairness-accuracy…

In recent years, Local Differential Privacy (LDP), a robust privacy-preserving methodology, has gained widespread adoption in real-world applications. With LDP, users can perturb their data on their devices before sending it out for…

Recent large language models (LLMs) employ billions of parameters to enable broad problem-solving capabilities. Such language models also tend to be memory-bound because of the dominance of matrix-vector and matrix-matrix multiplications…

Diffusion-based large language models (dLLMs) are gaining attention for their inherent capacity for parallel decoding, offering a compelling alternative to autoregressive LLMs. Among various decoding strategies, block-wise…

In this brief paper, we investigate online training of Long Short Term Memory (LSTM) architectures in a distributed network of nodes, where each node employs an LSTM based structure for online regression. In particular, each node…

The legal landscape encompasses a wide array of lawsuit types, presenting lawyers with challenges in delivering timely and accurate information to clients, particularly concerning critical aspects like potential imprisonment duration or…

It is significant to apply load-balancing strategy to improve the performance and reliability of resource in data centers. One of the challenging scheduling problems in Cloud data centers is to take the allocation and migration of…

Self-attention is an essential component of large language models (LLM) but a significant source of inference latency for long sequences. In multi-tenant LLM serving scenarios, the compute and memory operation cost of self-attention can be…

Long-sequence decision-making, which is usually addressed through reinforcement learning (RL), is a critical component for optimizing strategic operations in dynamic environments, such as real-time bidding in computational advertising. The…

Diffusion language models (DLMs) have emerged as a promising alternative to the long-dominant autoregressive (AR) paradigm, offering a parallelable decoding process that could yield greater efficiency. Yet, in practice, current open-source…

Large Language Models (LLMs) can perform zero-shot learning on unseen tasks and few-shot learning on complex reasoning tasks. However, resource-limited mobile edge networks struggle to support long-context LLM serving for LLM agents during…

LLM serving systems typically treat user prompts as monolithic inputs, optimizing inference through decoding tricks or inter-query batching. However, many real-world prompts contain latent semantic parallelism--decomposable structures where…

Deploying large language model (LLM) inference at scale requires jointly selecting base models, provisioning heterogeneous GPUs, configuring parallelism, and distributing workloads under tight latency, accuracy, and budget constraints.…

The Logical Execution Time (LET) programming model has recently received considerable attention, particularly because of its timing and dataflow determinism. In LET, task computation appears always to take the same amount of time (called…

Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to Autoregressive Models (ARMs), utilizing parallel decoding to overcome sequential bottlenecks. However, existing research focuses primarily on kernel-level…

With the emerging application of Federated Learning (FL) in finance, hiring and healthcare, FL models are regulated to be fair, preventing disparities with respect to legally protected attributes such as race or gender. Two concepts of…

Local consistencies stronger than arc consistency have received a lot of attention since the early days of CSP research. %because of the strong pruning they can achieve. However, they have not been widely adopted by CSP solvers. This is…

Prefix circuits are fundamental components in digital adders, widely used in digital systems due to their efficiency in calculating carry signals. Synthesizing prefix circuits with minimized area and delay is crucial for enhancing the…