Related papers: Trident: Adaptive Scheduling for Heterogeneous Mul…

While 3D Multi-modal Large Language Models (MLLMs) demonstrate remarkable scene understanding capabilities, their practical deployment faces critical challenges due to computational inefficiency. The key bottleneck stems from processing…

High-definition (HD) cameras for surveillance and road traffic have experienced tremendous growth, demanding intensive computation resources for real-time analytics. Recently, offloading frames from the front-end device to the back-end edge…

Multimodal large language models (MLLMs) demonstrate exceptional capabilities in semantic understanding and visual reasoning, yet they still face challenges in precise object localization and resource-constrained edge-cloud deployment. To…

This work proposes a competitive scheduling approach, designed to scale to large heterogeneous multicore systems. This scheduler overcomes the challenges of (1) the high computation overhead of near-optimal schedulers, and (2) the error…

In this paper, we propose the first optimum process scheduling algorithm for an increasingly prevalent type of heterogeneous multicore (HEMC) system that combines high-performance big cores and energy-efficient small cores with the same…

Multimodal Large Language Models (MLLMs) have been rapidly advancing, enabling cross-modal understanding and generation, and propelling artificial intelligence towards artificial general intelligence. However, existing MLLM inference…

Manufacturing companies typically use sophisticated production planning systems optimizing production steps, often delivering near-optimal solutions. As a downside for delivering a near-optimal schedule, planning systems have high…

To usher in the next round of client AI innovation, there is an urgent need to enable efficient, lossless inference of high-accuracy large language models (LLMs) and vision language models (VLMs), jointly referred to as xLMs, on client…

Modern Mixture-of-Experts (MoE) models increasingly rely on large-scale AI accelerator clusters for efficient training. Ascend NPUs expose heterogeneous on-chip compute resources, including matrix-oriented AIC units and vector-oriented AIV…

The increasing gap between datacenter traffic volume and the capacity of electrical switches has driven the development of reconfigurable network designs utilizing optical circuit switching. Recent advancements, particularly those featuring…

Neuromorphic Systems-on-Chip (NSoCs) are becoming heterogeneous by integrating general-purpose processors (GPPs) and neural processing units (NPUs) on the same SoC. For embedded systems, an NSoC may need to execute user applications built…

Simulation and optimization are crucial for advancing the engineering design of complex systems and processes. Traditional optimization methods require substantial computational time and effort due to their reliance on resource-intensive…

Intelligent surveillance systems often handle perceptual tasks such as object detection, facial recognition, and emotion analysis independently, but they lack a unified, adaptive runtime scheduler that dynamically allocates computational…

Managing and preparing complex data for deep learning, a prevalent approach in large-scale data science can be challenging. Data transfer for model training also presents difficulties, impacting scientific fields like genomics, climate…

Large Reasoning Models (LRMs) have shown impressive capabilities in complex problem-solving, often benefiting from training on difficult mathematical problems that stimulate intricate reasoning. Recent efforts have explored automated…

Frontier models increasingly adopt Mixture-of-Experts (MoE) architectures to achieve large-model performance at reduced cost. However, training MoE models on HPC platforms is hindered by large memory footprints, frequent large-scale…

As large language models (LLMs) continue to scale and new GPUs are released even more frequently, there is an increasing demand for LLM post-training in heterogeneous environments to fully leverage underutilized mid-range or…

In recent times, the emergence of Large Language Models (LLMs) has resulted in increasingly larger model size, posing challenges for inference on low-resource devices. Prior approaches have explored offloading to facilitate low-memory…

We present a number of novel algorithms, based on mathematical optimization formulations, in order to solve a homogeneous multiprocessor scheduling problem, while minimizing the total energy consumption. In particular, for a system with a…

Parameter-efficient transfer learning (PETL), i.e., fine-tuning a small portion of parameters, is an effective strategy for adapting pre-trained models to downstream domains. To further reduce the memory demand, recent PETL works focus on…