Related papers: Characterizing Mobile SoC for Accelerating Heterog…

Next-generation mixed-criticality Systems-on-chip (SoCs) for robotics, automotive, and space must execute mixed-criticality AI-enhanced sensor processing and control workloads, ensuring reliable and time-predictable execution of critical…

One of the most critical aspects of integrating loosely-coupled accelerators in heterogeneous SoC architectures is orchestrating their interactions with the memory hierarchy, especially in terms of navigating the various cache-coherence…

Heterogeneous MPSoCs comprise diverse processing units of varying compute capabilities. To date, the mapping strategies of neural networks (NNs) onto such systems are yet to exploit the full potential of processing parallelism, made…

Large language models (LLMs) are adopted for software and hardware design, yet these domains are still evaluated separately. Software benchmarks typically assume fixed hardware targets, while hardware benchmarks focus on component-level…

Edge computing processes data where it is generated, enabling faster decisions, lower bandwidth usage, and improved privacy. However, edge devices typically operate under strict constraints on processing power, memory, and energy…

Large language models (LLMs) power a new generation of interactive AI applications exemplified by ChatGPT. The interactive nature of these applications demands low latency for LLM inference. Existing LLM serving systems use…

As large language models (LLMs) continue to scale, the high power consumption of AI accelerators in datacenters presents significant challenges, substantially increasing the total cost of ownership (TCO) for cloud service providers (CSPs)…

The rapid development of large language model (LLM)-based agents has unlocked new possibilities for autonomous multi-turn reasoning and tool-augmented decision-making. However, their real-world deployment is hindered by severe…

In recent years, large language models have demonstrated remarkable performance across various natural language processing (NLP) tasks. However, deploying these models for real-world applications often requires efficient inference solutions…

Recent studies have extensively explored NPU architectures for accelerating AI inference in on-device environments, which are inherently resource-constrained. Meanwhile, transformer-based large language models (LLMs) have become dominant,…

Breakthroughs in the fields of deep learning and mobile system-on-chips are radically changing the way we use our smartphones. However, deep neural networks inference is still a challenging task for edge AI devices due to the computational…

Recent advancements in large language models (LLMs) boasting billions of parameters have generated a significant demand for efficient deployment in inference workloads. The majority of existing approaches rely on temporal architectures that…

Large language models (LLMs) have been widely applied but face challenges in efficient inference. While quantization methods reduce computational demands, ultra-low bit quantization with arbitrary precision is hindered by limited GPU Tensor…

Emerging AI accelerators increasingly adopt wafer-scale manufacturing technologies, integrating hundreds of thousands of AI cores in a mesh architecture with large distributed on-chip memory (tens of GB in total) and ultra-high on-chip…

Running language models in the browser presents a unique opportunity to build efficient, private, and portable AI applications, but requires contending with constrained memory availability and heterogeneous hardware targets. To realize this…

Multimodal large language model (MLLM) inference splits into two phases with opposing hardware demands: vision encoding is compute-bound, while language generation is memory-bandwidth-bound. We show that under standard transformer KV…

On-device inference of machine learning models for mobile phones is desirable due to its lower latency and increased privacy. Running such a compute-intensive task solely on the mobile CPU, however, can be difficult due to limited computing…

Efficiently harnessing GPU compute is critical to improving user experience and reducing operational costs in large language model (LLM) services. However, current inference engine schedulers overlook the attention backend's sensitivity to…

Edge computing's growing prominence, due to its ability to reduce communication latency and enable real-time processing, is promoting the rise of high-performance, heterogeneous System-on-Chip solutions. While current approaches often…

As large language models (LLMs) continue to grow in size, distributed inference has become increasingly important. Model-parallel strategies must now efficiently scale not only across multiple GPUs but also across multiple nodes. In this…