Related papers: A Hardware-oriented Approach for Efficient Active …
The inherent heavy computation of deep neural networks prevents their widespread applications. A widely used method for accelerating model inference is quantization, by replacing the input operands of a network using fixed-point values.…
Large Language Models (LLMs) have become essential in a variety of applications due to their advanced language understanding and generation capabilities. However, their computational and memory requirements pose significant challenges to…
Deploying large-scale transformer models on edge devices presents significant challenges due to strict constraints on memory, compute, and latency. In this work, we propose a lightweight yet effective multi-stage optimization pipeline…
Active inference is an account of cognition and behavior in complex systems which brings together action, perception, and learning under the theoretical mantle of Bayesian inference. Active inference has seen growing applications in…
Modern enterprise AI applications increasingly rely on compound AI systems - architectures that compose multiple models, retrievers, and tools to accomplish complex tasks. Deploying such systems in production demands inference…
In standard passive imitation learning, the goal is to learn a target policy by passively observing full execution trajectories of it. Unfortunately, generating such trajectories can require substantial expert effort and be impractical in…
Discrete optimization is a central problem in artificial intelligence. The optimization of the aggregated cost of a network of cost functions arises in a variety of problems including (W)CSP, DCOP, as well as optimization in stochastic…
Deep learning (DL) workloads are moving towards accelerators for faster processing and lower cost. Modern DL accelerators are good at handling the large-scale multiply-accumulate operations that dominate DL workloads; however, it is…
Autonomous robotic navigation in real-world environments requires exploration to acquire environmental information as well as goal-directed navigation in order to reach specified targets. Active inference (AIF) based on the free-energy…
Remote memory access (RMA) is an emerging high-performance programming model that uses RDMA hardware directly. Yet, accessing remote memories cannot invoke activities at the target which complicates implementation and limits performance of…
Personalized recommendation systems leverage deep learning models and account for the majority of data center AI cycles. Their performance is dominated by memory-bound sparse embedding operations with unique irregular memory access patterns…
Active inference, a neurally-inspired model for inferring actions based on the free energy principle (FEP), has been proposed as a unifying framework for understanding perception, action, and learning in the brain. Active inference has…
This paper proposes a memory-efficient optimization strategy for the high-performance point cloud registration algorithm VANICP, enabling lightweight execution on embedded GPUs with constrained hardware resources. VANICP is a recently…
The explosive growth of interactive Large Language Models (LLMs) has placed unprecedented demands for low latency on cloud GPUs, forcing them into high-power modes and causing escalating energy costs. Real-time inference workloads exhibit…
An adaptive inference method for crossbar (AIDX) is presented based on an optimization scheme for adjusting the duration and amplitude of input voltage pulses. AIDX minimizes the long-term effects of memristance drift on artificial neural…
Active inference has emerged as an alternative approach to control problems given its intuitive (probabilistic) formalism. However, despite its theoretical utility, computational implementations have largely been restricted to…
Remote Direct Memory Access (RDMA) is an efficient way to improve the performance of traditional client-server systems. Currently, there are two main design paradigms for RDMA-accelerated systems. The first allows the clients to directly…
Arbitrary-precision integer multiplication is the core kernel of many applications in simulation, cryptography, etc. Existing acceleration of arbitrary-precision integer multiplication includes CPUs, GPUs, FPGAs, and ASICs. Among these…
Large Language Models (LLMs) herald a transformative era in artificial intelligence (AI). However, the expansive scale of data and parameters of LLMs requires high-demand computational and memory resources, restricting their accessibility…
The analysis of massive scientific data often happens in the form of workflows with interdependent tasks. When such a scientific workflow needs to be scheduled on a parallel or distributed system, one usually represents the workflow as a…