相关论文: PretVM: Predictable, Efficient Virtual Machine for…
Serving systems for Large Language Models (LLMs) improve throughput by processing several requests concurrently. However, multiplexing hardware resources between concurrent requests involves non-trivial scheduling decisions. Practical…
The burgeoning computational demands for training large language models (LLMs) necessitate efficient methods, including quantized training, which leverages low-bit arithmetic operations to reduce costs. While FP8 precision has shown…
Getting the best performance from the ever-increasing number of hardware platforms has been a recurring challenge for data processing systems. In recent years, the advent of data science with its increasingly numerous and complex types of…
The subject of this work is quantum predicative programming -- the study of developing of programs intended for execution on a quantum computer. We look at programming in the context of formal methods of program development, or programming…
Consider the problem in which n jobs that are classified into k types are to be scheduled on m identical machines without preemption. A machine requires a proper setup taking s time units before processing jobs of a given type. The…
Virtualization, after having found widespread adoption in the server and desktop arena, is poised to change the architecture of embedded systems as well. The benefits afforded by virtualization - enhanced isolation, manageability,…
Virtual machine (VM) scheduling is an important technique to efficiently operate the computing resources in a data center. Previous work has mainly focused on consolidating VMs to improve resource utilization and thus to optimize energy…
Runtime efficiency and termination are crucial properties in the studies of program verification. Instead of dealing with these issues in an ad hoc manner, it would be useful to develop a robust framework in which such properties are…
Implementing correct distributed systems is an error-prone task. Runtime Verification (RV) offers a lightweight formal method to improve reliability by monitoring system executions against correctness properties. However, applying RV in…
Visual language models (VLMs) have made significant advances in accuracy in recent years. However, their efficiency has received much less attention. This paper introduces NVILA, a family of open VLMs designed to jointly optimize efficiency…
The context of this work is cooperative scheduling, a concurrency paradigm, where task execution is not arbitrarily preempted. Instead, language constructs exist that let a task voluntarily yield the right to execute to another task. The…
We investigate the capability of a transformer pretrained on natural language to generalize to other modalities with minimal finetuning -- in particular, without finetuning of the self-attention and feedforward layers of the residual…
Time series forecasting holds significant importance in many real-world dynamic systems and has been extensively studied. Unlike natural language process (NLP) and computer vision (CV), where a single large model can tackle multiple tasks,…
Long-term time series forecasting in centralized environments poses unique challenges regarding data privacy, communication overhead, and scalability. To address these challenges, we propose FedTime, a federated large language model (LLM)…
Virtualization technology has enabled applications to be decoupled from the underlying hardware providing the benefits of portability, better control over execution environment and isolation. It has been widely adopted in scientific grids…
This thesis concerns the implementation of Lambda Prolog, a higher-order logic programming language that supports the lambda-tree syntax approach to representing and manipulating formal syntactic objects. Lambda Prolog achieves its…
In our pursuit of advancing multi-modal AI assistants capable of guiding users to achieve complex multi-step goals, we propose the task of "Visual Planning for Assistance (VPA)". Given a succinct natural language goal, e.g., "make a shelf",…
Deploying large language model (LLM)-driven conversational agents in enterprise settings requires prompts that are simultaneously correct at launch and resilient to the non-deterministic behavioral drift that characterizes production LLM…
Temporal information is crucial for detecting occluded instances. Existing temporal representations have progressed from BEV or PV features to more compact query features. Compared to these aforementioned features, predictions offer the…
Memory consistency models (MCMs) specify the legal ordering and visibility of shared memory accesses in a parallel program. Traditionally, instruction set architecture (ISA) MCMs assume that relevant program-visible memory ordering…