Related papers: PretVM: Predictable, Efficient Virtual Machine for…
Performance prediction is a method to estimate the performance of Language Models (LMs) on various Natural Language Processing (NLP) tasks, mitigating computational costs associated with model capacity and data for fine-tuning. Our paper…
Large Language Models (LLMs) such as GPT-4 and Llama3 can already comprehend complex commands and process diverse tasks. This advancement facilitates their application in controlling drones and robots for various tasks. However, existing…
Actor frameworks and similar reactive programming techniques are widely used for building concurrent systems. They promise to be efficient and scale well to a large number of cores or nodes in a distributed system. However, they also expose…
In the field of robotics, researchers face a critical challenge in ensuring reliable and efficient task planning. Verifying high-level task plans before execution significantly reduces errors and enhance the overall performance of these…
The exploration and application of Large Language Models (LLMs) is thriving. To reduce deployment costs, continuous batching has become an essential feature in current service frameworks. The effectiveness of continuous batching relies on…
Modern online large language model (LLM) services, such as Retrieval-Augmented Generation (RAG) and agent systems, increasingly expose two prominent characteristics: prompt segmentation (e.g., system instructions, retrieved passages, tool…
We describe an intermediate language designed as a medium-level internal representation of programs of the interactive music system Antescofo. This representation is independent both of the Antescofo source language and of the architecture…
Programming microcontrollers involves low-level interfacing with hardware and peripherals that are concurrent and reactive. Such programs are typically written in a mixture of C and assembly using concurrent language extensions (like…
Large Language Models (LLMs) are widely used in real-time voice chat applications, typically in combination with text-to-speech (TTS) systems to generate audio responses. However, their large size often leads to noticeable latency between…
Recent advancements in language models (LMs) have gained substantial attentions on their capability to generate human-like responses. Though exhibiting a promising future for various applications such as conversation AI, these LMs face…
Unified Virtual Memory (UVM) relieves the developers from the onus of maintaining complex data structures and explicit data migration by enabling on-demand data movement between CPU memory and GPU memory. However, on-demand paging soon…
We study offline scheduling for large language model (LLM) serving under a fixed KV-cache memory budget, where requests have heterogeneous prompt (prefill) and response (decode) lengths. Prompt tokens determine initial KV usage, and each…
Large language models (LLMs) have been a disruptive innovation in recent years, and they play a crucial role in our daily lives due to their ability to understand and generate human-like text. Their capabilities include natural language…
We introduce the DeTerministic Virtual Machine (DTVM) Stack, a next-generation smart contract execution framework designed to address critical performance, determinism, and ecosystem compatibility challenges in blockchain networks. Building…
We study the problem of optimizing Large Language Model (LLM) inference scheduling to minimize total latency. LLM inference is an online and multi-task service process and also heavily energy consuming by which a pre-trained LLM processes…
Vision-Language-Action (VLA) policies are typically evaluated as if the user had finished typing or speaking before the robot begins acting. In real deployment, however, users take several seconds to enter a request, leaving the policy idle…
The multiprocessor Fixed-Job Priority (FJP) scheduling of real-time systems is studied. An important property for the schedulability analysis, the predictability (regardless to the execution times), is studied for heterogeneous…
Large language models (LLMs) are increasingly used for complex tasks that require multiple generation calls, advanced prompting techniques, control flow, and structured inputs/outputs. However, efficient systems are lacking for programming…
We study the problem of preemptive scheduling of n equal-length jobs with given release times on m identical parallel machines. The objective is to minimize the average flow time. Recently, Brucker and Kravchenko proved that the optimal…
While generative robot policies have demonstrated significant potential in learning complex, multimodal behaviors from demonstrations, they still exhibit diverse failures at deployment-time. Policy steering offers an elegant solution to…