172 citations · 205 across the 22 of their papers we have counts for
23 papers
Token Latency Fairness: Performance Isolation for Multi-Tenant LLM Serving
Dev Bali, Soujanya Ponnapalli, Yichuan Wang +3
LLM serving is typically offered as a shared, multi-tenant service, where high-demand workloads from one client can cause latency SLO violations for others. Existing solutions for…
Learning, Fast and Slow: Towards LLMs That Adapt Continually
Rishabh Tiwari, Kusha Sareen, Lakshya A Agrawal +6
Large language models (LLMs) are trained for downstream tasks by updating their parameters (e.g., via RL). However, updating model parameters forces them to absorb task-specific in…
Delta Fair Sharing: Performance Isolation for Multi-Tenant Storage Systems
Tyler Griggs, Soujanya Ponnapalli, Dev Bali +8
Modern storage systems, often deployed to support multiple tenants in the cloud, must provide performance isolation. Unfortunately, traditional approaches such as fair sharing do n…
LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess
Sai Kolasani, Maxim Saplin, Nicholas Crispino +5
We introduce LLM CHESS, an evaluation framework designed to probe the generalization of reasoning and instruction-following abilities in large language models (LLMs) through extend…
SkyRL-Agent: Efficient RL Training for Multi-turn LLM Agent
Shiyi Cao, Dacheng Li, Fangzhou Zhao +12
We introduce SkyRL-Agent, a framework for efficient, multi-turn, long-horizon agent training and evaluation. It provides efficient asynchronous dispatching, lightweight tool integr…
Barbarians at the Gate: How AI is Upending Systems Research
Audrey Cheng, Shu Liu, Melissa Pan +14
Artificial Intelligence (AI) is starting to transform the research process as we know it by automating the discovery of new solutions. Given a task, the typical AI-driven approach…
Reliable Fine-Grained Evaluation of Natural Language Math Proofs
Wenjie Ma, Andrei Cojocaru, Neel Kolhe +6
Recent advances in large language models (LLMs) for mathematical reasoning have largely focused on tasks with easily verifiable final answers while generating and verifying natural…
vAttention: Verified Sparse Attention
Aditya Desai, Kumar Krishna Agrawal, Shuo Yang +5
State-of-the-art sparse attention methods for reducing decoding latency fall into two main categories: approximate top- (and its extension, top-) and recently introduced samp…
Supporting Our AI Overlords: Redesigning Data Systems to be Agent-First
Shu Liu, Soujanya Ponnapalli, Shreya Shankar +12
Large Language Model (LLM) agents, acting on their users' behalf to manipulate and analyze data, are likely to become the dominant workload for data systems in the future. When wor…
Establishing Best Practices for Building Rigorous Agentic Benchmarks
Yuxuan Zhu, Tengjun Jin, Yada Pruksachatkun +22
Benchmarks are essential for quantitatively tracking progress in AI. As AI agents become increasingly capable, researchers and practitioners have introduced agentic benchmarks to e…
LEANN: A Low-Storage Vector Index
Yichuan Wang, Zhifei Li, Shu Liu +10
Embedding-based vector search underpins many important applications, such as recommendation and retrieval-augmented generation (RAG). It relies on vector indices to enable efficien…
The Cambridge Report on Database Research
Anastasia Ailamaki, Samuel Madden, Daniel Abadi +43
On October 19 and 20, 2023, the authors of this report convened in Cambridge, MA, to discuss the state of the database research field, its recent accomplishments and ongoing challe…
Reasoning Models Can Be Effective Without Thinking
Wenjie Ma, Jingxuan He, Charlie Snell +3
Recent LLMs have significantly improved reasoning capabilities, primarily by including an explicit, lengthy Thinking process as part of generation. In this paper, we question wheth…
Why Do Multi-Agent LLM Systems Fail?
Mert Cemri, Melissa Z. Pan, Shuyi Yang +10
Despite enthusiasm for Multi-Agent LLM Systems (MAS), their performance gains on popular benchmarks are often minimal. This gap highlights a critical need for a principled understa…
Optimizing Model Selection for Compound AI Systems
Lingjiao Chen, Jared Quincy Davis, Boris Hanin +4
Compound AI systems that combine multiple LLM calls, such as self-refine and multi-agent-debate, achieve strong performance on many AI tasks. We address a core question in optimizi…
LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!
Dacheng Li, Shiyi Cao, Tyler Griggs +9
Large reasoning models (LRMs) tackle complex reasoning problems by following long chain-of-thoughts (Long CoT) that incorporate reflection, backtracking, and self-validation. Howev…
BARE: Leveraging Base Language Models for Few-Shot Synthetic Data Generation
Alan Zhu, Parth Asawa, Jared Quincy Davis +5
As the demand for high-quality data in model training grows, researchers and developers are increasingly generating synthetic data to tune and train LLMs. However, current data gen…
Specifications: The missing link to making the development of LLM systems an engineering discipline
Ion Stoica, Matei Zaharia, Joseph Gonzalez +8
Despite the significant strides made by generative AI in just a few short years, its future progress is constrained by the challenge of building modular and robust systems. This ca…
HashAttention: Semantic Sparsity for Faster Inference
Aditya Desai, Shuo Yang, Alejandro Cuadron +3
Leveraging long contexts is crucial for advanced AI systems, but attention computation poses a scalability challenge. While scaled dot-product attention (SDPA) exhibits token spars…
Networks of Networks: Complexity Class Principles Applied to Compound AI Systems Design
Jared Quincy Davis, Boris Hanin, Lingjiao Chen +3
As practitioners seek to surpass the current reliability and quality frontier of monolithic models, Compound AI Systems consisting of many language model inference calls are increa…
Are More LLM Calls All You Need? Towards Scaling Laws of Compound Inference Systems
Lingjiao Chen, Jared Quincy Davis, Boris Hanin +4
Many recent state-of-the-art results in language tasks were achieved using compound systems that perform multiple Language Model (LM) calls and aggregate their responses. However,…
Data Acquisition: A New Frontier in Data-centric AI
Lingjiao Chen, Bilge Acun, Newsha Ardalani +8
As Machine Learning (ML) systems continue to grow, the demand for relevant and comprehensive datasets becomes imperative. There is limited study on the challenges of data acquisiti…
How is ChatGPT's behavior changing over time?
Lingjiao Chen, Matei Zaharia, James Zou
GPT-3.5 and GPT-4 are the two most widely used large language model (LLM) services. However, when and how these models are updated over time is opaque. Here, we evaluate the March…