Gabriele Oliaro

Gabriele Oliaro

CS PhD Student

Carnegie Mellon University

About

I am a 2nd year Ph.D. student in the Computer Science Department at Carnegie Mellon University, where I am fortunate to work with Zhihao Jia as part of the Catalyst Lab and Parallel Data Lab.

I am interested in machine learning systems, parallel computing and distributed systems, with a particular focus on large language models (LLMs).

I also have previous experience in cloud computing and computer networking. Before my PhD, I worked at Whist, a NYC-based startup in the cloud browser space, and did research on serverless computing with Eddie Kohler, computer networking (DTA project) with Minlan Yu, and distributed systems (Ray project) with Ion Stoica.

Download my CV.

Interests
  • Distributed Systems
  • Parallel Computing
  • Machine Learning
  • Networking
Education
  • PhD in Computer Science, 2028

    Carnegie Mellon University

  • MS in Computer Science, 2023

    Tsinghua University

  • BS in Electrical Engineering, 2021

    Harvard University

Recent Publications

Quickly discover relevant content by filtering publications.
FlexLLM: A System for Co-Serving Large Language Model Inference and Parameter-Efficient Finetuning
ArXiv 2024
SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification
ASPLOS 2024
Optimal Kernel Orchestration for Tensor Programs with Korch
ASPLOS 2024
Quantized Side Tuning: Fast and Memory-Efficient Tuning of Quantized Large Language Models
ArXiv 2024
Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems
ArXiv 2023
Direct Telemetry Access
SIGCOMM 2023
Zero-CPU Collection with Direct Telemetry Access
HotNets 2021

Industry Experience

 
 
 
 
 
FlexFlow
Open Source Project Contributor
Sep 2022 – Present Pittsburgh, PA
Lead developer of FlexFlow Serve, an open-source inference system GitHub stars
 
 
 
 
 
Whist Technologies
Software Engineer
Sep 2021 – Aug 2022 New York
Worked in the Systems Engineering Team
 
 
 
 
 
Ray
Open Source Project Contributor
Jun 2020 – Jun 2021 California
Worked on Ray Core and committed to the GitHub repository GitHub stars

Contact

  • goliaro@cs.cmu.edu
  • Computer Science Department, Carnegie Mellon University, Pittsburgh, PA 15213