Hi I am Haley Li
I currently work on large language model inference optimization at Huawei Canada. Previously, I completed my M.Sc in computer science at the University of British Columbia applying reinforcement learning to load balancing and scheduling for serverless and search engines.
Intelligent Cloud Infrastructure Lab. Large language model inference optimization. MoE-Attention disaggregation. Fault tolerant inference serving. Asynchronous reinforcement fine-tuning for large-scale MoE.
Systopia Lab. Performed research in the intersection of systems and machine learning.
Big Data and Intelligence Platform Lab. Fine-tuning language models for linear programming solver workflows.
Systopia Lab. Performed research in cloud schedulers.
Primarily worked on frontend development on an Electron-based LaTeX editing application.
Machine learning and systems