Jaewon Lee
Source-listed: Meta
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Optimizing Deployment Configurations for LLM InferenceSaved credit: Contributor · 2026Explore people connected to this work →
- Scaling Multi-Node Mixture-of-Experts Inference Using Expert Activation PatternsSaved credit: Contributor · 2026Explore people connected to this work →
- The Llama 3 Herd of ModelsSaved credit: Contributor · 2024Explore people connected to this work →
- Building a Performance Model for Deep Learning Recommendation Model Training on GPUsSaved credit: Contributor · 2022Explore people connected to this work →
- First-Generation Inference Accelerator Deployment at FacebookSaved credit: Contributor · 2021Explore people connected to this work →