Edward Hu
Principal AI Researcher
Verified Proof of Work Artifacts
2 items catalogedEach artifact below represents an authenticated research publication, production code repository, or technical architectural framework directly authored or co-created by Edward Hu. Every entry undergoes editorial source verification.
LoRA: Low-Rank Adaptation of Large Language Models
Authored the foundational ICLR 2022 paper introducing LoRA, which freezes pre-trained model weights and injects trainable rank decomposition matrices into Transformer attention layers, matching full fine-tuning quality with 3x less GPU VRAM.
Adapting non-attention feed-forward layers yields diminishing returns unless higher rank dimensions are budgeted.
LoRA: Official Parameter-Efficient Open-Source PyTorch Implementation
Created and open-sourced the original PyTorch LoRA package providing drop-in `nn.Linear`, `nn.Embedding`, and `nn.Conv2d` layers with automated weight merging, forming the foundation of modern Hugging Face PEFT.
Dynamic multi-tenant serving requires runtime adapter switching kernels (e.g., S-LoRA/Punica) to avoid memory fragmentation.