Search Results for author:
Found 2 papers, 0 papers with code
LoRA-Switch: Boosting the Efficiency of Dynamic LLM Adapters via System-Algorithm Co-design
Recent literature has found that an effective method to customize or further improve large language models (LLMs) is to add dynamic adapters, such as low-rank adapters (LoRA) with Mixture-of-Experts (MoE) structures.
SwapMoE: Serving Off-the-shelf MoE-based Large Language Models with Tunable Memory Budget
Mixture of experts (MoE) is a popular technique to improve capacity of Large Language Models (LLMs) with conditionally-activated parallel experts.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
