3 accepted papers
Low-Rank Adaptation (LoRA) is a popular approach that enables large language models (LLMs) to quickly adapt to domain-specific tasks by adding lightweight trainable adapters. Existing multi-LoRA serving systems typically exploit parameter sharing to serve hundreds of LoRA models with a single base m
Sparse attention can effectively alleviate the significant demands on memory when large language models (LLMs) process long contexts. Existing methods typically apply the same sparse pattern across different attention heads and inputs. However, this uniform approach fails to capture the inherent div…
Pre-trained foundation models, particularly large language models, have achieved remarkable success and led to massive fine-tuned variants. These models are commonly fine-tuned locally and then uploaded by users to cloud platforms such as HuggingFace for secure storage. However, the huge model numbe…