LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention Paper • 2502.14866 • Published 14 days ago • 12
Wolf: Captioning Everything with a World Summarization Framework Paper • 2407.18908 • Published Jul 26, 2024 • 32
LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models Paper • 2309.12307 • Published Sep 21, 2023 • 88