Writing in the Margins: Better Inference Pattern for Long Context Retrieval
Paper
•
2408.14906
•
Published
•
138
Long context
-
-
DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
Paper • 2410.10819 • Published • 6 -
LLMtimesMapReduce: Simplified Long-Sequence Processing using Large Language Models
Paper • 2410.09342 • Published • 38 -
PDFTriage: Question Answering over Long, Structured Documents
Paper • 2309.08872 • Published • 53