Collection by
4 days ago
4 days ago
-
Efficient Memory Management for Large Language Model Serving with PagedAttention
Paper β’ 2309.06180 β’ Published β’ 25 -
LM-Infinite: Simple On-the-Fly Length Generalization for Large Language Models
Paper β’ 2308.16137 β’ Published β’ 38 -
Scaling Transformer to 1M tokens and beyond with RMT
Paper β’ 2304.11062 β’ Published β’ 2 -
DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models
Paper β’ 2309.14509 β’ Published β’ 16
