hyperloglog

A technical blog post that explores sorting, hashing, and sketching algorithms on a dataset of 370,103 English words, measuring time and memory costs, with a focus on practical implementations like binary search, quicksort, and HyperLogLog.

Introduces a model-side aggregation interface using compact HyperLogLog sketches to maintain set-based aggregation states for long-context language models, achieving 99.2% accuracy on benchmark tasks and eliminating the need for external execution cycles.