Open benwtrent opened 4 weeks ago
In newer versions of Elasticsearch, we have an optimized ARM implementation for int8_hnsw vectors.
However, we are not using the the off-heap optimized scorer for int8_flat, we should try to do this if possible.
int8_flat
This is only applicable after our upgrade to Lucene 9.11
Pinging @elastic/es-search (Team:Search)
Description
In newer versions of Elasticsearch, we have an optimized ARM implementation for int8_hnsw vectors.
However, we are not using the the off-heap optimized scorer for
int8_flat
, we should try to do this if possible.This is only applicable after our upgrade to Lucene 9.11