That paper does a terrible job of making Lucene look useful, though. 10qps from a server with 1TB of RAM is not great (and I know Lucene HNSW can perform better than that in the real world, so I am somewhat mystified that this paper is being pushed by the community).
I know, FWIW, Elasticsearch has been investing a lot in this space lately. It's not perfect, but its bound to get better.