Regarding building time, did you configure a SerialMergeScheduler?
Otherwise merges run in separate threads, which would explain the speedup
as adding vectors to the graph gets more and more expensive as the size of
the graph increases.
Le mer. 11 oct. 2023, 05:07, Patrick Zhai a écrit :
> Hi fo
Hi folks,
I was running the HNSW benchmark today and found some weird results. Want
to share it here and see whether people have any ideas.
The set up is:
the 384 dimension vector that's available in luceneutil, 100k documents.
And lucene main branch.
max_conn=64, fanout=0, beam_width=250
I first
