[FEA] `raft-ann-bench.run` should distinguish the output from different search modes
fy opened this issue · comments
fy commented
Is your feature request related to a problem? Please describe.
Currently raft-ann-bench.run
does not distinguish the output from different search modes (latency
or throughtput
). As a result, the result file may be overwritten when we run raft-ann-bench.run
in different search mods.
Describe the solution you'd like
Encode the search mode in the file name. E.g. hnswlib,base,k10,bs1,latency.json
.