Examples: query, "exact match", wildcard*, wild?ard, wild*rd
Fuzzy search: cake~ (finds cakes, bake)
Term boost: "red velvet"^4, chocolate^2
Field grouping: tags:(+work -"fun-stuff")
Escaping: Escape characters +-&|!(){}[]^"~*?:\ with \, e.g. \+
Range search: properties.timestamp:[1587729413488 TO *] (inclusive), properties.title:{A TO Z}(excluding A and Z)
Combinations: chocolate AND vanilla, chocolate OR vanilla, (chocolate OR vanilla) NOT "vanilla pudding"
Field search: properties.title:"The Title" AND text
Hello Everyone! I'M Trying To Deploy Online Model With Clearml-Serving. For This Model, There Is A Need To Process Incoming Requests In A Queue Because The Model Inference Requires A Gpu And It Takes About One Minute To Serve One Request, While More Than

Hello everyone! I'm trying to deploy online model with clearml-serving. For this model, there is a need to process incoming requests in a queue because the model inference requires a GPU and it takes about one minute to serve one request, while more than 10 requests can come in simultaneously. How can I in model deployed with clearml-serving set up a limited queue? I couldn't find any information about queues usage for clearml-serving in the documentation.

Posted one month ago
Votes Newest


0 Answers
one month ago
one month ago