User story: As the ML team, I want have a clear optional Lift Wing caching strategy for our model servers, so that we can optimize model response times and reduce latency in model predictions.
Description
Description
Status | Subtype | Assigned | Task | ||
---|---|---|---|---|---|
Open | klausman | T348155 Goal: Decide on an optional Lift Wing caching strategy for model servers | |||
Resolved | klausman | T349180 Discuss caching strategies for Lift Wing | |||
Open | klausman | T356256 Epic: Implement prototype inference service that uses Cassandra for request caching | |||
Resolved | klausman | T360428 Add Istio (and related) config to allow LW isvcs to talk to ML Cassandra machines |