Goal: Decide on an optional Lift Wing caching strategy for model servers
Open, LowestPublic
Actions

Assigned To

Authored By

	calbon
	Oct 4 2023, 3:18 PM

Description

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.

Related Objects
Search...

Status	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

Event Timeline

calbon created this task.Oct 4 2023, 3:18 PM

Restricted Application added a subscriber: Aklapper. · View Herald TranscriptOct 4 2023, 3:18 PM

calbon renamed this task from Decide on an optional Lift Wing caching strategy for model servers to Goal: Decide on an optional Lift Wing caching strategy for model servers.Oct 4 2023, 3:19 PM

elukey added a project: Goal.Oct 9 2023, 3:41 PM

klausman added a subtask: T349180: Discuss caching strategies for Lift Wing.Oct 18 2023, 10:34 AM

Doc created. Two major options.

calbon triaged this task as High priority.Nov 27 2023, 3:56 PM

calbon lowered the priority of this task from High to Medium.

calbon lowered the priority of this task from Medium to Lowest.Dec 20 2023, 3:35 PM

calbon moved this task from Current Quarter Goals to 2023-2024 Q3 Done on the Machine-Learning-Team board.Jan 31 2024, 5:22 PM

klausman closed subtask T349180: Discuss caching strategies for Lift Wing as Resolved.Mar 5 2024, 11:50 AM