Once we have uploaded all draftquality model files to storage, we can create inference services by adding the isvc configurations to the ml-services helmfile then follow the deployment guide found here:
https://wikitech.wikimedia.org/wiki/Machine_Learning/LiftWing/Deploy#How_to_deploy
Description
Description
Details
Details
Subject | Repo | Branch | Lines +/- | |
---|---|---|---|---|
ml-services: add ptwiki draftquality isvc | operations/deployment-charts | master | +2 -0 |
Status | Subtype | Assigned | Task | ||
---|---|---|---|---|---|
Resolved | kevinbazira | T310698 Migrate draftquality models | |||
Resolved | kevinbazira | T310704 Create draftquality inference services |
Event Timeline
Comment Actions
Change 806394 had a related patch set uploaded (by Kevin Bazira; author: Kevin Bazira):
[operations/deployment-charts@master] ml-services: add ptwiki draftquality isvc
Comment Actions
Change 806394 merged by Elukey:
[operations/deployment-charts@master] ml-services: add ptwiki draftquality isvc
Comment Actions
Inference services were created for all the 2 draftquality models and they are all up and running in KServe on both eqiad and codfw.
NAME READY STATUS RESTARTS enwiki-draftquality-predictor-default-rzctc-deployment-7c4nfgjv 3/3 Running 0 ptwiki-draftquality-predictor-default-frwng-deployment-8fd9jwcx 3/3 Running 0