[07:49:44] good morning folks [07:50:43] this morning I was wondering if we should start tracking all the users of ORES in a task [07:50:52] for a variety of reasons: [07:51:01] 1) ease of migration to lift wing when ready [07:51:09] 2) figure out what functionalities are used [07:51:18] 3) possibly get a sign-in for early adopters [08:12:59] 10Lift-Wing: Integrate cert-manager/issuer in ml-serve clusters - https://phabricator.wikimedia.org/T298976 (10elukey) ` NAMESPACE NAME READY STATUS RESTARTS AGE cert-manager cert-manager-5f788b6dbb-sxz28... [08:49:53] -- [08:49:59] cert-manager is up in eqiad! [09:04:42] Noice [11:34:16] * elukey lunch! [15:48:44] o/ [15:49:01] elukey: nice work on cert-manager \o/ [15:49:56] thanksss [15:50:08] I have a couple of code reviews to merge to generate the discovery cert [15:50:13] deploying them now [15:50:14] let's see [16:03:19] the new tls secret is now in istio-system! [16:03:27] now the last bit is to switch the istio's config [16:03:51] morning all! [16:03:58] cert-manager! [16:07:09] morning chrisalbon [16:07:32] elukey: will we need to use cert-manager in the ml-sandbox? [16:07:32] morning all, my hellish week continues [16:07:59] accraze: in theory no, it is just a convenient way to provision certs for us [16:08:07] okok [16:34:25] worked!! [16:38:04] niiiiiice [16:41:18] now the next steps are: [16:41:28] 1) create a new intermediate CA only for k8s ml-serve [16:41:59] 2) move kserve to it [16:43:15] 3) move the istio egress gateway's cert to it [16:43:26] for 2) I mean the cert used by the webhook [16:43:34] after that we'll be completely on cert-manager [16:43:38] and off the puppet CA [16:48:28] awesome! [16:49:32] now that I think about it, the api gateway needs to trust the Root PKI [16:49:38] will check if it does [17:23:29] 10Lift-Wing, 10Platform Team Initiatives (API Gateway): Update the API-Gateway k8s config to trust the Root PKI CA - https://phabricator.wikimedia.org/T299550 (10elukey) [17:23:32] created --^ [18:16:19] 10Lift-Wing, 10Machine-Learning-Team, 10Patch-For-Review: Integrate cert-manager/issuer in ml-serve clusters - https://phabricator.wikimedia.org/T298976 (10elukey) [18:16:38] 10Lift-Wing, 10artificial-intelligence, 10editquality-modeling, 10revscoring, 10Machine-Learning-Team (Active Tasks): Create migration plan for editquality models from ORES to Lift Wing - https://phabricator.wikimedia.org/T284689 (10calbon) 05Open→03Resolved [18:19:36] 10Lift-Wing, 10ML-Governance, 10Machine-Learning-Team (Active Tasks): Outlinks model card - https://phabricator.wikimedia.org/T287527 (10calbon) @Htriedman lets talk about this next meeting [18:20:40] 10artificial-intelligence, 10Documentation, 10Machine-Learning-Team (Active Tasks): Experiment with on-wiki model documentation - https://phabricator.wikimedia.org/T276398 (10calbon) 05Open→03Resolved [18:20:44] 10Lift-Wing, 10Machine-Learning-Team, 10ORES, 10artificial-intelligence, 10Documentation: Model Reporting - https://phabricator.wikimedia.org/T276397 (10calbon) [18:23:05] 10artificial-intelligence, 10revscoring, 10Machine-Learning-Team (Active Tasks), 10Patch-For-Review: Move CJK segmentation features to a branch and revert revscoring - https://phabricator.wikimedia.org/T287021 (10calbon) 05Open→03Resolved a:03calbon [18:30:52] 10Lift-Wing, 10Machine-Learning-Team (Active Tasks), 10Patch-For-Review: Integrate cert-manager/issuer in ml-serve clusters - https://phabricator.wikimedia.org/T298976 (10elukey) [18:31:18] 10Lift-Wing, 10Machine-Learning-Team (Active Tasks), 10Patch-For-Review: Integrate cert-manager/issuer in ml-serve clusters - https://phabricator.wikimedia.org/T298976 (10elukey) a:03elukey [18:31:35] 10Lift-Wing, 10Machine-Learning-Team (Active Tasks): Load test the Lift Wing cluster - https://phabricator.wikimedia.org/T296173 (10elukey) a:03elukey [18:31:53] 10Lift-Wing, 10Machine-Learning-Team (Active Tasks): Add an envoy proxy sidecar to Kserve inference pods - https://phabricator.wikimedia.org/T294414 (10elukey) a:03elukey [18:37:08] 10Lift-Wing, 10ML-Governance, 10Machine-Learning-Team (Active Tasks): Outlinks model card - https://phabricator.wikimedia.org/T287527 (10Htriedman) @calbon sounds good — I'm also in the middle of putting the information spread across all the outlinks-model-related pages into my model card content v0.2 doc. T... [19:01:05] * elukey afk! [19:49:22] 10Machine-Learning-Team, 10ORES, 10good first task: Improve Czech Language assets - https://phabricator.wikimedia.org/T223383 (10dgsahethi) Heyy I worked on this issue but for Hindi language and created a PR for the same, can you please review it? [[ https://github.com/wikimedia/revscoring/pull/512 | https:... [19:54:09] 10Machine-Learning-Team, 10ORES, 10good first task: Improve Czech Language assets - https://phabricator.wikimedia.org/T223383 (10Aklapper) @dgsahethi: Thanks! This ticket is about Czech language. Please create a separate Phab ticket for Hindi, if not existing yet. Thanks. [19:57:06] 10Machine-Learning-Team, 10ORES, 10good first task: Improve Czech Language assets - https://phabricator.wikimedia.org/T223383 (10dgsahethi) Ohh, will do that! Also, wanted to ask if there is a dedicated IRC for this project on Slack or anything other than that? [20:07:23] 10Machine-Learning-Team, 10ORES, 10good first task: Improving Hindi Language Assets - https://phabricator.wikimedia.org/T299577 (10dgsahethi) [20:08:34] 10Machine-Learning-Team, 10ORES, 10good first task: Improving Hindi Language Assets - https://phabricator.wikimedia.org/T299577 (10dgsahethi) Created a PR for the same [[ https://github.com/wikimedia/revscoring/pull/512 | https://github.com/wikimedia/revscoring/pull/512 ]] [20:11:47] 10Machine-Learning-Team, 10ORES, 10Patch-For-Review, 10good first task: Improving Hindi Language Assets - https://phabricator.wikimedia.org/T299577 (10Aklapper) [20:19:10] MIC FIXED! [20:19:11] klondsfgkl;'jnds;kljng [20:19:16] one problem down [20:19:18] Sorry again all [21:51:29] 10Lift-Wing, 10Machine-Learning-Team (Active Tasks), 10Release Pipeline (Blubber): Inference Service pipeline intermittent failures - https://phabricator.wikimedia.org/T298995 (10ACraze) Ok I think all images that need to be updated have been updated. Going to mark this as RESOLVED. [21:51:49] 10Lift-Wing, 10Machine-Learning-Team (Active Tasks), 10Release Pipeline (Blubber): Inference Service pipeline intermittent failures - https://phabricator.wikimedia.org/T298995 (10ACraze) 05Open→03Resolved a:03ACraze [22:08:08] 10Lift-Wing, 10Machine-Learning-Team (Active Tasks): Load test the Lift Wing cluster - https://phabricator.wikimedia.org/T296173 (10ACraze) @elukey i've been reading the kserve docs (https://kserve.github.io/website/master/modelserving/v1beta1/custom/custom_model/#parallel-inference) and I think we shpould tu...