Hi folks!
After upgrading to KServe 0.11 we started noticing a regression in performances, and after a long debugging session we ended up in:
https://github.com/dmlc/xgboost/pull/9651
More context in: T347550
The change was included in xgboost 2.0.1, so I was wondering if knowledge_integrity's xgboost dependency could be upgraded as well or if there are blockers.
| Status | Subtype | Assigned | Task | ||
|---|---|---|---|---|---|
| Resolved | elukey | T337213 Update to KServe 0.11 | |||
| Resolved | achou | T347550 Upgrade Revert Risk Language-agnostic docker images to KServe 0.11 | |||
| Resolved | isarantopoulos | T347551 Upgrade Revert Risk Multilingual docker images to KServe 0.11.2 | |||
| Open | BUG REPORT | None | T349844 Increased latencies with Kserve 0.11.1 (cgroups v2) | ||
| Resolved | MunizaA | T350389 Upgrade xgboost in knowledge_integrity |
Ilias is working in T349844 on a proposal for the upgrade, but if anybody from Research could do it beforehand we'd be grateful :)
Hi, I've opened an MR for dropping support for Python 3.7 in KI since this was already on the roadmap after its EOL in June 2023 and it also helps support this change (xgboost 2.x requires minimum Python 3.8).
Knowledge Integrity v0.5.0 has been released which now depends on xgboost 2.x. Upgrading xgboost also required serializing the classifier with the new version so the version for RevertRiskModel has also been bumped to v3. I've shared the model file with @achou. The SHA512 sum for RevertRiskModel v3 is:
fb6d76b105b7e8198cee47f779c69f1bd85be61075061665bdd0811e8d52e1d4f793dacb4a00fc3776ace8c518f1fa5f653879cec81777854cf235b0483156e7 *revert_risk_language_agnostic_model_v3.pkl
Going to resolve this now but please feel free to reopen if something does not look right!
I verified the sha512 checksum. The model file has been uploaded to Swift:
aikochou@stat1005:~$ s3cmd -c /etc/s3cmd/cfg.d/ml-team.cfg ls s3://wmf-ml-models/revertrisk/language-agnostic/20231117132654/ 2023-11-17 13:26 167741 s3://wmf-ml-models/revertrisk/language-agnostic/20231117132654/model.pkl
The model is also downloadable publicly at https://analytics.wikimedia.org/published/wmf-ml-models/revertrisk/language-agnostic/20231117132654/ (thanks @elukey for creating the script to automate this step; it works like a charm :)