[06:05:22] <wikibugs>	 (03CR) 10Kevin Bazira: "Pausing work on using `cirrusdoc` until we know the outcome of next week's meeting with the Search team:" [machinelearning/liftwing/inference-services] - 10https://gerrit.wikimedia.org/r/1119370 (https://phabricator.wikimedia.org/T385970) (owner: 10Kevin Bazira)
[08:10:49] <isaranto>	 Wasuze otya o/
[08:32:30] <georgekyz>	 good morning o/
[08:38:57] <isaranto>	 \o
[08:50:44] <kevinbazira>	 o/ kaliméra :)
[08:52:13] <isaranto>	 kalimera Kevin!
[10:50:15] <wikibugs>	 06Machine-Learning-Team: [LLM] ML-lab benchmarking - https://phabricator.wikimedia.org/T382343#10552027 (10gkyziridis) Thanks for your time @achou and @MunizaA but I am still having the same issue, which probably has to do with `typing_extensions`. I used `conda env` I used the `--user` flag to `pip install llmp...
[11:02:53] <wikibugs>	 06Machine-Learning-Team: [LLM] ML-lab benchmarking - https://phabricator.wikimedia.org/T382343#10552096 (10MunizaA) @gkyziridis One thing you could try is with your `PYTHONPATH` set to `"$(conda info --base)/envs/llenv/lib/python3.11/site-packages:/srv/pytorch-rocm/venv/lib/python3.11/site-packages`, install `ty...
[12:57:42] <wikibugs>	 06Machine-Learning-Team: [LLM] ML-lab benchmarking - https://phabricator.wikimedia.org/T382343#10552327 (10gkyziridis) Thank you @MunizaA for your time, that fixes the issue.  I think `llmperf` does not recognise the `gptqmodel`, it tries to use `auto-gptq` same as in the `optimum-benchmark` repo discussed in: T...
[13:41:35] <elukey>	 hey folks!
[13:41:59] <elukey>	 if you want to merge/deploy https://gerrit.wikimedia.org/r/c/operations/deployment-charts/+/1117939 to staging (basically all namespaces) feel free to
[13:43:58] <elukey>	 it doesn't change much, we already set that option via pod security policy (that will be removed)
[13:44:10] <elukey>	 otherwise I'll do it next week :)
[13:54:31] <wikibugs>	 06Machine-Learning-Team: [LLM] ML-lab benchmarking - https://phabricator.wikimedia.org/T382343#10552448 (10MunizaA) >>! In T382343#10552327, @gkyziridis wrote: > I think `llmperf` does not recognise the `gptqmodel`, it tries to use `auto-gptq` same as in the `optimum-benchmark` repo discussed in: T382343#1054861...
[14:21:33] <isaranto>	 o/ elukey will start deploying this today and will report back. Thanks!
[15:26:12] <wikibugs>	 06Machine-Learning-Team: [LLM] ML-lab benchmarking - https://phabricator.wikimedia.org/T382343#10552751 (10gkyziridis) Thank you so much @MunizaA for your help. I finally made it to work. Much appreciated!!!
[15:50:11] <chrisalbon>	 Good morning all
[15:51:05] <isaranto>	 Hola Chris
[17:32:48] <isaranto>	 going afk folks, have a nice weekend!
[18:26:26] <wikibugs>	 10Lift-Wing, 06Machine-Learning-Team, 07OKR-Work, 13Patch-For-Review: Update the article-country isvc to use Wikilinks for predictions - https://phabricator.wikimedia.org/T385970#10553381 (10dcausse) @Isaac the weight disappeared in your second tsv file, should I assume that all the predictions have to be...
[19:00:16] <wikibugs>	 10Lift-Wing, 06Machine-Learning-Team, 07OKR-Work, 13Patch-For-Review: Update the article-country isvc to use Wikilinks for predictions - https://phabricator.wikimedia.org/T385970#10553426 (10Isaac) @dcausse whoops - apologies that got lost in the format change but now fixed! Many of them are 1.0 but not al...