[07:40:01] <wikibugs>	 06Machine-Learning-Team: Semantic Search - Embeddings Service for MVP - https://phabricator.wikimedia.org/T412338 (10OKarakaya-WMF) 03NEW
[07:46:57] <wikibugs>	 06Machine-Learning-Team: Semantic Search - Embeddings Service for MVP - https://phabricator.wikimedia.org/T412338#11450286 (10OKarakaya-WMF)
[07:55:18] <wikibugs>	 06Machine-Learning-Team: Semantic Search - Embeddings Service for MVP - https://phabricator.wikimedia.org/T412338#11450291 (10OKarakaya-WMF)
[09:05:31] <wikibugs>	 06Machine-Learning-Team: Semantic Search - Embeddings Service for MVP - https://phabricator.wikimedia.org/T412338#11450467 (10OKarakaya-WMF) Below I share how long it will take to generate embeddings with different set ups and I compare two models: model_name = "Qwen/Qwen3-Embedding-0.6B" - float16, all chars 20...
[09:07:06] <wikibugs>	 06Machine-Learning-Team: Semantic Search - Embeddings Service for MVP - https://phabricator.wikimedia.org/T412338#11450477 (10OKarakaya-WMF)
[10:29:16] <wikibugs>	 06Machine-Learning-Team: Install AMD GPU + torch version of ML Labs machines - https://phabricator.wikimedia.org/T412357 (10gkyziridis) 03NEW
[10:30:12] <wikibugs>	 06Machine-Learning-Team: Install AMD GPU + torch version of ML Labs machines - https://phabricator.wikimedia.org/T412357#11450770 (10gkyziridis)
[10:31:01] <wikibugs>	 06Machine-Learning-Team: Install AMD GPU + torch version of ML Labs machines - https://phabricator.wikimedia.org/T412357#11450774 (10gkyziridis)
[10:33:10] <wikibugs>	 06Machine-Learning-Team: Install AMD GPU + torch version of ML Labs machines - https://phabricator.wikimedia.org/T412357#11450798 (10gkyziridis)
[10:36:59] <wikibugs>	 06Machine-Learning-Team: Install AMD GPU + torch version of ML Labs machines - https://phabricator.wikimedia.org/T412357#11450800 (10gkyziridis)
[10:37:15] <wikibugs>	 06Machine-Learning-Team: Install AMD GPU + torch version of ML Labs machines - https://phabricator.wikimedia.org/T412357#11450802 (10gkyziridis)
[10:44:50] <wikibugs>	 06Machine-Learning-Team, 07Essential-Work: Upgrade AMD GPU + torch version of ML Labs machines - https://phabricator.wikimedia.org/T410663#11450824 (10gkyziridis) >>! In T410663#11447291, @Isaac wrote: >> Nevertheless, this combination of versions seems to fix the issue using the GPU image, so your curiosity i...
[10:45:28] <wikibugs>	 06Machine-Learning-Team: Install AMD GPU + torch version of ML Labs machines - https://phabricator.wikimedia.org/T412357#11450826 (10gkyziridis)
[10:45:58] <wikibugs>	 06Machine-Learning-Team: Install AMD GPU + torch version of ML Labs machines - https://phabricator.wikimedia.org/T412357#11450827 (10gkyziridis)
[11:38:29] <wikibugs>	 06Machine-Learning-Team: Install AMD GPU + torch version of ML Labs machines - https://phabricator.wikimedia.org/T412357#11451015 (10DPogorzelski-WMF) a:05DPogorzelski-WMF→03klausman
[13:45:13] <wikibugs>	 06Machine-Learning-Team: Article Summary Generation and Evaluation Pipeline using vLLM image - https://phabricator.wikimedia.org/T395246#11451555 (10mfossati) 05Open→03Invalid Thank you ML folks for your work! We're decommissioning the `ArticleSummaries` MediaWiki extension in {T411558} and {T411560}, so...
[15:32:07] <wikibugs>	 07artificial-intelligence, 06cloud-services-team: Supporting AI, LLM, and data models on WMCS - https://phabricator.wikimedia.org/T336905#11451872 (10Alaexis) Speaking of use cases, there are quite a few tools here https://en.wikipedia.org/wiki/Wikipedia:WikiProject_AI_Tools#Projects. For now they require API...
[16:08:34] <wikibugs>	 07artificial-intelligence, 06cloud-services-team: Supporting AI, LLM, and data models on WMCS - https://phabricator.wikimedia.org/T336905#11451993 (10Zache) Apertus is under OSI-compatible licence (Apache 2.0), multilingual and training process should be reproducible.  It should be also reasonable good.  - htt...
[19:04:34] <wikibugs>	 07artificial-intelligence, 06cloud-services-team: Supporting AI, LLM, and data models on WMCS - https://phabricator.wikimedia.org/T336905#11452620 (10Sj) And we are making Apertus and Olmo-Think and other fully public models available via API for free (though with rate limits to prevent saturation) vua the Pub...
[19:10:33] <wikibugs>	 (03CR) 10Sbisson: [C:04-2] "Good to go AFTER the corresponding cx server patch has been deployed." [research/recommendation-api] - 10https://gerrit.wikimedia.org/r/1217170 (owner: 10Nik Gkountas)
[20:27:16] <wikibugs>	 07artificial-intelligence, 06cloud-services-team: Supporting AI, LLM, and data models on WMCS - https://phabricator.wikimedia.org/T336905#11452862 (10Alaexis) >>! In T336905#11452620, @Sj wrote: > And we are making Apertus and Olmo-Think and other fully public models available via API for free (though with rat...