[04:19:39] 06Machine-Learning-Team (Q1 FY2026-27): Host a tool-server on LiftWing - https://phabricator.wikimedia.org/T436892 (10kevinbazira) 03NEW [04:31:22] 06Machine-Learning-Team (Q1 FY2026-27): Explore LLM tool calling support in our vLLM-based inference services - https://phabricator.wikimedia.org/T434274#12284064 (10kevinbazira) @isarantopoulos as discussed in yesterday's [ML technical meeting](https://docs.google.com/document/d/1Cymx4tSe3Xh11A2Nhce_mzxa9RSwAHQ... [07:37:54] (03PS1) 10Bartosz Wójtowicz: tts-section-generator: add TTS V1 article dataset script [machinelearning/liftwing/inference-services] - 10https://gerrit.wikimedia.org/r/1334627 (https://phabricator.wikimedia.org/T432128) [07:59:09] (03CR) 10Kevin Bazira: [C:03+1] tts-section-generator: add TTS V1 article dataset script [machinelearning/liftwing/inference-services] - 10https://gerrit.wikimedia.org/r/1334627 (https://phabricator.wikimedia.org/T432128) (owner: 10Bartosz Wójtowicz) [08:02:19] (03CR) 10Kevin Bazira: [C:03+1] "thank you for working on this. as discussed we'll clean it up as we continue using it : )" [machinelearning/liftwing/inference-services] - 10https://gerrit.wikimedia.org/r/1334627 (https://phabricator.wikimedia.org/T432128) (owner: 10Bartosz Wójtowicz) [08:07:17] (03CR) 10Bartosz Wójtowicz: [C:03+2] tts-section-generator: add TTS V1 article dataset script [machinelearning/liftwing/inference-services] - 10https://gerrit.wikimedia.org/r/1334627 (https://phabricator.wikimedia.org/T432128) (owner: 10Bartosz Wójtowicz) [08:13:37] (03Merged) 10jenkins-bot: tts-section-generator: add TTS V1 article dataset script [machinelearning/liftwing/inference-services] - 10https://gerrit.wikimedia.org/r/1334627 (https://phabricator.wikimedia.org/T432128) (owner: 10Bartosz Wójtowicz) [08:21:29] (03CR) 10DCausse: Add semantic_highlighting (031 comment) [machinelearning/liftwing/inference-services] - 10https://gerrit.wikimedia.org/r/1322788 (https://phabricator.wikimedia.org/T433872) (owner: 10DCausse) [10:06:06] 06Machine-Learning-Team (Q1 FY2026-27), 06Data-Platform-SRE (2026-08-28 - 2026-09-18), 07Essential-Work: Support GPU Partition specification in deployments - https://phabricator.wikimedia.org/T424923#12284819 (10achou) Thanks @DPogorzelski-WMF, this is really helpful. That clears up the infra-side questions... [11:46:27] 10Lift-Wing, 06Machine-Learning-Team (Q1 FY2026-27), 13Patch-For-Review: Host Qwen3.8-27B-FP8 on LiftWing - https://phabricator.wikimedia.org/T436644#12285315 (10gkyziridis) === Update === The `Qwen3.8-27B-FP8` model is deployed under experimental namespace in `ml-serve-eqiad`. The [[ https://gerrit.wikimedi... [11:59:02] 06Machine-Learning-Team (Q1 FY2026-27), 06Data-Platform-SRE: [draft] ml-serve-eqiad: Repartition two MI300X nodes from CPX (24GB) to DPX (96GB) partitions - https://phabricator.wikimedia.org/T436928 (10isarantopoulos) 03NEW [12:01:08] 10Lift-Wing, 06Machine-Learning-Team (Q1 FY2026-27), 13Patch-For-Review: Host Qwen3.8-27B-FP8 on LiftWing - https://phabricator.wikimedia.org/T436644#12285369 (10gkyziridis) [12:06:45] 06Machine-Learning-Team (Q1 FY2026-27), 06Data-Platform-SRE (2026-08-28 - 2026-09-18), 07Essential-Work: Support GPU Partition specification in deployments - https://phabricator.wikimedia.org/T424923#12285385 (10Gehel) #machine-learning-team will give the list of partitions / nodes to repartition [12:14:09] 06Machine-Learning-Team (Q1 FY2026-27), 06Data-Platform-SRE: Extend KServe's LLMInferenceService by Gateway API Inference Extension and KEDA autoscaling - https://phabricator.wikimedia.org/T436650#12285430 (10isarantopoulos) [13:14:21] 06Machine-Learning-Team (Q1 FY2026-27), 06Traffic: CDN caching request for TTS v1 audio files - https://phabricator.wikimedia.org/T434046#12285798 (10BTullis) As I understand it (from T435952 and T436758) , the back-end service hosting these files for the period of the experiment will be: [[https://wikitech.wi... [13:57:57] 10Lift-Wing, 06Machine-Learning-Team, 07Essential-Work: [LLM] Lift Wing load testing - https://phabricator.wikimedia.org/T377225#12286045 (10gkyziridis) Hey, just a short question regarding LiftWing LLM testing: I see that the current task is an old one (Oct 15 2024) and it refers to https://gitlab.wikimedia... [14:59:47] 06Machine-Learning-Team (Q1 FY2026-27), 06Data-Platform-SRE: ml-serve-eqiad: Repartition two MI300X nodes from CPX (24GB) to DPX (96GB) partitions - https://phabricator.wikimedia.org/T436928#12286359 (10isarantopoulos) [15:00:08] 06Machine-Learning-Team (Q1 FY2026-27), 06Data-Platform-SRE: ml-serve-eqiad: Repartition two MI300X nodes from 24GB to 96GB partitions - https://phabricator.wikimedia.org/T436928#12286363 (10isarantopoulos) [15:37:22] 06Machine-Learning-Team (Q1 FY2026-27): Explore LLM tool calling support in our vLLM-based inference services - https://phabricator.wikimedia.org/T434274#12286558 (10kevinbazira) >>! In T434274#12284064, @kevinbazira wrote: > @isarantopoulos as discussed in yesterday's [ML technical meeting](https://docs.google.... [15:42:25] (03PS1) 10Kevin Bazira: tool_server: add tool-server exposing REST and MCP [machinelearning/liftwing/inference-services] - 10https://gerrit.wikimedia.org/r/1334976 (https://phabricator.wikimedia.org/T436892)