Author	SHA1	Message	Date
Meta Vens	43d05465c3	Research: correct the "MNTP missing" diagnosis; the difference is the chat header ... Appends a dated correction to both probe notes, citing motion-pipeline:finding:cut-vili-cpu-body.s1.ab-premise-inverted. The measurements stand as measured. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-10-23 17:40:09 +02:00
Meta Vens	3faa541ce9	Research: Vili on Yggdrasil CPU (Kimodo torch timings, A/B and Q8 clips vs assembly B, move map) ... Measured on Yggdrasil CPU under other agents' load; Raven untouched. A/B eye-check BVHs and a Blender side-by-side viewer under docs/research/assets/. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-10-23 03:18:57 +02:00
Meta Vens	4a4c8ea5dd	Research: kimodo.cpp probe (Q8 GGML encoder, MNTP adapter missing from Vili's vectors) ... Measured on Yggdrasil CPU; Raven GPU timing deferred (household using the GPU). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-10-23 02:20:44 +02:00
Meta Vens	329de4ea84	Research: community tooling around Kimodo, SOMA and ARDY (facts only) ... Serves the fbx-export and soma-humanoid-avatar cuts and the authoring UX target. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-10-23 01:29:45 +02:00
Meta Vens	96ddec1204	Research: NVIDIA motion generation since Kimodo 6bb5848 (facts only) ... Serves motion-pipeline fork: which motion model and text encoder Vili runs (follow_up kimodo-v1-2). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-10-22 20:27:57 +02:00