ruv 92d433523d bench: deployed quantized accuracy + QAT for micro edge model ... int8 PTQ lossless (74.70%, 73.5KB); int4 naive PTQ drops below SOTA (70.21%) but QAT recovers to 74.46% (36.7KB) - still beats MultiFormer. A SOTA-beating WiFi-pose model genuinely runs in ~37KB int4 (QAT) / 73KB int8. Distillation negative noted. Co-Authored-By: claude-flow <ruv@ruv.net>		2026-05-31 01:23:30 -04:00
..
homecore-vs-home-assistant.md	bench: HOMECORE vs Home Assistant — measured perf + capability matrix	2026-05-30 23:41:15 -04:00
person-count-cog.md	docs(bench): append v0.0.2 section to person-count benchmark log	2026-05-21 19:47:55 -04:00
pose-estimation-cog.md	docs: repoint #640 references to #645 (original deleted, replaced) (#646)	2026-05-19 17:18:05 -04:00
wifi-pose-efficiency-frontier.md	bench: deployed quantized accuracy + QAT for micro edge model	2026-05-31 01:23:30 -04:00