diff --git a/docs/npu.md b/docs/npu.md index 6f49e1a70..df513e12e 100644 --- a/docs/npu.md +++ b/docs/npu.md @@ -2430,6 +2430,13 @@ route loads and a captured `--device npu` run stands behind it; the regenerated GGUF-on-NPU forward), while every D3-* pack in this body declares the dense `qwen3_5` family, so the two are not the same answer and the registry keeps them apart. +How a pack's line is marked, as `census_watch.flm_line()` decides it: a class the registry does not map is `!! NEW FLM` +unless `registry/significant.json` reviews it as not-an-alias or `flm_answers.json` answers it (then `. FLM`); a class +mapped for a backend other than `npu` is `!! NPU FLM` unless `flm_answers.json` answers it (then `. NPU FLM`), and +`significant.json` does not quiet it; a family the route serves is `+ FLM`. So a reviewed class that the registry later +maps for hrx only starts alerting again until it gets an answer here (engine#2528: `DFlash2DraftModel`, +`Lfm3ForCausalLM`). + The answers are also machine-readable, in `registry/flm_answers.json`, because CI keeps no watcher state: every scheduled run sees the whole org as new, and before that file each family answered above printed `!! NPU FLM` again and re-filed the census issue the day after it closed (engine#2171; the 2026-11-11 run alerted on 31 packs, every one already