kv_inp
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)
kv_inp has 7 facts recorded in Dontopedia across 4 references.
Mostly:must match shape for compatibility(1), exists in both models(1), has tensor shape(1)
Maturity scale
raw canonical shape-checked rule-derived certifiedOther facts (6)
The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.
| Predicate | Value | Ref |
|---|---|---|
| Must Match Shape for Compatibility | Spectralattention | [1] |
| Exists in Both Models | true | [2] |
| Has Tensor Shape | (B, T, 32, 768) | [3] |
| Is Larger Than | Spectral Attention Equivalent | [3] |
| Has Element Count Per Forward | 100M | [3] |
| Rdf:type | Parameter | [4] |
Timeline
Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.
References (4)
ctx:discord/blah/watt-activation/part-204ctx:discord/blah/watt-activation/part-202ctx:discord/blah/watt-activation/part-203ctx:discord/blah/watt-activation/158- full textwatt-activation-158text/plain2 KB
doc:agent/watt-activation-158/746cbfb1-750c-4df5-ae90-78f0235bc1e9Show excerpt
[2026-03-09 16:27] xenonfun: ⏺ For batch prefill, each attention class's forward() currently runs _gated_cumsum over the full sequence and returns output — but throws away the final recurrent state. The step() method maintains that state …
See also
Keep researching
Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.