kv_inp tensor
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)
kv_inp tensor has 12 facts recorded in Dontopedia across 3 references, with 1 live disagreement.
Mostly:has shape(3), has size(1), is memory bottleneck(1)
Maturity scale
raw canonical shape-checked rule-derived certifiedOther facts (11)
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 |
|---|---|---|
| Has Shape | (B,T,32,768) | [1] |
| Has Shape | (16, 2048, 8, 4, 104) | [2] |
| Has Shape | (16, 2048, 8, 4, 104) | [3] |
| Has Size | 416MB | [2] |
| Is Memory Bottleneck | Cumsum | [2] |
| Rdf:type | Tensor | [3] |
| Has Memory Size | 416000000 | [3] |
| Has Data Type | float32 | [3] |
| Identified As | memory bottleneck | [3] |
| Unavoidable for | cumsum | [3] |
| Dominates | memory pressure | [3] |
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 (3)
ctx:discord/blah/watt-activation/part-203ctx:discord/blah/watt-activation/part-293ctx:discord/blah/watt-activation/291- full textwatt-activation-291text/plain3 KB
doc:agent/watt-activation-291/883c968e-0b03-4e27-aca9-027dfc155696Show excerpt
[2026-03-14 03:41] xenonfun: Why Keeping the Spherical Head Still Makes Sense (performace at 600K parm scale is effectively same as euclidian head) ``` Even if performance is the same, the spherical head is still the better design. Reasons…
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.