Spectral Throughput Measurement
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-07-01.)
Spectral Throughput Measurement has 7 facts recorded in Dontopedia across 1 reference.
7 facts·7 predicates·1 sources
Mostly:approximation strength(1), is approximate(1), has unit(1)
Maturity scale
raw canonical shape-checked rule-derived certifiedApproximation StrengthapproximationStrength
- approximate[1]sourceall time · 019a8f6a D43b 40ba Afc1 247f4b73c3a5
Is ApproximateisApproximate
- true[1]sourceall time · 019a8f6a D43b 40ba Afc1 247f4b73c3a5
Has UnithasUnit
- tok/s[1]sourceall time · 019a8f6a D43b 40ba Afc1 247f4b73c3a5
Measured ValuemeasuredValue
- 400[1]sourceall time · 019a8f6a D43b 40ba Afc1 247f4b73c3a5
Measured formeasuredFor
Has Normalized UnithasNormalizedUnit
- Token Per Second[1]all time · 019a8f6a D43b 40ba Afc1 247f4b73c3a5
Rdf:typerdf:type
- Throughput Measurement[1]all time · 019a8f6a D43b 40ba Afc1 247f4b73c3a5
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.
—
approximationStrengthdocument/019a8f6a-d43b-40ba-afc1-247f4b73c3a5
approximate
—
hasNormalizedUnitdocument/019a8f6a-d43b-40ba-afc1-247f4b73c3a5
ex:token-per-second
—
hasUnitdocument/019a8f6a-d43b-40ba-afc1-247f4b73c3a5
tok/s
—
isApproximatedocument/019a8f6a-d43b-40ba-afc1-247f4b73c3a5
true
—
measuredFordocument/019a8f6a-d43b-40ba-afc1-247f4b73c3a5
ex:spectral
—
measuredValuedocument/019a8f6a-d43b-40ba-afc1-247f4b73c3a5
400
—
typedocument/019a8f6a-d43b-40ba-afc1-247f4b73c3a5
ex:throughput-measurement
References (1)
1 references
- [1]xenonfun: well not that much speed up 46K now peak, think its memory bound already. 8K voc7 factscustom
ctx:claims/document/019a8f6a-d43b-40ba-afc1-247f4b73c3a5- full textxenonfun: well not that much speed up 46K now peak, think its memory bound already. 8K voctext/plain680 B
discord:msg/a3126764-fdd1-42f8-9653-a5170ea5bdefShow excerpt
xenonfun: well not that much speed up 46K now peak, think its memory bound already. 8K vocab is signifigantly worse output at same training but makes sense, model was too lopsided with that much embeddings, but at 100K it did observe intere…
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.