Dontopedia

GroupedLinear

From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)

GroupedLinear has 17 facts recorded in Dontopedia across 3 references, with 1 live disagreement.

17 facts·13 predicates·3 sources·1 in dispute

Mostly:has time complexity(2), rdf:type(2), uses method(1)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (3)

Other subjects in dontopedia point AT this entity as a value. These are inverse relationships — e.g. "X motherOf this subject" — and answer questions the forward facts can't. Grouped by predicate.

comparesModelsCompares Models(1)

comparesSubject1Compares Subject1(1)

includesIncludes(1)

Other facts (15)

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.

15 facts
PredicateValueRef
Has Time ComplexityO(T log T · d)[1]
Has Time ComplexityO(T log T · d)[3]
Rdf:typeModel Architecture[2]
Rdf:typeAlgorithm Variant[3]
Uses MethodFft G=1[1]
Has Op Count~290M ops[1]
Uses Implementation ApproachFft[2]
Has Group Size1[2]
Has Fft Channels Per Head64[2]
Has Computational Work290000000[2]
Work Calculation Expression64 × 12 × 3 × 8192 × 13[2]
Requires Memory Bufferspadded 2T buffers[2]
Has Fft Size8192[2]
Has Method BasisFFT g=1[3]
Has Approximate Operation Count290000000[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.

usesMethodblah/watt-activation/part-102
ex:fft-g=1
hasOpCountblah/watt-activation/part-102
~290M ops
hasTimeComplexityblah/watt-activation/part-102
O(T log T · d)
labelblah/watt-activation/101
GroupedLinear
typeblah/watt-activation/101
ex:ModelArchitecture
usesImplementationApproachblah/watt-activation/101
ex:FFT
hasGroupSizeblah/watt-activation/101
1
hasFftChannelsPerHeadblah/watt-activation/101
64
hasComputationalWorkblah/watt-activation/101
290000000
workCalculationExpressionblah/watt-activation/101
64 × 12 × 3 × 8192 × 13
requiresMemoryBuffersblah/watt-activation/101
padded 2T buffers
hasFftSizeblah/watt-activation/101
8192
typeblah/watt-activation/102
ex:AlgorithmVariant
labelblah/watt-activation/102
GroupedLinear
hasMethodBasisblah/watt-activation/102
FFT g=1
hasTimeComplexityblah/watt-activation/102
O(T log T · d)
hasApproximateOperationCountblah/watt-activation/102
290000000

References (3)

3 references
  1. [1]Part 1023 facts
    ctx:discord/blah/watt-activation/part-102
  2. [2]1019 facts
    ctx:discord/blah/watt-activation/101
    • full textwatt-activation-101
      text/plain3 KBdoc:agent/watt-activation-101/6f90e9c2-2d77-484f-96fd-98a89c99440a
      Show excerpt
      [2026-03-08 18:08] xenonfun: ### Concrete comparison at T=4096, H=12, d_h=64: ResonanceV2 (cumsum, K=8 bands): Work: 12 × 8 × 4096 × 64 = 25M multiply-adds Kernel launches: ~K cumsums = 8 Metal kernels Memory: O(T · H · K ·
  3. [3]1025 facts
    ctx:discord/blah/watt-activation/102
    • full textwatt-activation-102
      text/plain3 KBdoc:agent/watt-activation-102/197f49fd-089d-42f2-ae23-c3d99df52ba0
      Show excerpt
      [2026-03-08 18:20] xenonfun: easier to read and consolidated doc: https://github.com/MonumentalSystems/CustomModelMLXConversion/blob/62d270249a911f6ab482a2d89000a4b47c51363d/HARMONIC_PORT.md [2026-03-08 18:21] xenonfun: ``` cumsum-based

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.