Skip to content
KernelIndex
Search⌘K

Adaptive LayerNorm continuous with modulation

30 eligible runs
rmsnorm

AdaLayerNormContinuous normalization with adaptive scale and shift modulation conditioned on timestep embeddings. Computes layer normalization, projects temb through a linear layer to get scale/shift, then modulates: normalized * (1 + scale) + shift.

Fastest reported
21.1µsmean · 81% of SOL
RIAC as wellLicense unknown · unknown

Reported evidence · last observed 2026-08-23. Reported by source; not independently reproduced. No public source. License unknown.

No public sourceRun detail →

Current records

Workloadsuite of 16 cases · mean latencyinner_dim = 2432 · inner_dim_x2 = 486416 cases

Not measured on H100 for this workload. Challenges →

Source-native comparison · GPU NVIDIA B200 · Workload suite of 16 cases · mean latency · Protocol SOL-ExecBench evaluation stack v1.1 · mean · 19 results · last observed 2026-08-23Record history →
#
Implementation
Latency
vs #1
Trust
Observed
1
21.1µs81% SOL
1.00×
Reported · license unknown · no source
2026-08-23

Measured exactly what you asked. Reported by source; not independently reproduced.

no sourcelicense unknownno install recipeRun detail →
2
22.0µs80% SOL
1.04×
Reported · license unknown · no source
2026-07-10

Measured exactly what you asked. Reported by source; not independently reproduced.

no sourcelicense unknownno install recipeRun detail →
3
23.6µs79% SOL
1.12×
Reported · license unknown · no source
2026-07-10

Measured exactly what you asked. Reported by source; not independently reproduced.

no sourcelicense unknownno install recipeRun detail →
4
23.9µs79% SOL
1.13×
Reported · license unknown · no source
2026-07-13

Measured exactly what you asked. Reported by source; not independently reproduced.

no sourcelicense unknownno install recipeRun detail →
5
24.4µs78% SOL
1.15×
Reported · license unknown · no source
2026-08-06

Measured exactly what you asked. Reported by source; not independently reproduced.

no sourcelicense unknownno install recipeRun detail →
6
24.4µs78% SOL
1.15×
Reported · license unknown · no source
2026-07-10

Measured exactly what you asked. Reported by source; not independently reproduced.

no sourcelicense unknownno install recipeRun detail →
7
25.7µs77% SOL
1.22×
Reported · license unknown · no source
2026-08-17

Measured exactly what you asked. Reported by source; not independently reproduced.

no sourcelicense unknownno install recipeRun detail →
8
25.9µs77% SOL
1.23×
Reported · license unknown · no source
2026-08-17

Measured exactly what you asked. Reported by source; not independently reproduced.

no sourcelicense unknownno install recipeRun detail →
9
26.8µs76% SOL
1.27×
Reported · license unknown · no source
2026-08-15

Measured exactly what you asked. Reported by source; not independently reproduced.

no sourcelicense unknownno install recipeRun detail →
10
27.5µs76% SOL
1.30×
Reported · license unknown · no source
2026-07-12

Measured exactly what you asked. Reported by source; not independently reproduced.

no sourcelicense unknownno install recipeRun detail →
11
28.2µs75% SOL
1.33×
Reported · license unknown · no source
2026-08-14

Measured exactly what you asked. Reported by source; not independently reproduced.

no sourcelicense unknownno install recipeRun detail →
12
28.3µs75% SOL
1.34×
Reported · license unknown · no source
2026-07-28

Measured exactly what you asked. Reported by source; not independently reproduced.

no sourcelicense unknownno install recipeRun detail →
13
28.4µs75% SOL
1.34×
Reported · license unknown · no source
2026-07-10

Measured exactly what you asked. Reported by source; not independently reproduced.

no sourcelicense unknownno install recipeRun detail →
14
30.3µs74% SOL
1.43×
Reported · license unknown · no source
2026-07-10

Measured exactly what you asked. Reported by source; not independently reproduced.

no sourcelicense unknownno install recipeRun detail →
15
30.6µs73% SOL
1.45×
Reported · license unknown · no source
2026-07-16

Measured exactly what you asked. Reported by source; not independently reproduced.

no sourcelicense unknownno install recipeRun detail →
16
31.8µs73% SOL
1.51×
Reported · license unknown · no source
2026-07-10

Measured exactly what you asked. Reported by source; not independently reproduced.

no sourcelicense unknownno install recipeRun detail →
17
32.1µs72% SOL
1.52×
Reported · license unknown · no source
2026-07-10

Measured exactly what you asked. Reported by source; not independently reproduced.

no sourcelicense unknownno install recipeRun detail →
18
47.0µs63% SOL
2.22×
Reported · license unknown · no source
2026-07-10

Measured exactly what you asked. Reported by source; not independently reproduced.

no sourcelicense unknownno install recipeRun detail →
19
80.2µs50% SOL
3.80×
Reported · license unknown · no source
2026-07-10

Measured exactly what you asked. Reported by source; not independently reproduced.

no sourcelicense unknownno install recipeRun detail →

Implementations

Implementation
Runtime
Best latency
Evidence
Availability
unknown
21.1µs
1.00×
Reported
license unknown · no source
unknown
21.7µs
1.03×
Reported
license unknown · no source
unknown
23.6µs
1.12×
Reported
license unknown · no source
unknown
23.9µs
1.13×
Reported
license unknown · no source
unknown
24.4µs
1.15×
Reported
license unknown · no source
unknown
25.7µs
1.22×
Reported
license unknown · no source
unknown
28.2µs
1.33×
Reported
license unknown · no source
unknown
28.3µs
1.34×
Reported
license unknown · no source
Show all 30 implementations ›
unknown
30.6µs
1.45×
Reported
license unknown · no source
unknown
31.7µs
1.50×
Reported
license unknown · no source
unknown
47.0µs
2.22×
Reported
license unknown · no source
unknown
47.4µs
2.24×
Reported
license unknown · no source
unknown
48.7µs
2.30×
Reported
license unknown · no source
unknown
24.4µs
1.15×
Reported
license unknown · no source
unknown
24.4µs
1.16×
Reported
license unknown · no source
unknown
25.9µs
1.23×
Reported
license unknown · no source
unknown
26.8µs
1.27×
Reported
license unknown · no source
unknown
27.5µs
1.30×
Reported
license unknown · no source
unknown
28.4µs
1.34×
Reported
license unknown · no source
unknown
28.6µs
1.35×
Reported
license unknown · no source
unknown
30.3µs
1.43×
Reported
license unknown · no source
unknown
31.8µs
1.50×
Reported
license unknown · no source
unknown
31.8µs
1.51×
Reported
license unknown · no source
unknown
32.1µs
1.52×
Reported
license unknown · no source
unknown
47.0µs
2.22×
Reported
license unknown · no source
unknown
49.2µs
2.33×
Reported
license unknown · no source
unknown
80.2µs
3.80×
Reported
license unknown · no source
unknown
22.0µs
1.04×
Reported
license unknown · no source
unknown
22.2µs
1.05×
Reported
license unknown · no source
unknown
23.6µs
1.12×
Reported
license unknown · no source

Semantics

Inputs and outputs
hidden_statesfp32 [batch_size, seq_len, inner_dim]
tembfp32 [batch_size, inner_dim]
linear_weightfp32 [inner_dim_x2, inner_dim]
linear_biasfp32 [inner_dim_x2]
epsfp32 scalar
outputfp32 [batch_size, seq_len, inner_dim]
Axes and behavior
seq_lenvariable
inner_dimconstant = 2432
batch_sizevariable
inner_dim_x2inner_dim_x2 = inner_dim * 2
determinismunspecified
constraintsNo mutation or aliasing
Identity
alias080_adaptive_layernorm_continuous_with_modulationmodelstable-diffusion-3-5-largesha2566ad052d55659…
Sources: NVIDIA SOL-ExecBench (2026-08-23)last observed 2026-08-23How records are decidedJSON