Skip to content
KernelIndex
Search⌘K

GEMM n4096 k4096

407 eligible runs
gemm

General matrix multiply (GEMM) C = A @ B.T. Captured from Llama 3.1 8B attn.o_proj.

Fastest reported
14.3µsmean · 56% of SOL
Amir M. Mir | SF TensorLicense unknown · unknown

Reported evidence · last observed 2026-08-03. Reported by source; not independently reproduced. No public source. License unknown.

No public sourceRun detail →

Current records

Source-native comparison · GPU NVIDIA B200 · Workload suite of 43 cases · mean latency · Protocol SOL-ExecBench evaluation stack v1.1 · mean · 51 results · last observed 2026-08-24Record history →
#
Implementation
Latency
vs #1
Trust
Observed
1
14.3µs56% SOL
1.00×
Reported · license unknown · no source
2026-08-03

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

no sourcelicense unknownno install recipeRun detail →
2
15.0µs54% SOL
1.05×
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 →
3
15.2µs54% SOL
1.06×
Reported · license unknown · no source
2026-08-03

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

no sourcelicense unknownno install recipeRun detail →
4
15.2µs53% SOL
1.07×
Reported · license unknown · no source
2026-07-31

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

no sourcelicense unknownno install recipeRun detail →
5
15.2µs54% SOL
1.07×
Reported · license unknown · no source
2026-07-29

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

no sourcelicense unknownno install recipeRun detail →
6
15.3µs53% SOL
1.07×
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 →
7
15.3µs53% SOL
1.07×
Reported · license unknown · no source
2026-07-30

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

no sourcelicense unknownno install recipeRun detail →
8
15.4µs53% SOL
1.08×
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 →
9
15.5µs52% SOL
1.09×
Reported · license unknown · no source
2026-07-27

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

no sourcelicense unknownno install recipeRun detail →
10
15.5µs52% SOL
1.09×
Reported · license unknown · no source
2026-08-24

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

no sourcelicense unknownno install recipeRun detail →
10=
15.5µs52% SOL
1.09×
Reported · license unknown · no source
2026-08-20

Measured exactly what you asked; tied ranks share a number. Reported by source; not independently reproduced.

no sourcelicense unknownno install recipeRun detail →
10=
15.5µs52% SOL
1.09×
Reported · license unknown · no source
2026-08-05

Measured exactly what you asked; tied ranks share a number. Reported by source; not independently reproduced.

no sourcelicense unknownno install recipeRun detail →
11
15.6µs52% SOL
1.09×
Reported · license unknown · no source
2026-08-03

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

no sourcelicense unknownno install recipeRun detail →
12
15.6µs52% SOL
1.09×
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
15.6µs52% SOL
1.09×
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
15.7µs52% SOL
1.10×
Reported · license unknown · no source
2026-07-30

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

no sourcelicense unknownno install recipeRun detail →
15
15.7µs52% SOL
1.10×
Reported · license unknown · no source
2026-07-29

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

no sourcelicense unknownno install recipeRun detail →
16
15.9µs51% SOL
1.11×
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
15.9µs51% SOL
1.11×
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 →
18
15.9µs51% SOL
1.12×
Reported · license unknown · no source
2026-07-18

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

no sourcelicense unknownno install recipeRun detail →
19
16.0µs51% SOL
1.12×
Reported · license unknown · no source
2026-07-30

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

no sourcelicense unknownno install recipeRun detail →
20
16.1µs51% SOL
1.13×
Reported · license unknown · no source
2026-08-13

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

no sourcelicense unknownno install recipeRun detail →
21
16.1µs51% SOL
1.13×
Reported · license unknown · no source
2026-07-25

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

no sourcelicense unknownno install recipeRun detail →
22
16.3µs50% SOL
1.14×
Reported · license unknown · no source
2026-07-30

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

no sourcelicense unknownno install recipeRun detail →
23
16.4µs50% SOL
1.15×
Reported · license unknown · no source
2026-07-25

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

no sourcelicense unknownno install recipeRun detail →
24
16.4µs50% SOL
1.15×
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 →
25
16.5µs50% SOL
1.15×
Reported · license unknown · no source
2026-07-23

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

no sourcelicense unknownno install recipeRun detail →
26
16.5µs50% SOL
1.15×
Reported · license unknown · no source
2026-07-21

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

no sourcelicense unknownno install recipeRun detail →
27
16.5µs50% SOL
1.16×
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 →
28
16.5µs50% SOL
1.16×
Reported · license unknown · no source
2026-07-23

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

no sourcelicense unknownno install recipeRun detail →
29
16.7µs49% SOL
1.17×
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 →
30
16.7µs50% SOL
1.17×
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 →
31
17.1µs48% SOL
1.20×
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 →
32
17.1µs48% SOL
1.20×
Reported · license unknown · no source
2026-08-13

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

no sourcelicense unknownno install recipeRun detail →
33
17.2µs48% SOL
1.20×
Reported · license unknown · no source
2026-08-13

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

no sourcelicense unknownno install recipeRun detail →
34
17.2µs48% SOL
1.20×
Reported · license unknown · no source
2026-07-19

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

no sourcelicense unknownno install recipeRun detail →
35
17.3µs48% SOL
1.21×
Reported · license unknown · no source
2026-07-19

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

no sourcelicense unknownno install recipeRun detail →
36
17.4µs48% SOL
1.22×
Reported · license unknown · no source
2026-07-19

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

no sourcelicense unknownno install recipeRun detail →
37
17.4µs48% SOL
1.22×
Reported · license unknown · no source
2026-07-15

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

no sourcelicense unknownno install recipeRun detail →
38
17.4µs48% SOL
1.22×
Reported · license unknown · no source
2026-07-19

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

no sourcelicense unknownno install recipeRun detail →
39
17.4µs48% SOL
1.22×
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 →
40
17.6µs47% SOL
1.23×
Reported · license unknown · no source
2026-07-21

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

no sourcelicense unknownno install recipeRun detail →
41
17.6µs47% SOL
1.23×
Reported · license unknown · no source
2026-07-19

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

no sourcelicense unknownno install recipeRun detail →
42
18.0µs46% SOL
1.26×
Reported · license unknown · no source
2026-07-25

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

no sourcelicense unknownno install recipeRun detail →
43
18.0µs47% SOL
1.26×
Reported · license unknown · no source
2026-07-19

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

no sourcelicense unknownno install recipeRun detail →
44
18.1µs46% SOL
1.27×
Reported · license unknown · no source
2026-07-21

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

no sourcelicense unknownno install recipeRun detail →
45
18.1µs46% SOL
1.27×
Reported · license unknown · no source
2026-07-21

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

no sourcelicense unknownno install recipeRun detail →
46
18.1µs46% SOL
1.27×
Reported · license unknown · no source
2026-07-15

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

no sourcelicense unknownno install recipeRun detail →
47
18.5µs45% SOL
1.30×
Reported · license unknown · no source
2026-07-25

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

no sourcelicense unknownno install recipeRun detail →
48
18.8µs45% SOL
1.32×
Reported · license unknown · no source
2026-07-19

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

no sourcelicense unknownno install recipeRun detail →
49
19.4µs45% SOL
1.36×
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
16.3µs
1.14×
Reported
license unknown · no source
unknown
16.4µs
1.15×
Reported
license unknown · no source
unknown
16.4µs
1.15×
Reported
license unknown · no source
unknown
16.3µs
1.14×
Reported
license unknown · no source
unknown
15.4µs
1.08×
Reported
license unknown · no source
unknown
15.4µs
1.08×
Reported
license unknown · no source
unknown
15.5µs
1.09×
Reported
license unknown · no source
unknown
15.5µs
1.09×
Reported
license unknown · no source
Show all 84 implementations ›
unknown
15.5µs
1.09×
Reported
license unknown · no source
unknown
15.6µs
1.09×
Reported
license unknown · no source
unknown
14.3µs
1.00×
Reported
license unknown · no source
unknown
15.2µs
1.07×
Reported
license unknown · no source
unknown
15.2µs
1.06×
Reported
license unknown · no source
unknown
15.9µs
1.12×
Reported
license unknown · no source
unknown
15.5µs
1.09×
Reported
license unknown · no source
unknown
15.6µs
1.09×
Reported
license unknown · no source
unknown
16.4µs
1.15×
Reported
license unknown · no source
unknown
16.1µs
1.13×
Reported
license unknown · no source
unknown
15.0µs
1.05×
Reported
license unknown · no source
unknown
15.2µs
1.06×
Reported
license unknown · no source
unknown
15.3µs
1.07×
Reported
license unknown · no source
unknown
15.3µs
1.07×
Reported
license unknown · no source
unknown
15.4µs
1.08×
Reported
license unknown · no source
unknown
15.7µs
1.10×
Reported
license unknown · no source
unknown
16.4µs
1.15×
Reported
license unknown · no source
unknown
16.5µs
1.15×
Reported
license unknown · no source
unknown
16.7µs
1.17×
Reported
license unknown · no source
unknown
16.7µs
1.17×
Reported
license unknown · no source
unknown
17.2µs
1.20×
Reported
license unknown · no source
unknown
15.2µs
1.07×
Reported
license unknown · no source
unknown
15.4µs
1.08×
Reported
license unknown · no source
unknown
15.3µs
1.07×
Reported
license unknown · no source
unknown
15.6µs
1.09×
Reported
license unknown · no source
unknown
15.7µs
1.10×
Reported
license unknown · no source
unknown
16.0µs
1.12×
Reported
license unknown · no source
unknown
15.9µs
1.11×
Reported
license unknown · no source
unknown
15.9µs
1.11×
Reported
license unknown · no source
unknown
16.0µs
1.12×
Reported
license unknown · no source
unknown
15.9µs
1.11×
Reported
license unknown · no source
unknown
16.1µs
1.13×
Reported
license unknown · no source
unknown
16.5µs
1.15×
Reported
license unknown · no source
unknown
16.5µs
1.16×
Reported
license unknown · no source
unknown
16.5µs
1.16×
Reported
license unknown · no source
unknown
17.2µs
1.20×
Reported
license unknown · no source
unknown
17.1µs
1.20×
Reported
license unknown · no source
unknown
17.1µs
1.20×
Reported
license unknown · no source
unknown
17.2µs
1.20×
Reported
license unknown · no source
unknown
17.2µs
1.20×
Reported
license unknown · no source
unknown
17.2µs
1.20×
Reported
license unknown · no source
unknown
17.2µs
1.20×
Reported
license unknown · no source
unknown
17.3µs
1.21×
Reported
license unknown · no source
unknown
17.4µs
1.22×
Reported
license unknown · no source
unknown
17.4µs
1.22×
Reported
license unknown · no source
unknown
17.4µs
1.22×
Reported
license unknown · no source
unknown
17.4µs
1.22×
Reported
license unknown · no source
unknown
17.4µs
1.22×
Reported
license unknown · no source
unknown
17.5µs
1.22×
Reported
license unknown · no source
unknown
17.5µs
1.23×
Reported
license unknown · no source
unknown
17.6µs
1.24×
Reported
license unknown · no source
unknown
17.6µs
1.23×
Reported
license unknown · no source
unknown
17.6µs
1.23×
Reported
license unknown · no source
unknown
17.8µs
1.25×
Reported
license unknown · no source
unknown
18.0µs
1.26×
Reported
license unknown · no source
unknown
18.0µs
1.26×
Reported
license unknown · no source
unknown
18.1µs
1.27×
Reported
license unknown · no source
unknown
18.1µs
1.27×
Reported
license unknown · no source
unknown
18.1µs
1.27×
Reported
license unknown · no source
unknown
18.4µs
1.29×
Reported
license unknown · no source
unknown
18.4µs
1.29×
Reported
license unknown · no source
unknown
18.5µs
1.30×
Reported
license unknown · no source
unknown
19.4µs
1.36×
Reported
license unknown · no source
unknown
18.8µs
1.32×
Reported
license unknown · no source
unknown
19.5µs
1.37×
Reported
license unknown · no source
unknown
19.8µs
1.39×
Reported
license unknown · no source
unknown
20.8µs
1.46×
Reported
license unknown · no source
claude-opus-4-1 / cuda1970e7claude-opus-4-1-20250805
cuda
279.7µs
19.59×
Reproduction-ready
Apache-2.0 · source
claude-opus-4-1 / tritond18c66claude-opus-4-1-20250805
triton
68.7µs
4.81×
Reported
Apache-2.0 · source
cuda
15.8µs
1.10×
Reproduction-ready
Apache-2.0 · source
triton
45.1µs
3.16×
Reported
Apache-2.0 · source
gpt-5 / cuda5c1f52gpt-5-2025-08-07
cuda
484.8µs
33.95×
Reproduction-ready
Apache-2.0 · source
gpt-5 / triton14f133gpt-5-2025-08-07
triton
32.6µs
2.29×
Reported
Apache-2.0 · source
cuda
—
—
Apache-2.0 · source
triton
103.6µs
7.26×
Reported
Apache-2.0 · source
torch / matmul0d13dfFlashInfer-Bench baselines
python
15.6µs
1.10×
Reported
Apache-2.0 · source

Semantics

Inputs and outputs
afp16 [m, k]
bfp16 [n, k]
cfp16 [m, n]
Axes and behavior
kconstant = 4096
mvariable
nconstant = 4096
determinismunspecified
constraintsNo mutation or aliasing
Identity
alias007_gemm_n4096_k4096sha2567cb6f2f5e32b…

Also indexed as gemm-n4096-k4096 · reviewed as the same computation; every definition's cohorts are shown here, ranked separately.

Sources: NVIDIA SOL-ExecBench (2026-08-24) · FlashInfer-Bench (2025-10-16) · Apache-2.0last observed 2026-08-24How records are decidedJSON