Skip to content
KernelIndex
Search⌘K

GEMM n6144 k4096

308 eligible runs
gemm

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

Fastest reported
19.6µsmean · 53% of SOL
GeometricLicense unknown · unknown

Reported evidence · last observed 2026-08-05. 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 · 47 results · last observed 2026-08-21Record history →
#
Implementation
Latency
vs #1
Trust
Observed
1
19.6µs53% SOL
1.00×
Reported · license unknown · no source
2026-08-05

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

no sourcelicense unknownno install recipeRun detail →
2
19.7µs53% SOL
1.00×
Reported · license unknown · no source
2026-08-10

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

no sourcelicense unknownno install recipeRun detail →
3
19.8µs53% SOL
1.01×
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 →
4
19.8µs53% SOL
1.01×
Reported · license unknown · no source
2026-08-08

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

no sourcelicense unknownno install recipeRun detail →
5
19.9µs53% SOL
1.01×
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
20.0µs52% SOL
1.02×
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 →
7
20.1µs52% SOL
1.02×
Reported · license unknown · no source
2026-08-04

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

no sourcelicense unknownno install recipeRun detail →
8
20.1µs52% SOL
1.02×
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 →
9
20.2µs52% SOL
1.03×
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 →
10
20.4µs51% SOL
1.04×
Reported · license unknown · no source
2026-08-01

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

no sourcelicense unknownno install recipeRun detail →
11
20.5µs51% SOL
1.04×
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 →
12
20.5µs51% SOL
1.04×
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 →
13
20.5µs51% SOL
1.04×
Reported · license unknown · no source
2026-08-02

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

no sourcelicense unknownno install recipeRun detail →
14
20.5µs51% 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 →
15
20.5µs51% SOL
1.05×
Reported · license unknown · no source
2026-08-01

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

no sourcelicense unknownno install recipeRun detail →
16
20.6µs51% SOL
1.05×
Reported · license unknown · no source
2026-08-02

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

no sourcelicense unknownno install recipeRun detail →
17
20.6µs51% SOL
1.05×
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
20.7µs51% SOL
1.05×
Reported · license unknown · no source
2026-08-02

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

no sourcelicense unknownno install recipeRun detail →
19
20.8µs51% SOL
1.06×
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 →
20
20.9µs50% SOL
1.06×
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 →
21
20.9µs50% 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 →
22
20.9µs50% SOL
1.07×
Reported · license unknown · no source
2026-08-01

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

no sourcelicense unknownno install recipeRun detail →
23
21.1µs50% SOL
1.08×
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 →
24
21.1µs50% SOL
1.08×
Reported · license unknown · no source
2026-07-20

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

no sourcelicense unknownno install recipeRun detail →
25
21.2µs49% SOL
1.08×
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 →
26
21.4µs49% SOL
1.09×
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 →
27
21.5µs49% SOL
1.09×
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 →
28
21.5µs49% SOL
1.10×
Reported · license unknown · no source
2026-08-19

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

no sourcelicense unknownno install recipeRun detail →
29
21.5µs49% 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 →
30
21.5µs49% SOL
1.10×
Reported · license unknown · no source
2026-08-21

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

no sourcelicense unknownno install recipeRun detail →
31
21.6µs49% 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 →
32
21.6µs49% SOL
1.10×
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 →
33
21.6µs49% SOL
1.10×
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 →
34
21.6µs49% SOL
1.10×
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 →
35
21.7µs49% 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 →
36
21.7µs48% SOL
1.11×
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 →
37
22.0µs48% SOL
1.12×
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 →
38
22.2µs48% SOL
1.13×
Reported · license unknown · no source
2026-07-24

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

no sourcelicense unknownno install recipeRun detail →
39
22.2µs47% SOL
1.13×
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
22.3µs48% SOL
1.13×
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 →
41
22.4µs47% SOL
1.14×
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 →
42
22.7µs46% 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 →
43
24.0µs45% SOL
1.22×
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 →
44
24.2µs44% SOL
1.23×
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 →
45
24.2µs45% SOL
1.24×
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 →
46
25.5µs42% SOL
1.30×
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 →
47
25.6µs42% SOL
1.30×
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 →

Implementations

Implementation
Runtime
Best latency
Evidence
Availability
unknown
19.6µs
1.08×
Reported
license unknown · no source
unknown
19.8µs
1.08×
Reported
license unknown · no source
unknown
19.7µs
1.08×
Reported
license unknown · no source
unknown
21.4µs
1.17×
Reported
license unknown · no source
unknown
19.6µs
1.08×
Reported
license unknown · no source
unknown
19.7µs
1.08×
Reported
license unknown · no source
unknown
19.7µs
1.08×
Reported
license unknown · no source
unknown
19.8µs
1.09×
Reported
license unknown · no source
Show all 70 implementations ›
unknown
20.0µs
1.10×
Reported
license unknown · no source
unknown
21.0µs
1.15×
Reported
license unknown · no source
unknown
21.5µs
1.18×
Reported
license unknown · no source
unknown
22.0µs
1.20×
Reported
license unknown · no source
unknown
21.9µs
1.20×
Reported
license unknown · no source
unknown
22.3µs
1.22×
Reported
license unknown · no source
unknown
22.4µs
1.23×
Reported
license unknown · no source
unknown
19.9µs
1.09×
Reported
license unknown · no source
unknown
20.1µs
1.10×
Reported
license unknown · no source
unknown
20.1µs
1.10×
Reported
license unknown · no source
unknown
20.3µs
1.11×
Reported
license unknown · no source
unknown
20.2µs
1.11×
Reported
license unknown · no source
unknown
20.4µs
1.12×
Reported
license unknown · no source
unknown
20.5µs
1.12×
Reported
license unknown · no source
unknown
20.5µs
1.12×
Reported
license unknown · no source
unknown
20.5µs
1.12×
Reported
license unknown · no source
unknown
20.5µs
1.13×
Reported
license unknown · no source
unknown
20.6µs
1.13×
Reported
license unknown · no source
unknown
20.5µs
1.12×
Reported
license unknown · no source
unknown
20.7µs
1.13×
Reported
license unknown · no source
unknown
20.6µs
1.13×
Reported
license unknown · no source
unknown
20.8µs
1.14×
Reported
license unknown · no source
unknown
20.9µs
1.14×
Reported
license unknown · no source
unknown
20.9µs
1.15×
Reported
license unknown · no source
unknown
20.9µs
1.15×
Reported
license unknown · no source
unknown
21.1µs
1.16×
Reported
license unknown · no source
unknown
21.1µs
1.16×
Reported
license unknown · no source
unknown
21.2µs
1.16×
Reported
license unknown · no source
unknown
21.2µs
1.16×
Reported
license unknown · no source
unknown
21.5µs
1.18×
Reported
license unknown · no source
unknown
21.5µs
1.18×
Reported
license unknown · no source
unknown
21.5µs
1.18×
Reported
license unknown · no source
unknown
21.6µs
1.18×
Reported
license unknown · no source
unknown
21.6µs
1.18×
Reported
license unknown · no source
unknown
21.6µs
1.18×
Reported
license unknown · no source
unknown
21.6µs
1.19×
Reported
license unknown · no source
unknown
21.7µs
1.19×
Reported
license unknown · no source
unknown
21.7µs
1.19×
Reported
license unknown · no source
unknown
22.0µs
1.21×
Reported
license unknown · no source
unknown
22.2µs
1.22×
Reported
license unknown · no source
unknown
22.3µs
1.22×
Reported
license unknown · no source
unknown
22.2µs
1.22×
Reported
license unknown · no source
unknown
22.1µs
1.21×
Reported
license unknown · no source
unknown
23.3µs
1.28×
Reported
license unknown · no source
unknown
22.7µs
1.25×
Reported
license unknown · no source
unknown
24.2µs
1.33×
Reported
license unknown · no source
unknown
24.0µs
1.32×
Reported
license unknown · no source
unknown
24.2µs
1.33×
Reported
license unknown · no source
unknown
24.5µs
1.34×
Reported
license unknown · no source
unknown
24.8µs
1.36×
Reported
license unknown · no source
unknown
25.5µs
1.39×
Reported
license unknown · no source
unknown
25.6µs
1.40×
Reported
license unknown · no source
unknown
28.8µs
1.58×
Reported
license unknown · no source
claude-opus-4-1 / cudad26d88claude-opus-4-1-20250805
cuda
—
—
Apache-2.0 · source
claude-opus-4-1 / triton48d048claude-opus-4-1-20250805
triton
70.4µs
3.86×
Reported
Apache-2.0 · source
cuda
18.3µs
1.00×
Reproduction-ready
Apache-2.0 · source
triton
43.0µs
2.36×
Reported
Apache-2.0 · source
gpt-5 / cudab704b7gpt-5-2025-08-07
cuda
—
—
Apache-2.0 · source
gpt-5_triton_793693gpt-5-2025-08-07
triton
88.2µs
4.83×
Reported
Apache-2.0 · source
cuda
—
—
Apache-2.0 · source
triton
69.9µs
3.83×
Reported
Apache-2.0 · source
torch / matmul3b6488FlashInfer-Bench baselines
python
18.5µs
1.01×
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 = 6144
determinismunspecified
constraintsNo mutation or aliasing
Identity
aliasgemm_n6144_k4096modelllama-3-1-8bsha256ae26b1af2cf6…

Also indexed as 010-gemm-n6144-k4096 · reviewed as the same computation; every definition's cohorts are shown here, ranked separately.

Sources: FlashInfer-Bench (2025-10-16) · Apache-2.0 · NVIDIA SOL-ExecBench (2026-08-21)last observed 2026-08-21How records are decidedJSON