Skip to content
KernelIndex
Search⌘K

Transformers

Hugging Face Transformers · python · Apache-2.0
holds 2 records

Use it

Source available upstream · Apache-2.0View source →

No install recipe recorded for this revision.

interfacepython
Compatibility
measured onNVIDIA GeForce RTX 4090, NVIDIA A100
declared hardwaredeclared only
architectures—
dtypes

Benchmark evidence

42 measurements across 2 GPUs, fastest first.

Operation / workload
Hardware
Latency
Rank
Observed
GeGLU MLPbf16 · [2, 1024, 2048]
NVIDIA GeForce RTX 4090
674.3µs
#2 of 4
2025-11-11
GeGLU MLPbf16 · [2, 1024, 2048]
NVIDIA GeForce RTX 4090
743.4µs
#4 of 4
2025-11-11
GeGLU MLPbf16 · [2, 2048, 2048]
NVIDIA GeForce RTX 4090
1.41ms
#3 of 4
2025-11-11
GeGLU MLPbf16 · [2, 2048, 2048]
NVIDIA GeForce RTX 4090
1.42ms
#4 of 4
2025-11-11
GeGLU MLPbf16 · [2, 1024, 2048]
NVIDIA GeForce RTX 4090
1.55ms
#2 of 4
2025-11-11
GeGLU MLPbf16 · [2, 1024, 2048]
NVIDIA GeForce RTX 4090
2.34ms
#2 of 4
2025-11-11
GeGLU MLPbf16 · [2, 1024, 2048]
NVIDIA GeForce RTX 4090
2.68ms
#4 of 4
2025-11-11
GeGLU MLPbf16 · [2, 4096, 2048]
NVIDIA GeForce RTX 4090
2.82ms
#3 of 4
2025-11-11
GeGLU MLPbf16 · [2, 4096, 2048]
NVIDIA GeForce RTX 4090
2.89ms
#4 of 4
2025-11-11
GeGLU MLPbf16 · [2, 2048, 2048]
NVIDIA GeForce RTX 4090
3.17ms
#2 of 4
2025-11-11
Show all 42 measurements ›
GeGLU MLPbf16 · [2, 1024, 2048]
NVIDIA GeForce RTX 4090
3.42ms
#4 of 4
2025-11-11
GeGLU MLPbf16 · [2, 2048, 2048]
NVIDIA GeForce RTX 4090
4.73ms
#4 of 4
2025-11-11
GeGLU MLPbf16 · [2, 2048, 2048]
NVIDIA GeForce RTX 4090
4.76ms
#2 of 4
2025-11-11
GeGLU MLPbf16 · [2, 8192, 2048]
NVIDIA GeForce RTX 4090
5.70ms
#2 of 4
2025-11-11
GeGLU MLPbf16 · [2, 8192, 2048]
NVIDIA GeForce RTX 4090
6.09ms
#4 of 4
2025-11-11
GeGLU MLPbf16 · [2, 2048, 2048]
NVIDIA GeForce RTX 4090
6.16ms
#4 of 4
2025-11-11
GeGLU MLPbf16 · [2, 4096, 2048]
NVIDIA GeForce RTX 4090
6.26ms
#2 of 4
2025-11-11
GeGLU MLPbf16 · [2, 4096, 2048]
NVIDIA GeForce RTX 4090
9.08ms
#4 of 4
2025-11-11
GeGLU MLPbf16 · [8, 1024, 4096]
NVIDIA A100
9.26ms
#1 of 2
2024-09-03
GeGLU MLPbf16 · [2, 4096, 2048]
NVIDIA GeForce RTX 4090
9.42ms
#2 of 4
2025-11-11
GeGLU MLPbf16 · [2, 16384, 2048]
NVIDIA GeForce RTX 4090
11.3ms
#2 of 4
2025-11-11
GeGLU MLPbf16 · [2, 4096, 2048]
NVIDIA GeForce RTX 4090
11.9ms
#4 of 4
2025-11-11
GeGLU MLPbf16 · [2, 8192, 2048]
NVIDIA GeForce RTX 4090
12.0ms
#2 of 4
2025-11-11
GeGLU MLPbf16 · [2, 16384, 2048]
NVIDIA GeForce RTX 4090
12.4ms
#4 of 4
2025-11-11
GeGLU MLPbf16 · [2, 8192, 2048]
NVIDIA GeForce RTX 4090
17.6ms
#2 of 4
2025-11-11
GeGLU MLPbf16 · [8, 2048, 4096]
NVIDIA A100
18.1ms
#2 of 2
2024-09-03
GeGLU MLPbf16 · [8, 1024, 4096]
NVIDIA A100
18.5ms
#2 of 2
2024-09-03
GeGLU MLPbf16 · [2, 8192, 2048]
NVIDIA GeForce RTX 4090
18.6ms
#4 of 4
2025-11-11
GeGLU MLPbf16 · [2, 16384, 2048]
NVIDIA GeForce RTX 4090
23.8ms
#2 of 4
2025-11-11
GeGLU MLPbf16 · [2, 8192, 2048]
NVIDIA GeForce RTX 4090
24.7ms
#4 of 4
2025-11-11
GeGLU MLPbf16 · [8, 1024, 4096]
NVIDIA A100
27.9ms
#1 of 2
2024-09-03
GeGLU MLPbf16 · [2, 16384, 2048]
NVIDIA GeForce RTX 4090
35.1ms
#2 of 4
2025-11-11
GeGLU MLPbf16 · [8, 2048, 4096]
NVIDIA A100
36.0ms
#2 of 2
2024-09-03
GeGLU MLPbf16 · [8, 4096, 4096]
NVIDIA A100
36.4ms
#2 of 2
2024-09-03
GeGLU MLPbf16 · [2, 16384, 2048]
NVIDIA GeForce RTX 4090
37.1ms
#4 of 4
2025-11-11
GeGLU MLPbf16 · [2, 16384, 2048]
NVIDIA GeForce RTX 4090
49.5ms
#4 of 4
2025-11-11
GeGLU MLPbf16 · [8, 2048, 4096]
NVIDIA A100
54.5ms
#2 of 2
2024-09-03
GeGLU MLPbf16 · [8, 8192, 4096]
NVIDIA A100
72.7ms
#2 of 2
2024-09-03
GeGLU MLPbf16 · [8, 4096, 4096]
NVIDIA A100
72.9ms
#2 of 2
2024-09-03
GeGLU MLPbf16 · [8, 4096, 4096]
NVIDIA A100
111.0ms
#2 of 2
2024-09-03
GeGLU MLPbf16 · [8, 8192, 4096]
NVIDIA A100
144.2ms
#2 of 2
2024-09-03
GeGLU MLPbf16 · [8, 8192, 4096]
NVIDIA A100
220.9ms
#2 of 2
2024-09-03

Reported · How evidence levels are derived →

Source and license

sourceavailable
revision digestsha256:d12c674a0643ab8fef38f7997fd47abbc4f9018f1da04629789cd5fd11fad7b4
license declaredApache-2.0
license concludedApache-2.0
imported2026-08-18

Best evidence level for this revision: reported

JSON