Skip to content
KernelIndex
Search⌘K

Transformers

Hugging Face Transformers · python · Apache-2.0
holds 8 records

Use it

Source available upstream · Apache-2.0View source →

No install recipe recorded for this revision.

interfacepython
Compatibility
measured onNVIDIA A100
declared hardwaredeclared only
architectures—
dtypes

Benchmark evidence

16 measurements across 1 GPU, fastest first.

Operation / workload
Hardware
Latency
Rank
Observed
Fused linear + ORPO lossbf16 · [2, 1024, 4096]
NVIDIA A100
12.9ms
#1 of 2
2024-11-13
Fused linear + ORPO lossbf16 · [4, 1024, 4096]
NVIDIA A100
25.6ms
#1 of 2
2024-11-13
Fused linear + ORPO lossbf16 · [2, 1024, 4096]
NVIDIA A100
39.3ms
#2 of 2
2024-11-13
Fused linear + ORPO lossbf16 · [2, 4096, 4096]
NVIDIA A100
39.6ms
#1 of 2
2024-11-13
Fused linear + ORPO lossbf16 · [8, 1024, 4096]
NVIDIA A100
51.8ms
#1 of 2
2024-11-13
Fused linear + ORPO lossbf16 · [4, 1024, 4096]
NVIDIA A100
77.9ms
#2 of 2
2024-11-13
Fused linear + ORPO lossbf16 · [4, 4096, 4096]
NVIDIA A100
80.0ms
#1 of 2
2024-11-13
Fused linear + ORPO lossbf16 · [16, 1024, 4096]
NVIDIA A100
103.9ms
#1 of 2
2024-11-13
Fused linear + ORPO lossbf16 · [2, 4096, 4096]
NVIDIA A100
120.7ms
#2 of 2
2024-11-13
Fused linear + ORPO lossbf16 · [8, 1024, 4096]
NVIDIA A100
151.6ms
#2 of 2
2024-11-13
Show all 16 measurements ›
Fused linear + ORPO lossbf16 · [8, 4096, 4096]
NVIDIA A100
160.1ms
#1 of 2
2024-11-13
Fused linear + ORPO lossbf16 · [4, 4096, 4096]
NVIDIA A100
241.2ms
#2 of 2
2024-11-13
Fused linear + ORPO lossbf16 · [16, 1024, 4096]
NVIDIA A100
304.5ms
#2 of 2
2024-11-13
Fused linear + ORPO lossbf16 · [16, 4096, 4096]
NVIDIA A100
321.5ms
#1 of 2
2024-11-13
Fused linear + ORPO lossbf16 · [8, 4096, 4096]
NVIDIA A100
492.5ms
#2 of 2
2024-11-13
Fused linear + ORPO lossbf16 · [16, 4096, 4096]
NVIDIA A100
1.00s
#2 of 2
2024-11-13

Reported · How evidence levels are derived →

Source and license

sourceavailable
revision digestsha256:5d3abd82b7390063c125f70bd451418ae67f5557e714afb5271f4cbf00c92703
license declaredApache-2.0
license concludedApache-2.0
imported2026-08-20

Best evidence level for this revision: reported

JSON