Skip to content
KernelIndex
Search⌘K

Transformers

Hugging Face Transformers · python · Apache-2.0
holds 4 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

8 measurements across 1 GPU, fastest first.

Operation / workload
Hardware
Latency
Rank
Observed
Fused linear + SimPO lossbf16 · [2, 1024, 4096]
NVIDIA A100
14.5ms
#1 of 2
2024-11-15
Fused linear + SimPO lossbf16 · [4, 1024, 4096]
NVIDIA A100
28.8ms
#1 of 2
2024-11-15
Fused linear + SimPO lossbf16 · [2, 1024, 4096]
NVIDIA A100
39.8ms
#2 of 2
2024-11-15
Fused linear + SimPO lossbf16 · [8, 1024, 4096]
NVIDIA A100
52.6ms
#1 of 2
2024-11-15
Fused linear + SimPO lossbf16 · [4, 1024, 4096]
NVIDIA A100
77.2ms
#2 of 2
2024-11-15
Fused linear + SimPO lossbf16 · [16, 1024, 4096]
NVIDIA A100
104.4ms
#1 of 2
2024-11-15
Fused linear + SimPO lossbf16 · [8, 1024, 4096]
NVIDIA A100
153.7ms
#2 of 2
2024-11-15
Fused linear + SimPO lossbf16 · [16, 1024, 4096]
NVIDIA A100
307.7ms
#2 of 2
2024-11-15

Reported · How evidence levels are derived →

Source and license

sourceavailable
revision digestsha256:b798ab4ce55be614863feffb05aba75acd6bb6428fb4f55f8a361042d746b162
license declaredApache-2.0
license concludedApache-2.0
imported2026-08-20

Best evidence level for this revision: reported

JSON