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

8 measurements across 1 GPU, fastest first.

Operation / workload
Hardware
Latency
Rank
Observed
Fused linear + cross-entropybf16 · [4096, 4096]
NVIDIA A100
20.9ms
#1 of 2
2024-11-22
Fused linear + cross-entropybf16 · [8192, 4096]
NVIDIA A100
38.0ms
#1 of 2
2024-11-22
Fused linear + cross-entropybf16 · [4096, 4096]
NVIDIA A100
56.0ms
#1 of 2
2024-11-22
Fused linear + cross-entropybf16 · [16384, 4096]
NVIDIA A100
76.4ms
#1 of 2
2024-11-22
Fused linear + cross-entropybf16 · [8192, 4096]
NVIDIA A100
111.5ms
#1 of 2
2024-11-22
Fused linear + cross-entropybf16 · [32768, 4096]
NVIDIA A100
151.9ms
#1 of 2
2024-11-22
Fused linear + cross-entropybf16 · [16384, 4096]
NVIDIA A100
220.8ms
#1 of 2
2024-11-22
Fused linear + cross-entropybf16 · [32768, 4096]
NVIDIA A100
452.5ms
#1 of 2
2024-11-22

Reported · How evidence levels are derived →

Source and license

sourceavailable
revision digestsha256:45096ed5d8a02d4239615c0c5778b4b48ba152f733b71e43fe37a51abcaa1e31
license declaredApache-2.0
license concludedApache-2.0
imported2026-08-20

Best evidence level for this revision: reported

JSON