Skip to content
KernelIndex
Search⌘K

Transformers

Hugging Face Transformers · python · Apache-2.0

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

18 measurements across 1 GPU, fastest first.

Operation / workload
Hardware
Latency
Rank
Observed
RMSNormbf16 · [2048, 1024]
NVIDIA A100
78.2µs
#2 of 2
2024-09-03
RMSNormbf16 · [2048, 2048]
NVIDIA A100
136.3µs
#2 of 2
2024-09-03
RMSNormbf16 · [2048, 1024]
NVIDIA A100
195.8µs
#2 of 2
2024-09-03
RMSNormbf16 · [2048, 4096]
NVIDIA A100
279.9µs
#2 of 2
2024-09-03
RMSNormbf16 · [2048, 1024]
NVIDIA A100
317.7µs
#2 of 2
2024-09-03
RMSNormbf16 · [2048, 2048]
NVIDIA A100
361.9µs
#2 of 2
2024-09-03
RMSNormbf16 · [2048, 2048]
NVIDIA A100
490.4µs
#2 of 2
2024-09-03
RMSNormbf16 · [2048, 8192]
NVIDIA A100
519.0µs
#2 of 2
2024-09-03
RMSNormbf16 · [2048, 4096]
NVIDIA A100
740.4µs
#2 of 2
2024-09-03
RMSNormbf16 · [2048, 16384]
NVIDIA A100
985.6µs
#2 of 2
2024-09-03
Show all 18 measurements ›
RMSNormbf16 · [2048, 4096]
NVIDIA A100
1.01ms
#2 of 2
2024-09-03
RMSNormbf16 · [2048, 8192]
NVIDIA A100
1.35ms
#2 of 2
2024-09-03
RMSNormbf16 · [2048, 8192]
NVIDIA A100
1.86ms
#2 of 2
2024-09-03
RMSNormbf16 · [2048, 32768]
NVIDIA A100
1.92ms
#2 of 2
2024-09-03
RMSNormbf16 · [2048, 16384]
NVIDIA A100
2.57ms
#2 of 2
2024-09-03
RMSNormbf16 · [2048, 16384]
NVIDIA A100
3.54ms
#2 of 2
2024-09-03
RMSNormbf16 · [2048, 32768]
NVIDIA A100
5.01ms
#2 of 2
2024-09-03
RMSNormbf16 · [2048, 32768]
NVIDIA A100
6.91ms
#2 of 2
2024-09-03

Reported · How evidence levels are derived →

Source and license

sourceavailable
revision digestsha256:d0846f0b6ab4d23bc51fcd7979b189c953df29327453372e7cc66c4809fb8801
license declaredApache-2.0
license concludedApache-2.0
imported2026-08-18

Best evidence level for this revision: reported

JSON