Skip to content
KernelIndex
Search⌘K
Sign in

Transformers

Hugging Face Transformers · python · Apache-2.0
holds 7 records

Use it

Source available upstream · Apache-2.0View source →

No install recipe recorded for this revision.

interfacepython
Compatibility
measured onNVIDIA H100
declared hardwaredeclared only
architectures—
dtypes

Benchmark evidence

24 measurements across 1 GPU, fastest first.

Operation / workload
Hardware
Latency
Rank
Observed
Llama 4 rotary position embeddingbf16 · [1, 2048, 8, 16]
NVIDIA H100
37.6µs
#1 of 2
2025-08-07
Run →
Llama 4 rotary position embeddingbf16 · [1, 2048, 8, 64]
NVIDIA H100
61.9µs
#1 of 2
2025-08-07
Run →
Llama 4 rotary position embeddingbf16 · [1, 1024, 8, 256]
NVIDIA H100
116.4µs
#2 of 2
2025-08-07
Run →
Llama 4 rotary position embeddingbf16 · [1, 1024, 8, 256]
NVIDIA H100
118.9µs
#2 of 2
2025-08-07
Run →
Llama 4 rotary position embeddingbf16 · [1, 2048, 8, 64]
NVIDIA H100
136.0µs
#1 of 2
2025-08-07
Run →
Llama 4 rotary position embeddingbf16 · [1, 2048, 8, 16]
NVIDIA H100
137.6µs
#1 of 2
2025-08-07
Run →
Llama 4 rotary position embeddingbf16 · [1, 2048, 8, 256]
NVIDIA H100
206.5µs
#3 of 4
2025-08-07
Run →
Llama 4 rotary position embeddingbf16 · [1, 2048, 8, 256]
NVIDIA H100
206.6µs
#4 of 4
2025-08-07
Run →
Llama 4 rotary position embeddingbf16 · [1, 2048, 8, 256]
NVIDIA H100
210.1µs
#3 of 4
2025-08-07
Run →
Llama 4 rotary position embeddingbf16 · [1, 2048, 8, 256]
NVIDIA H100
210.1µs
#3= of 4
2025-08-07
Run →
Show all 24 measurements ›
Llama 4 rotary position embeddingbf16 · [1, 1024, 8, 256]
NVIDIA H100
245.9µs
#1 of 2
2025-08-07
Run →
Llama 4 rotary position embeddingbf16 · [1, 2048, 8, 16]
NVIDIA H100
246.9µs
#1 of 2
2025-08-07
Run →
Llama 4 rotary position embeddingbf16 · [1, 2048, 8, 64]
NVIDIA H100
247.7µs
#1 of 2
2025-08-07
Run →
Llama 4 rotary position embeddingbf16 · [1, 4096, 8, 256]
NVIDIA H100
385.5µs
#2 of 2
2025-08-07
Run →
Llama 4 rotary position embeddingbf16 · [1, 4096, 8, 256]
NVIDIA H100
397.4µs
#2 of 2
2025-08-07
Run →
Llama 4 rotary position embeddingbf16 · [1, 2048, 8, 256]
NVIDIA H100
413.8µs
#3 of 4
2025-08-07
Run →
Llama 4 rotary position embeddingbf16 · [1, 2048, 8, 256]
NVIDIA H100
414.1µs
#4 of 4
2025-08-07
Run →
Llama 4 rotary position embeddingbf16 · [1, 8192, 8, 256]
NVIDIA H100
741.2µs
#2 of 2
2025-08-07
Run →
Llama 4 rotary position embeddingbf16 · [1, 8192, 8, 256]
NVIDIA H100
754.0µs
#2 of 2
2025-08-07
Run →
Llama 4 rotary position embeddingbf16 · [1, 4096, 8, 256]
NVIDIA H100
780.1µs
#2 of 2
2025-08-07
Run →
Llama 4 rotary position embeddingbf16 · [1, 16384, 8, 256]
NVIDIA H100
1.46ms
#2 of 2
2025-08-07
Run →
Llama 4 rotary position embeddingbf16 · [1, 16384, 8, 256]
NVIDIA H100
1.48ms
#2 of 2
2025-08-07
Run →
Llama 4 rotary position embeddingbf16 · [1, 8192, 8, 256]
NVIDIA H100
1.49ms
#2 of 2
2025-08-07
Run →
Llama 4 rotary position embeddingbf16 · [1, 16384, 8, 256]
NVIDIA H100
2.93ms
#2 of 2
2025-08-07
Run →

Reported · How evidence levels are derived →

Source and license

sourceavailable
revision digestsha256:cca024409163839a832c1d39bd301f536494b645171665d65fae5faf2717be48
license declaredApache-2.0
license concludedApache-2.0
imported2026-08-20

Best evidence level for this revision: reported

JSON