Skip to content
KernelIndex
Search⌘K
Sign in

PyTorch

python · BSD-3-Clause
holds 4 records

Use it

Source available upstream · BSD-3-ClauseView 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
ReLU squaredbf16 · [4096, 128]
NVIDIA H100
8.67µs
#2 of 2
2026-03-27
Run →
ReLU squaredbf16 · [4096, 256]
NVIDIA H100
10.1µs
#2 of 2
2026-03-27
Run →
ReLU squaredbf16 · [4096, 512]
NVIDIA H100
11.9µs
#2 of 2
2026-03-27
Run →
ReLU squaredbf16 · [4096, 1024]
NVIDIA H100
16.9µs
#2 of 2
2026-03-27
Run →
ReLU squaredbf16 · [4096, 128]
NVIDIA H100
16.9µs
#2 of 2
2026-03-27
Run →
ReLU squaredbf16 · [4096, 256]
NVIDIA H100
18.6µs
#2 of 2
2026-03-27
Run →
ReLU squaredbf16 · [4096, 512]
NVIDIA H100
23.5µs
#2 of 2
2026-03-27
Run →
ReLU squaredbf16 · [4096, 128]
NVIDIA H100
25.9µs
#1 of 2
2026-03-27
Run →
ReLU squaredbf16 · [4096, 2048]
NVIDIA H100
26.8µs
#2 of 2
2026-03-27
Run →
ReLU squaredbf16 · [4096, 512]
NVIDIA H100
31.7µs
#1 of 2
2026-03-27
Run →
Show all 24 measurements ›
ReLU squaredbf16 · [4096, 256]
NVIDIA H100
34.8µs
#1 of 2
2026-03-27
Run →
ReLU squaredbf16 · [4096, 1024]
NVIDIA H100
35.5µs
#2 of 2
2026-03-27
Run →
ReLU squaredbf16 · [4096, 1024]
NVIDIA H100
47.2µs
#1 of 2
2026-03-27
Run →
ReLU squaredbf16 · [4096, 4096]
NVIDIA H100
53.2µs
#2 of 2
2026-03-27
Run →
ReLU squaredbf16 · [4096, 2048]
NVIDIA H100
60.3µs
#2 of 2
2026-03-27
Run →
ReLU squaredbf16 · [4096, 2048]
NVIDIA H100
81.7µs
#2 of 2
2026-03-27
Run →
ReLU squaredbf16 · [4096, 8192]
NVIDIA H100
97.9µs
#2 of 2
2026-03-27
Run →
ReLU squaredbf16 · [4096, 4096]
NVIDIA H100
126.3µs
#2 of 2
2026-03-27
Run →
ReLU squaredbf16 · [4096, 4096]
NVIDIA H100
177.7µs
#2 of 2
2026-03-27
Run →
ReLU squaredbf16 · [4096, 16384]
NVIDIA H100
185.5µs
#2 of 2
2026-03-27
Run →
ReLU squaredbf16 · [4096, 8192]
NVIDIA H100
235.5µs
#2 of 2
2026-03-27
Run →
ReLU squaredbf16 · [4096, 8192]
NVIDIA H100
331.1µs
#2 of 2
2026-03-27
Run →
ReLU squaredbf16 · [4096, 16384]
NVIDIA H100
452.7µs
#2 of 2
2026-03-27
Run →
ReLU squaredbf16 · [4096, 16384]
NVIDIA H100
635.4µs
#2 of 2
2026-03-27
Run →

Reported · How evidence levels are derived →

Source and license

sourceavailable
revision digestsha256:ce55d39a62f0f84142e1fb25300736a7880501f42bec3a607a0d6fb5925a1ee6
license declaredBSD-3-Clause
license concludedBSD-3-Clause
imported2026-08-20

Best evidence level for this revision: reported

JSON