ThroughputBencher — Globe Race

Model performance

Throughput vs compute cost — click a family in the legend to filter.
Showing fp32 precision, no torch.compile (eager baseline)

GPU

X axis

Y axis

Precision & torch.compile speedup

Throughput relative to fp32-eager (baseline = 1.0×) for ResNet, ViT, and EfficientNet families.

Best throughput (img/s) per model on each GPU · click a column header to sort

Don't show automatically