Compare Runtimes

Select runtimes to compare side by side. Click chips below to toggle selection.

MetricExLlamaV2Text Generation Inference
ScoreD47F39
Type
Executionaothybrid
Interfacesdkapi
Cold Start1000ms10000ms
Memory300MB2000MB
Startup200ms5000ms
Isolationprocesscontainer
Maturitystableproduction
LanguagesPython, C++, CUDARust, Python
LicenseMITApache-2.0
Links