Compare Runtimes

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

MetricExLlamaV2vLLM
ScoreD47F35
Type
Executionaotjit
Interfacesdkapi
Cold Start1000ms5000ms
Memory300MB2000MB
Startup200ms3000ms
Isolationprocessprocess
Maturitystableproduction
LanguagesPython, C++, CUDAPython
LicenseMITApache-2.0
Links