Glossary: Serving LLMs at Scale
FLOP
Also written: FLOPs, teraFLOPS
One arithmetic operation on decimal numbers; a teraFLOPS is a trillion per second. It measures a GPU's computing power.
Glossary: Serving LLMs at Scale
Also written: FLOPs, teraFLOPS
One arithmetic operation on decimal numbers; a teraFLOPS is a trillion per second. It measures a GPU's computing power.