Model techniques map
Techniquesinference & servingKV cache management

implementation detail · filed under inference & serving

Disable prefix caching for benchmarking

Also called disabling prefix caching.

source
1
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

Add --no-enable-prefix-caching to the server command for a clean measurement.

usedevaluation onlyvLLM

Filed alongside

Other methods under inference & serving :: KV cache management.