title: one load four times in a row, with and without a flush
source: manuals/sglang-101/capture/gpu/out-l4/prefix-cache-flush.txt
lines: 9-11
lang: text
note: A smaller model on another GPU. Read the ratios, not the times.
---
engine        fresh   repeat, not flushed   repeat after a flush   repeat, not flushed
SGLang 0.6B   394     82.5                  289                    77
vLLM 0.6B     925     148                   1,163                  184
