Performance

CPU release¶

IDLive Doc Server for CPU is configured to achieve the optimal throughput by default. In order to switch the server to latency optimization mode one should set the DOCSDK_OPTIMIZE_THROUGHPUT environment variable to 0 value on the container start.

GPU release¶

IDLive Doc Server for GPU doesn't provide different performance modes. However, it's important to mention that available GPU resources are distributed fairly between all initialized liveness pipelines. This means that the more initialized pipelines you have within a single container, the less concurrent liveness check requests can be processed in parallel by each instance resulting in lower per-pipeline TPS.