zer-bench 1.1.0

Benchmark harness for zer: throughput, accuracy, and competitor-library comparison

zer-bench

There is very little structured metadata to build this page from currently. You should check the main library docs, readme, or Cargo.toml in case the author documented the features in them.

This version has 12 feature flags, 1 of them enabled by default.

default

collect-pairs (default)

avx2

cpu

cuda

judge_cuda

judge_directml

judge_openvino

judge_rocm

judge_tensorrt

perf-metrics

This feature flag does not enable additional features.

progress

This feature flag does not enable additional features.

vulkan