ai-hwaccel 1.0.0

Universal AI hardware accelerator detection, capability querying, and workload planning for Rust

ai-hwaccel

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 23 feature flags, 19 of them enabled by default.

default

all-backends (default)

cli (default)

amd-xdna (default)

This feature flag does not enable additional features.

apple (default)

This feature flag does not enable additional features.

aws-neuron (default)

This feature flag does not enable additional features.

cerebras (default)

This feature flag does not enable additional features.

cuda (default)

This feature flag does not enable additional features.

gaudi (default)

This feature flag does not enable additional features.

graphcore (default)

This feature flag does not enable additional features.

groq (default)

This feature flag does not enable additional features.

intel-npu (default)

This feature flag does not enable additional features.

intel-oneapi (default)

This feature flag does not enable additional features.

mediatek-apu (default)

This feature flag does not enable additional features.

qualcomm (default)

This feature flag does not enable additional features.

rocm (default)

This feature flag does not enable additional features.

samsung-npu (default)

This feature flag does not enable additional features.

tpu (default)

This feature flag does not enable additional features.

vulkan (default)

This feature flag does not enable additional features.

windows-wmi (default)

This feature flag does not enable additional features.

async-detect

common

fuzz

This feature flag does not enable additional features.

minimal

This feature flag does not enable additional features.