inferencelayer 0.2.2

Kortexya's engine-native inference layer — LLM generation + embedding/encoder family on wgpu (WGSL kernels, any adapter) with a pure-Rust CPU fallback
Documentation

inferencelayer

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 9 feature flags, 3 of them enabled by default.

default

cli (default)

encoder-cpu (default)

net (default)

This feature flag does not enable additional features.

audio-io

cudarc

server

webrtc

webrtc-media

ws