oxillama 0.1.0

Pure Rust LLM inference engine — the sovereign alternative to llama.cpp (meta crate)
Documentation

oxillama

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 14 feature flags, 2 of them enabled by default.

default

bench (default)

server (default)

command-r

gemma

gpu

llama

llava

mistral

phi

qwen3

simd-avx2

simd-avx512

simd-neon

starcoder