Fast, unified, Rust-native, Axum-compatible inference endpoints and nervous system for tensor models and LLMs: KServe / Triton and OpenAI APIs from one pure-Rust server
# The Dockerfile uses backslash line continuations, which CRLF line endings break
Dockerfiletexteol=lf*.shtexteol=lf# Wycheproof test vectors: byte-for-byte as upstream publishes them
rustls-pure/wycheproof/**-text