kopitiam-runtime 0.2.5

Kopitiam Runtime: the Qwen transformer forward pass (embedding, RoPE, grouped-query attention, SwiGLU MLP, KV cache, greedy sampling) running entirely in Rust on CPU.
Documentation

kopitiam-runtime

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 1 feature flags, 1 of them enabled by default.

default

gpu (default)