kopitiam-runtime 0.2.3

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

Builds

kopitiam-runtime's sandbox limits

All the builds on docs.rs are executed inside a sandbox with limited resources. The limits for this crate are the following:

Available RAM 6.44 GB
Maximum rustdoc execution time 15m
Maximum size of a build log 102.4 kB
Network access blocked
Maximum number of build targets 10

If a build fails because it hit one of those limits please open an issue to get them increased.