oxfuse-runtime
Tensors, execution plans and the CPU backends for oxfuse graphs: a reference backend, and a fast backend that returns the same bits. The optional parallel feature threads the fast matmul without changing results.
An example that builds a graph, runs the passes and compares both backends is examples/optimize_and_run.rs:
cargo run --release -p oxfuse-runtime --example optimize_and_run
Experimental. The optional GPU backend is the oxfuse-wgpu crate. Measurements are in the repository's docs/benchmarks.md.
Licensed under Apache-2.0.