reuse-rs: a plain-Rust port of NVIDIA's live speech denoiser runs faster on the CPU than on the GPU
One developer rewrote NVIDIA's streaming RE-USE model in Rust and measured 8.4 ms per 20 ms frame on an M3 CPU, against 16.9 ms through WebGPU.
Topic · 5 stories
5 stories tagged onnx on AI Tamer, newest first.
One developer rewrote NVIDIA's streaming RE-USE model in Rust and measured 8.4 ms per 20 ms frame on an M3 CPU, against 16.9 ms through WebGPU.
pyke's ort 2.0.0-rc.15 fixes what it calls over 30 cases of undefined behavior and adds no features. It breaks a few APIs, including run_async inputs.
Sonos published tract 0.23.9 on 15 October with a tract_moe_ffn operator. The deploy runtime is marked WIP. crates.io still lists 0.21.19 as newest.
pyke shipped ort 2.0.0-rc.14. Sessions take an explicit Environment. Older ort can fail on Rust 1.100 when copy-dylibs is enabled.
Qdrant’s Clelia Bertelli blog (Sep 25, 2026) covers cross-encode-rs—a Rust ONNX Runtime cross-encoder for reranking. crates.io owner is AstraBert (not a Qdrant-org crate). ~1.1×/~1.4× vs Python stacks on M4 Max are vendor-reported; all three hand work to onnxruntime. Linux/macOS only.