A crate for managing the machine learning inference process
A dead-simple Ollama wrapper – auto-installs Ollama & models, then lets you prompt in two lines of code.
Local STT server powered by Zipformer-vi RNN-T — on-device Vietnamese speech recognition via ONNX Runtime
Local STT server powered by GigaAM v3 e2e_rnnt — on-device Russian speech recognition via ONNX Runtime
Local Japanese speech-to-text server — on-device, real-time, privacy-first. Powered by ReazonSpeech-k2-v2 via ONNX Runtime.
Remove testing docker containers after this object goes away
A highly parallel Perl 5 interpreter written in Rust
All-in-one DevOps toolkit: typed serde models for Kubernetes, Docker Compose, GitLab CI, GitHub Actions, Prometheus, Helm, Ansible + offline YAML validation and auto-repair.
A toolkit for developing, testing, and deploying quantum-resistant cryptographic algorithms.
A high-performance inference server for CTranslate2 models, compatible with OpenAI's API.
Local ML runner: declarative neuron.yaml, model store, daemon, and terminal dashboard
Local ML runner: declarative neuron.yaml, model store, daemon, and terminal dashboard
No description provided.
No description provided.
No description provided.