R_REDDYX.XYZ
AIRust★ 7,803⑂ 570 forksApache-2.0

magnitudedev/magnitude

Auto-Tuning ML Inference Engine

Open-source inference engine that auto-tunes kernels per hardware for 2x faster model execution than Ollama across Apple Silicon, NVIDIA, AMD, Intel, and CPU.

// KEY FEATURES

  • Auto-tunes kernels on your hardware for optimal model performance
  • Runs 2x faster than Ollama on Apple Silicon, NVIDIA, AMD, Intel, and CPU
  • Written in Rust with zero runtime dependencies for easy deployment
Open on GitHub →

New repositories every 30 minutes

REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.

Join on Telegram
← Full catalog·Full index

// SIMILAR REPOSITORIES

Native Zelda on Apple Silicon★ 7811Claude Day Trading Skills★ 7791Reef: continuous learning★ 7823Self-Hosted A-Share Quant Workbench★ 7782WHATSAPP HTTP API IN MINUTES★ 7825ODS - YOUR AI SERVER★ 7832

← FULL CATALOG

magnitudedev/magnitude — Auto-Tuning ML Inference Engine