mirror of
https://github.com/ruvnet/RuVector.git
synced 2026-05-22 19:56:25 +00:00
Reimagined embedding generation using ONNX Runtime in pure Rust: - Native ONNX inference via ort crate with GPU support (CUDA, TensorRT, CoreML) - HuggingFace tokenizer integration for 8+ pretrained models - Multiple pooling strategies (Mean, CLS, Max, etc.) - SIMD-optimized distance calculations - Batch processing with parallel execution - Direct RuVector HNSW index integration - RAG pipeline support - WebGPU/CUDA-WASM GPU acceleration with 11 WGSL compute shaders 46 tests pass with GPU feature, comprehensive benchmarks included. |
||
|---|---|---|
| .. | ||
| GPU_ACCELERATION.md | ||