vrr/ruvector
2
0
Fork 0
mirror of https://github.com/ruvnet/RuVector.git synced 2026-05-29 11:13:33 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

docs: Add feature overview table to Attention Mechanisms section

Browse source 
Replaced single-line intro with structured table matching other sections:
- 39 Mechanisms: lists key attention types
- Graph Attention: GNN-specific mechanisms
- Hyperbolic Attention: curved-space operations
- SIMD Optimized: performance benefits
- Streaming & Caching: memory and inference optimization

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
rUv 2025-12-02 17:55:09 +00:00
parent 9e6f87641b
commit 1eb348322e
1 changed files with 7 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

8
README.md
View file

@ -85,7 +85,13 @@ cargo add ruvector-raft ruvector-cluster ruvector-replication
### Attention Mechanisms (`@ruvector/attention`)
High-performance attention mechanisms for transformers, graph neural networks, and hyperbolic embeddings. Native Rust with NAPI-RS bindings for maximum performance.
| Feature | What It Does | Why It Matters |
|---------|--------------|----------------|
| **39 Mechanisms** | Dot-product, multi-head, flash, linear, sparse, cross-attention | Cover all transformer and GNN use cases |
| **Graph Attention** | RoPE, edge-featured, local-global, neighborhood | Purpose-built for graph neural networks |
| **Hyperbolic Attention** | Poincaré ball operations, curved-space math | Better embeddings for hierarchical data |
| **SIMD Optimized** | Native Rust with AVX2/NEON acceleration | 2-10x faster than pure JS |
| **Streaming & Caching** | Chunk-based processing, KV-cache | Constant memory, 10x faster inference |
> **Documentation**: [Attention Module Docs](./crates/ruvector-attention/README.md)