diff --git a/README.md b/README.md index c21bb938..fd9db2ce 100644 --- a/README.md +++ b/README.md @@ -91,6 +91,8 @@ High-performance attention mechanisms for transformers, graph neural networks, a #### Core Attention Mechanisms +Standard attention layers for sequence modeling and transformers. + | Mechanism | Complexity | Memory | Best For | |-----------|------------|--------|----------| | **DotProductAttention** | O(n²) | O(n²) | Basic attention for small-medium sequences | @@ -102,6 +104,8 @@ High-performance attention mechanisms for transformers, graph neural networks, a #### Graph Attention Mechanisms +Attention layers designed for graph-structured data and GNNs. + | Mechanism | Complexity | Best For | |-----------|------------|----------| | **GraphRoPeAttention** | O(n²) | Position-aware graph transformers | @@ -111,6 +115,8 @@ High-performance attention mechanisms for transformers, graph neural networks, a #### Specialized Mechanisms +Task-specific attention variants for efficiency and multi-modal learning. + | Mechanism | Type | Best For | |-----------|------|----------| | **SparseAttention** | Efficiency | Long docs, low-memory inference | @@ -120,7 +126,7 @@ High-performance attention mechanisms for transformers, graph neural networks, a #### Hyperbolic Math Functions -Operations for Poincaré ball embeddings (curved space for hierarchies): +Operations for Poincaré ball embeddings—curved space that naturally represents hierarchies. | Function | Description | Use Case | |----------|-------------|----------| @@ -132,6 +138,8 @@ Operations for Poincaré ball embeddings (curved space for hierarchies): #### Async & Batch Operations +Utilities for high-throughput inference and training optimization. + | Operation | Description | Performance | |-----------|-------------|-------------| | `asyncBatchCompute()` | Process batches in parallel | 3-5x faster |