Expand description
PINN Extension for QualiaDB Advanced
Physics-Informed Neural Networks with SMX formatting and 1.58-bit ternary quantization for solving differential equations and continuous physical systems while maintaining core engine constraints.
This extension uses the native Qualia LLM pipeline (wgpu + WGSL shaders) for neural network inference, ensuring zero-allocation hot paths and GPU acceleration without external ML frameworks.
Structs§
- Boundary
Condition - Boundary condition for PINN
- Convergence
Metrics - Convergence metrics for PINN
- Native
Pinn Backend - Native Qualia LLM backend for PINN inference
- Physics
Constraint - Physics constraint for PINN
- Physics
Violation - Physics violation detected in PINN
- Pinn
Execution Result - PINN execution result with SMX formatting
- Pinn
Extension - PINN Extension implementation with SMX formatting and ternary quantization
- Pinn
JobParams - PINN execution parameters
- Quantization
Metrics - Quantization metrics for PINN execution
- SmxFormatter
- SMX Formatter for structured model exchange
- SmxMetadata
Schema - SMX Metadata Schema for PINN models
- SmxOutput
- SMX output format for PINN results
- Tensor
Metadata - Metadata for ternary tensors
- Ternary
Pinn Model - Ternary Physics-Informed Neural Network model
- Ternary
Pinn Model Manager - Ternary PINN Model Manager with 1.58-bit quantization support
- Ternary
Quantization Config - Ternary Quantization Configuration for 1.58-bit models
- Ternary
Tensor - Ternary tensor representation for 1.58-bit quantization
- Training
Metadata - Training metadata for SMX format
Enums§
- Boundary
Type - Types of boundary conditions
- Equation
Type - Types of physics equations
- Physics
Domain - Physics domains supported by PINN models