Expand description
§kizzasi-model
Model architectures for Kizzasi AGSP (Autoregressive General-Purpose Signal Predictor).
This crate implements various State Space Model architectures optimized for continuous signal prediction with O(1) inference step complexity:
- Mamba/Mamba2: Selective State Space Models with input-dependent dynamics
- RWKV: Linear attention with time-mixing and channel-mixing
- S4/S4D: Structured State Space Models with diagonal state matrices
- Transformer: Standard attention for comparison (O(N) per step)
§COOLJAPAN Ecosystem
This crate follows KIZZASI_POLICY.md and uses scirs2-core for all
array and numerical operations.
§Architecture Philosophy
As described in the AGSP concept, these models treat all signals (audio, video, sensors, actions) as equivalent tokenized sequences, enabling cross-modal prediction and world model construction.
Re-exports§
pub use loader::ModelLoader;pub use loader::TensorInfo;pub use loader::WeightLoader;pub use blas_ops::axpy;pub use blas_ops::batch_matmul_vec;pub use blas_ops::dot;pub use blas_ops::matmul_mat;pub use blas_ops::matmul_vec;pub use blas_ops::norm_frobenius;pub use blas_ops::norm_l2;pub use blas_ops::transpose;pub use blas_ops::BlasConfig;pub use profiling::BottleneckInfo;pub use profiling::BottleneckSeverity;pub use profiling::ComprehensiveComparison;pub use profiling::ComprehensiveProfiler;pub use profiling::ModelBottleneckAnalysis;
Modules§
- batch
- Batched Inference Support
- blas_
ops - BLAS-Accelerated Operations
- cache_
friendly - Cache-Friendly Memory Layouts
- checkpoint
- Checkpointing and Training Utilities
- compression
- Model Compression Utilities
- dynamic_
quantization - Dynamic Quantization for On-the-Fly Model Compression
- factory
- Model Factory for Instantiating Models from Loaded Weights
- h3
- H3: Hungry Hungry Hippos
- huggingface
- HuggingFace Hub Integration
- huggingface_
loader - HuggingFace Model Loading and Weight Conversion
- hybrid
- Hybrid Mamba+Attention Model
- loader
- Weight loading from safetensors format
- mamba
- Mamba: Selective State Space Model
- mamba2
- Mamba2: Enhanced Selective State Space Model with State Space Duality (SSD)
- mixed_
precision - Mixed Precision Support (FP16/BF16)
- moe
- Mixture of Experts (MoE)
- parallel_
multihead - Parallel Multi-Head Computation
- profiling
- Model Profiling and Benchmarking Utilities
- pytorch_
compat - PyTorch Checkpoint Compatibility
- quantization
- Weight Quantization for Efficient Inference
- rwkv
- RWKV v6: Receptance Weighted Key Value
- rwkv7
- RWKV v7: Next Generation Receptance Weighted Key Value (Forward-Compatible Scaffolding)
- s4
- S4 and S4D: Structured State Space Models
- s5
- S5: Simplified State Space Model
- simd_
ops - SIMD-Optimized Operations for Model Inference
- training
- Training Infrastructure for kizzasi-model
- transformer
- Transformer: Standard Multi-Head Attention Baseline
Structs§
- Hidden
State - Represents the hidden state of the SSM
Enums§
- Model
Error - Errors that can occur in model operations
- Model
Type - Enumeration of supported model architectures
Traits§
- Autoregressive
Model - Trait for model architectures that support autoregressive prediction
- Signal
Predictor - Core trait for autoregressive signal prediction
Type Aliases§
- Array1
- one-dimensional array
- Array2
- two-dimensional array
- Core
Result - Result type alias for core operations
- Model
Result - Result type alias for model operations