# Summary

[Introduction](./introduction.md)

# Getting Started

- [Installation](./getting-started/installation.md)
- [Quick Start](./getting-started/quick-start.md)
- [Model Hub](./getting-started/model-hub.md)
- [First Model](./getting-started/first-model.md)
- [Project Setup](./getting-started/project-setup.md)

# Architecture

- [Overview](./architecture/overview.md)
- [Crate Organization (62 Crates)](./architecture/crate-organization.md)
- [Tensor System](./architecture/tensor-system.md)
- [Autograd Engine](./architecture/autograd-engine.md)
- [GPU Runtime](./architecture/gpu-runtime.md)

# LLM Inference

- [Flash Attention](./llm/flash-attention.md)
- [KV-Cache Optimization](./llm/kv-cache.md)
- [Speculative Decoding](./llm/speculative-decoding.md)
- [Continuous Batching](./llm/continuous-batching.md)
- [Ring Attention](./llm/ring-attention.md)
- [Quantization](./llm/quantization.md)

# Deployment

- [Production Deployment](./deployment/production.md)
- [Edge Deployment](./deployment/edge.md)
- [Docker & Kubernetes](./deployment/containers.md)
- [Serving API](./deployment/serving-api.md)
- [WebAssembly & WebGPU](./deployment/wasm-webgpu.md)

# Performance

- [GPU Optimization](./performance/gpu-optimization.md)
- [Memory Management](./performance/memory.md)
- [Benchmarking](./performance/benchmarking.md)
- [Profiling](./performance/profiling.md)
- [Competitive Analysis](./performance/competitive-analysis.md)

# Troubleshooting

- [Build Errors](./troubleshooting/build-errors.md)
- [GPU Issues](./troubleshooting/gpu-issues.md)
- [Memory Problems](./troubleshooting/memory.md)
- [FAQ](./troubleshooting/faq.md)

# Migration

- [PyTorch to RustyTorch](./migration/from-pytorch.md)
- [API Reference Mapping](./migration/api-mapping.md)
- [Idioms](./migration/rust-idioms.md)