English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Born Book Appendix C: Glossary of Key Terms

Forum topic · QianXun · 2026-06-13

Summary

Appendix C of the serialized technical book Born provides standard definitions for the core terminology used throughout the text. The glossary is organized into five domains. Tensors and data structures: Tensor[T, B], shape, stride, and broadcasting. Compute backends: backend (CPU/WebGPU), lazy evaluation for batching operations to hide latency, WGSL (WebGPU Shading Language), and workgroups. Automatic differentiation: autodiff, gradient tape, and backpropagation through the computation graph. Neural networks: modules, multi-head attention (MHA), grouped-query attention (GQA), and residual connections. Models and deployment: checkpoints, GGUF (Georgi Gerganov Universal Format), KV-cache for avoiding repeated key/value computation, and quantization. This is part 4 of the appendix series from the book's ongoing serialization on zhichai.net.

This appendix provides standard definitions for the core terminology used throughout the book *Born*.

Tensors and Data Structures

| Term | Definition | |------|------------| | Tensor | A general term for multi-dimensional arrays; represented in Born as Tensor[T, B] | | Shape | The list of lengths of a tensor along each axis | | Stride | The memory offset required to move one element along each axis | | Broadcasting | Rules for automatically expanding smaller shapes to match larger ones |

Compute Backends

| Term | Definition | |------|------------| | Backend | A concrete implementation that executes tensor operations (CPU/WebGPU) | | Lazy evaluation | Deferring operation execution and submitting them in batches to hide communication latency | | WGSL | WebGPU Shading Language | | Workgroup | The basic unit of compute dispatch in WebGPU |

Automatic Differentiation

| Term | Definition | |------|------------| | Automatic differentiation | Algorithms that compute function gradients automatically | | Gradient tape | A data structure that records the sequence of forward operations | | Backpropagation | Propagating gradients backward from the output loss through the computation graph |

Neural Networks

| Term | Definition | |------|------------| | Module | The basic building block of neural networks | | Multi-head attention (MHA) | Multiple attention heads computed in parallel | | Grouped-query attention (GQA) | Multiple query heads sharing key-value heads | | Residual connection | A shortcut connection that adds the input directly to the output |

Models and Deployment

| Term | Definition | |------|------------| | Checkpoint | A snapshot of model state saved during training | | GGUF | Georgi Gerganov Universal Format, a model format for LLMs | | KV-Cache | Caching key-value tensors to avoid repeated computation | | Quantization | Converting parameters from high precision to low precision |

---

📘 This is Appendix C (part 4) of *Born*, a technical book being published in serial form.

Tags

#glossary#tensors#webgpu#automatic-differentiation#neural-networks#gguf#kv-cache#quantization

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177981257