Principle:Ggml org Llama cpp SpeculativeDecoding
| Knowledge Sources | Domains | Last Updated |
|---|---|---|
| ggml-org/llama.cpp | Speculative Execution, N-gram Lookup | 2026-02-15 |
Overview
Description
Speculative Decoding Ngrams is a design principle in the llama.cpp project covering speculative execution and N-gram lookup.
Usage
See linked implementation pages for concrete usage details.
Related Pages
Page Connections
Double-click a node to navigate. Hold to expand connections.
Principle
Implementation
Heuristic
Environment