Topic
Speculative Decoding
5 posts on speculative decoding — part of glossary on the n4n AI blog.
What is speculative decoding in LLM inference?
Speculative decoding explained: how draft models accelerate LLM inference without quality loss, with code examples and practical trade-offs.
Speculative decoding vs standard autoregressive decoding
A practitioner's comparison of speculative decoding vs autoregressive decoding — latency gains, implementation costs, quality trade-offs, and when each approach fits your inference stack.
How speculative decoding preserves output quality
How speculative decoding maintains output quality while accelerating LLM inference — the mechanics, verification guarantees, and practical tradeoffs every engineer should understand.
How acceptance rate affects speculative decoding speedup
How speculative decoding acceptance rate mathematically determines speedup, why it varies in practice, and what engineers should optimize for.
How a draft model speeds up speculative decoding
A technical explainer of how draft models accelerate speculative decoding in LLM inference, with concrete mechanics, code examples, and common pitfalls.
More topics in glossary
- Structured Outputs & JSON Mode19
- AI Agents Fundamentals12
- Hallucination in LLMs11
- Sampling Parameters: Top-p, Top-k & Penalties11
- Context Window & Context Length10
- Fine-Tuning Fundamentals9
- Foundation Models: Base vs Instruct vs Chat9
- Model Families & Naming Conventions: GPT-5, Claude, Gemini 3, Llama 4, Mistral, DeepSeek, Qwen, Grok9
- Grounding & Fact-Checking in AI8
- LLM Benchmarks: MMLU, HumanEval, SWE-bench & GPQA8
- Max Tokens, Stop Sequences & Output Truncation8
- Quantization Formats: GGUF, GPTQ, AWQ & INT4/INT88