How does speculative decoding reduce generation latency?
PICTURE THIS: A SENTENCE BECOMES TOKENS
The model does not read letters like humans. It reads these pieces, then predicts the next one.
Simple meaning
A cheap draft model proposes several tokens
WHY — Tokens instead of words?
LLMs use tokens (not full words) because it helps them:
question about Cost.
trade-offs, and what you would actually do on a GenAI / LLM project - not buzzwords.
Each piece maps to a number the network can learn.
Fixed pieces are what transformers expect as input.
STEPS — What happens with tokens?
Before the model can read a sentence, it goes through these steps:
- 1A cheap draft model
proposes several tokens
- 2the large model verifies
them in one parallel pass.
- 3Accepted tokens skip sequential
large-model steps.
- 4Context mix
Gains depend on draft quality
- 5Next token
a bad draft wastes verification.
- 6Decode
IDs turn back into readable text.
EXAMPLE — See it in action
Let's see how a real sentence is tokenized (tokens may vary by model):
Note: Actual tokens and IDs depend on the tokenizer (e.g., GPT, Llama, etc.).
Key takeaway
A cheap draft model proposes several tokens the large model verifies them in one parallel pass.