Skip to content

CONCEPT Cited by 1 source

Prefill-only inference

Definition

Prefill-only inference is an LLM serving mode where the model processes the input prompt in a single forward pass (the prefill phase) and extracts a representation — without performing any autoregressive token-by-token decoding. The model never enters the decode phase.

This is specifically useful for scoring or embedding workloads where the output is a numeric vector (not generated text). The cost profile shifts from O(prompt + generated_tokens) to O(prompt) only, eliminating the sequential decode bottleneck.

Why It Matters

Autoregressive decoding over large candidate sets is prohibitively expensive for recommendation workloads. If a model must decode N candidate IDs one-by-one, the cost is linear in N. Prefill-only mode:

  • Processes the prompt once — a single parallel forward pass across all tokens.
  • Extracts a pooled representation from the last-layer hidden states.
  • Scores the entire candidate set via a scoring head (dot product or MLP against learned item embeddings) in a single matrix operation.

The distinction from standard embedding inference is that prefill-only inference here still leverages a generative model's architecture and training signal — the model was trained with next-token-prediction objectives — but at inference time the decoding path is never invoked.

Trade-offs

Property Prefill-only Autoregressive
Latency Single forward pass + matmul Sequential per-token decoding
Cost O(prompt_length) O(prompt_length + output_length)
Output Numeric scores / embeddings Generated tokens
Flexibility Fixed scoring function Arbitrary text output
KV cache Populated once, discarded Grows with output length

Seen in

Last updated · 606 distilled / 1,847 read