Learn Before
Activity (Process)

Establishing the Initial Context for Inference

The inference process within the prefilling-decoding framework begins by establishing an initial context, denoted as 'x'. This input sequence serves as the foundation for the prefilling phase, where its representation is computed and stored in the KV cache.

0

1

Updated 2025-10-10

Contributors are:

Who are from:

Tags

Ch.5 Inference - Foundations of Large Language Models

Foundations of Large Language Models

Foundations of Large Language Models Course

Computing Sciences