← all papers · overview

Prepacking: A Simple Method For Fast Prefilling And Increased Throughput In Large Language Models

Abstract

During inference for transformer-based large language models (LLM), prefilling is the computation of the key-value (KV) cache for input tokens in the prompt prior to autoregressive generation. For longer input prompt lengths, prefilling will incur a significant overhead on decoding time. In this work, we highlight the following pitfall of prefilling: for batches containing high-varying prompt leng

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).