References & Citations
Computer Science > Computation and Language
Title: Prompt Cache: Modular Attention Reuse for Low-Latency Inference
(Submitted on 7 Nov 2023 (v1), last revised 25 Apr 2024 (this version, v2))
Abstract: We present Prompt Cache, an approach for accelerating inference for large language models (LLM) by reusing attention states across different LLM prompts. Many input prompts have overlapping text segments, such as system messages, prompt templates, and documents provided for context. Our key insight is that by precomputing and storing the attention states of these frequently occurring text segments on the inference server, we can efficiently reuse them when these segments appear in user prompts. Prompt Cache employs a schema to explicitly define such reusable text segments, called prompt modules. The schema ensures positional accuracy during attention state reuse and provides users with an interface to access cached states in their prompt. Using a prototype implementation, we evaluate Prompt Cache across several LLMs. We show that Prompt Cache significantly reduce latency in time-to-first-token, especially for longer prompts such as document-based question answering and recommendations. The improvements range from 8x for GPU-based inference to 60x for CPU-based inference, all while maintaining output accuracy and without the need for model parameter modifications.
Submission history
From: In Gim [view email][v1] Tue, 7 Nov 2023 18:17:05 GMT (1389kb,D)
[v2] Thu, 25 Apr 2024 15:45:19 GMT (1687kb,D)
Link back to: arXiv, form interface, contact.