Evaluating the Performance of the DeepSeek Model in Confidential Computing Environment

TL;DR

This paper evaluates the performance of the DeepSeek large language model within Intel TDX-based confidential computing environments, demonstrating promising results for secure, resource-efficient AI deployment.

Contribution

First comprehensive performance evaluation of DeepSeek in TEE-enabled confidential computing, comparing CPU, GPU, and hybrid implementations for secure LLM inference.

Findings

TDX outperforms CPU in small model secure inference

GPU-to-CPU performance ratio averages 12 across models

Provides insights for optimizing confidential AI deployments

Abstract

The increasing adoption of Large Language Models (LLMs) in cloud environments raises critical security concerns, particularly regarding model confidentiality and data privacy. Confidential computing, enabled by Trusted Execution Environments (TEEs), offers a promising solution to mitigate these risks. However, existing TEE implementations, primarily CPU-based, struggle to efficiently support the resource-intensive nature of LLM inference and training. In this work, we present the first evaluation of the DeepSeek model within a TEE-enabled confidential computing environment, specifically utilizing Intel Trust Domain Extensions (TDX). Our study benchmarks DeepSeek's performance across CPU-only, CPU-GPU hybrid, and TEE-based implementations. For smaller parameter sets, such as DeepSeek-R1-1.5B, the TDX implementation outperforms the CPU version in executing computations within a secure environment. It highlights the potential for efficiently deploying LLM models on resource-constrained systems while ensuring security. The overall GPU-to-CPU performance ratio averages 12 across different model sizes, with smaller models exhibiting a lower ratio. Additionally, we provide foundational insights and guidance on optimizing CPU-GPU confidential computing solutions for scalable and secure AI deployments. Our findings contribute to the advancement of privacy-preserving AI, paving the way for efficient and secure LLM inference in confidential computing environments.