Apple 的 ReDrafter：通过闪电般快速的令牌生成彻底改变语言模型训练

Apple 凭借其创新方法使语言模型训练速度快如闪电，在机器学习领域取得了显着突破。这家科技巨头的新方法称为 ReDrafter，它将通过显着加速代币生成过程来彻底改变我们构建和部署人工智能模型的方式。

Apple has made a remarkable breakthrough in the world of machine learning with its innovative approach to making language model training lightning-fast. The tech giant’s new method, called ReDrafter, is set to revolutionize the way we build and deploy AI models by significantly accelerating the token generation process.

Apple 凭借其创新方法使语言模型训练速度快如闪电，在机器学习领域取得了显着突破。这家科技巨头的新方法称为 ReDrafter，它将通过显着加速代币生成过程来彻底改变我们构建和部署人工智能模型的方式。

The Challenges in Building AI Models

构建人工智能模型的挑战

Developing large language models (LLMs) is known to be a resource-intensive undertaking. Traditional methods require substantial hardware investments and incur high energy costs. Earlier this year, Apple introduced ReDrafter, an open-sourced technique aimed at streamlining this process.

众所周知，开发大型语言模型 (LLM) 是一项资源密集型工作。传统方法需要大量的硬件投资并产生高昂的能源成本。今年早些时候，苹果推出了 ReDrafter，这是一种旨在简化这一流程的开源技术。

A Breakthrough in Speed

速度的突破

ReDrafter, which utilizes a Recurrent Neural Network (RNN) draft model, leverages a unique combination of beam search and dynamic tree attention. This innovation has led to LLM token generation speeds up to 3.5 times faster than conventional auto-regressive techniques. Now, Apple's ReDrafter is ready for prime time, particularly with Nvidia GPUs.

ReDrafter 采用循环神经网络 (RNN) 草图模型，利用波束搜索和动态树注意力的独特组合。这项创新使 LLM 代币生成速度比传统自回归技术快 3.5 倍。现在，Apple 的 ReDrafter 已准备好迎接黄金时段，特别是在 Nvidia GPU 的帮助下。

Collaboration with Nvidia

与英伟达合作

Apple collaborated closely with Nvidia to integrate ReDrafter into the Nvidia TensorRT-LLM framework. This partnership has resulted in a significant 2.7-times speed increase in token generation during testing on Nvidia’s powerful GPUs, offering substantial benefits in terms of efficiency and hardware reduction.

Apple 与 Nvidia 密切合作，将 ReDrafter 集成到 Nvidia TensorRT-LLM 框架中。在 Nvidia 强大的 GPU 上进行测试时，这种合作关系使代币生成速度显着提高了 2.7 倍，在效率和硬件减少方面带来了巨大的好处。

Impact on the AI Community

对人工智能社区的影响

This advancement will not only mean faster responses for users but also reduced hardware expenses for companies, paving the way for more sophisticated AI models. Nvidia hailed the collaboration as enhancing TensorRT-LLM’s flexibility and power.

这一进步不仅意味着用户的响应速度更快，而且还减少了公司的硬件支出，为更复杂的人工智能模型铺平了道路。 Nvidia 称赞此次合作增强了 TensorRT-LLM 的灵活性和功能。

In light of these advances, Apple continues to explore new frontiers, previously indicating potential efficiency gains from using Amazon’s Trainium2 chip for future AI model training.

鉴于这些进步，苹果公司继续探索新领域，此前曾表明使用亚马逊的 Trainium2 芯片进行未来人工智能模型训练可能会带来效率提升。