彻底改变人工智能：Apple 和 Nvidia 的突破性合作塑造语言模型的未来

Apple 和 Nvidia 推出了一种称为 Recurrent Drafter 或 ReDrafter 的范式转换技术，这是 AI 领域令人兴奋的进步。

Apple and Nvidia Join Forces to Spearhead AI Advancements with ReDrafter Technology

Apple 和 Nvidia 联手利用 ReDrafter 技术引领 AI 进步

In a groundbreaking collaboration, Apple and Nvidia have unveiled a cutting-edge initiative aimed at revolutionizing language model processing. Their newly introduced technology, Recurrent Drafter, or ReDrafter, promises significant advancements in the field of AI by tackling the computational hurdles of auto-regressive token generation.

在一项突破性的合作中，苹果和英伟达推出了一项旨在彻底改变语言模型处理的尖端举措。他们新推出的技术 Recurrent Drafter 或 ReDrafter 通过解决自动回归令牌生成的计算障碍，有望在人工智能领域取得重大进步。

Apple, which launched ReDrafter in November 2024, has developed an innovative method focusing on a speculative decoding approach. The technique integrates a recurrent neural network (RNN) with beam search and dynamic tree attention, resulting in an impressive boost in processing speed. According to Apple’s benchmarks, ReDrafter can produce a remarkable 2.7 times more tokens per second compared to traditional methods.

Apple 于 2024 年 11 月推出了 ReDrafter，开发了一种专注于推测解码方法的创新方法。该技术将循环神经网络 (RNN) 与波束搜索和动态树注意力集成在一起，从而显着提高了处理速度。根据 Apple 的基准测试，与传统方法相比，ReDrafter 每秒可以生成多出 2.7 倍的代币。

The collaboration primarily enhances Nvidia’s TensorRT-LLM framework, thereby delivering accelerated large language model (LLM) inference on Nvidia GPUs. To facilitate these advancements, Nvidia has not only introduced new operators but has also optimized existing ones within TensorRT-LLM. This allows developers to enhance the performance of large-scale models significantly.

此次合作主要增强了 Nvidia 的 TensorRT-LLM 框架，从而在 Nvidia GPU 上提供加速的大语言模型 (LLM) 推理。为了促进这些进步，Nvidia 不仅引入了新的运算符，还优化了 TensorRT-LLM 中的现有运算符。这使得开发人员能够显着提高大型模型的性能。

Beyond speed, ReDrafter’s efficiency reduces user latency and minimizes the need for GPUs, leading to lower computational costs and energy consumption. This aspect is especially crucial for large-scale AI applications where power efficiency is a priority.

除了速度之外，ReDrafter 的效率还减少了用户延迟并最大限度地减少了对 GPU 的需求，从而降低了计算成本和能耗。这对于优先考虑电源效率的大规模人工智能应用来说尤其重要。

While the current focus centers on Nvidia, the potential for similar enhancements on AMD and Intel GPUs looms on the horizon, promising a broader impact on the industry. This collaboration marks a substantial leap forward in machine learning capabilities, opening doors to future innovations and efficiencies across AI platforms.

虽然目前的焦点集中在 Nvidia 上，但 AMD 和英特尔 GPU 类似增强功能的潜力也即将显现，有望对该行业产生更广泛的影响。此次合作标志着机器学习能力的重大飞跃，为人工智能平台的未来创新和效率打开了大门。