徹底改變人工智慧：Apple 和 Nvidia 的突破性合作塑造語言模型的未來

Apple 和 Nvidia 推出了一種稱為 Recurrent Drafter 或 ReDrafter 的範式轉換技術，這是 AI 領域令人興奮的進步。

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

Apple 和 Nvidia 聯手利用 ReDrafter 技術引領 AI 進步

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.

在一項突破性的合作中，蘋果和英偉達推出了一項旨在徹底改變語言模型處理的尖端舉措。他們新推出的技術 Recurrent Drafter 或 ReDrafter 透過解決自動回歸令牌產生的計算障礙，有望在人工智慧領域取得重大進展。

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 於 2024 年 11 月推出了 ReDrafter，開發了一種專注於推測解碼方法的創新方法。該技術將循環神經網路 (RNN) 與波束搜尋和動態樹注意力整合在一起，從而顯著提高了處理速度。根據 Apple 的基準測試，與傳統方法相比，ReDrafter 每秒鐘可以產生多出 2.7 倍的代幣。

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.

此次合作主要增強了 Nvidia 的 TensorRT-LLM 框架，從而在 Nvidia GPU 上提供加速的大語言模型 (LLM) 推理。為了促進這些進步，Nvidia 不僅引入了新的運算符，還優化了 TensorRT-LLM 中的現有運算符。這使得開發人員能夠顯著提高大型模型的效能。

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 的效率還減少了使用者延遲並最大限度地減少了對 GPU 的需求，從而降低了運算成本和能耗。這對於優先考慮電源效率的大規模人工智慧應用尤其重要。

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.

雖然目前的焦點集中在 Nvidia 上，但 AMD 和英特爾 GPU 類似增強功能的潛力也即將顯現，並有望對該行業產生更廣泛的影響。此次合作標誌著機器學習能力的重大飛躍，為人工智慧平台的未來創新和效率打開了大門。