Customize Consent Preferences

We use cookies to help you navigate efficiently and perform certain functions. You will find detailed information about all cookies under each consent category below.

The cookies that are categorized as "Necessary" are stored on your browser as they are essential for enabling the basic functionalities of the site. ... 

Always Active

Necessary cookies are required to enable the basic features of this site, such as providing secure log-in or adjusting your consent preferences. These cookies do not store any personally identifiable data.

No cookies to display.

Functional cookies help perform certain functionalities like sharing the content of the website on social media platforms, collecting feedback, and other third-party features.

No cookies to display.

Analytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics such as the number of visitors, bounce rate, traffic source, etc.

No cookies to display.

Performance cookies are used to understand and analyze the key performance indexes of the website which helps in delivering a better user experience for the visitors.

No cookies to display.

Advertisement cookies are used to provide visitors with customized advertisements based on the pages you visited previously and to analyze the effectiveness of the ad campaigns.

No cookies to display.

上海的陆家嘴
0

OpenAI 宣布推出全新功能“预测输出”,让 GPT-4o的生成速度大幅提升,最高可达 5 倍。这一功能的核心在于跳过已知内容,直接从预测结果开始生成,从而大幅缩短生成时间。

编程领域率先受益:

FactoryAI 与 OpenAI 合作开发了该功能,并在编程任务中取得显著成果。实验结果显示,使用“预测输出”的 GPT-4o 响应时间比之前快了 2-4 倍,同时保持高精度。官方数据表明,原先需要 70 秒完成的编程任务,现在仅需 20 秒。

网友实测验证速度提升:

消息一出,众多网友纷纷进行实测,验证“预测输出”的实际效果。Firecrawl 创始人 Eric Ciarla 使用该功能将博客文章转化为 SEO 内容,并表示速度“超级快”。其他网友也分享了类似的体验,例如将代码中的详细信息更改为随机文本片段,速度明显提升。

技术原理:

OpenAI 解释称,在某些情况下,LLM 的大部分输出都是可预测的。例如,修改代码时,大部分内容可能保持不变。通过将现有内容作为预测输入,模型可以更快地生成最终结果。

使用限制和注意事项:

目前,“预测输出”仅支持 GPT-4o 和 GPT-4o mini 模型,且以 API 的形式提供。此外,该功能不支持某些 API 参数,例如 n 值大于 1、logprobs、presence_penalty 大于 0 等。

未来展望:

“预测输出”的推出标志着 LLM 生成速度的显著提升,为开发者和用户带来了更多便利。未来,OpenAI可能将该功能扩展到更多模型和场景,进一步提升 LLM 的效率和应用价值。

参考文献:

[1] OpenAI 官方文档:https://platform.openai.com/docs/guides/latency-optimization#use-predicted-outputs

[2] Twitter 讨论:https://x.com/OpenAIDevs/status/1853564730872607229

[3] Twitter 讨论:https://x.com/romainhuet/status/1853586848641433834

[4] Twitter 讨论:https://x.com/GregKamradt/status/1853620167655481411


>>> Read more <<<

Views: 0

0

发表回复

您的邮箱地址不会被公开。 必填项已用 * 标注