TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Ask HN: Looking for empirical advices on "serverless" ML hosting

2 点作者 tonyabracadabra11 个月前
Hey HN,<p>I&#x27;m exploring serverless platforms for hosting custom machine learning models and could use some advice from those who have experience with these services. I get that &quot;serverless&quot; still involves servers, but I&#x27;m looking at options that market themselves this way.<p>I&#x27;m considering:<p>modal.com runpod.io replicate.com beam.cloud<p>I&#x27;m curious about two main things: Pricing: How do the costs compare for running custom ML models on these platforms? Any detailed breakdowns would be great. Cold Start Time: How quickly can each platform start up a custom model from a cold start? Are there big differences in startup times?<p>If you&#x27;ve used any of these, I&#x27;d love to hear your thoughts and experiences.

暂无评论

暂无评论