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: How would one go about building an API for fine tuning?

8 点作者 samlhuillier超过 2 年前
Let&#x27;s say I wanted to build an API to let users upload images and the api would fine tune stable diffusion for them returning either a checkpoint or another api that let&#x27;s them run inference on the fine-tuned model. Does anyone have any architecture considerations&#x2F;issues they&#x27;d suggest?<p>Two things I&#x27;m considering:<p>- Would the problem with this approach of ad-hoc GPUs likely be cold boot? It would take a shit ton of time to load. Though with data center networks speeds that wouldn&#x27;t be too much of an issue - considering the fine-tuning itself would likely dwarf boot times.<p>- Is it possible to launch remote GPU instances ad-hoc from code? Is there a service that provides this service? Every time a call is made we&#x27;d spin up a GPU<p>Maybe the best approach for a V1 is to use the AWS SDK or something similar to just launch instances as calls come in.<p>Appreciate the help!

2 条评论

fswd超过 2 年前
I am using github actions with a local runner. It simply has a API via post for &#x2F;finetune (which takes multipart file upload). I have not yet deployed it, as it was a weekend project. The first task was actually fine tuning GPT-J-6B
DarthNebo超过 2 年前
You can check which of these work best for you-<p>1. Kubeflow pipelines<p>2. Cloud Run using GPU instances<p>3. Knative training<p>4. Banana.dev for launching GPU bound stuff without much cruft