TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Show HN: depot.ai – easily embed ML / AI models in your Dockerfile

7 pointsby jacobwgalmost 2 years ago
Hey HN! We&#x27;re excited to launch https:&#x2F;&#x2F;depot.ai today - depot.ai is an open-source Docker registry that makes it easy to embed public models from Hugging Face in your Docker images using a `COPY`:<p><pre><code> # Copy all files from the model repo to the current WORKDIR COPY --link --from=depot.ai&#x2F;runwayml&#x2F;stable-diffusion-v1-5 &#x2F; . # COPY just one file from the model repo to the current WORKDIR COPY --link --from=depot.ai&#x2F;runwayml&#x2F;stable-diffusion-v1-5 &#x2F;v1-5-pruned.ckpt . </code></pre> To optimize build speed, cache hits, and registry storage, we&#x27;re building each image reproducibly and indexing the contents with eStargz[0]. The image is stored on Cloudflare R2, and served via a Cloudflare Worker. Everything is open source[1]!<p>Compared to alternatives like `git lfs clone` or downloading your model at runtime, embedding it with `COPY` produces layers that are cache-stable, with identical hash digests across rebuilds. This means they can be fully cached, even if your base image or source code changes.<p>And for Docker builders that enable eStargz, copying single files from the image will download <i>only</i> the requested files. eStargz can be enabled in a variety of image builders[2], and we’ve enabled it by default on Depot[3].<p>Here’s an announcement post with more details: https:&#x2F;&#x2F;depot.dev&#x2F;blog&#x2F;depot-ai.<p>We’d love to hear any feedback you may have!<p>[0] https:&#x2F;&#x2F;github.com&#x2F;containerd&#x2F;stargz-snapshotter&#x2F;blob&#x2F;main&#x2F;docs&#x2F;estargz.md<p>[1] https:&#x2F;&#x2F;github.com&#x2F;depot&#x2F;depot.ai<p>[2] https:&#x2F;&#x2F;github.com&#x2F;containerd&#x2F;stargz-snapshotter&#x2F;blob&#x2F;main&#x2F;docs&#x2F;integration.md#image-builders<p>[3] https:&#x2F;&#x2F;depot.dev

1 comment

araghuvanshialmost 2 years ago
We use this product at pyq and I have to say, the speedup in our build times is amazing. Especially when HuggingFace is slow&#x2F;backed up