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.

Docker Model Runner

100 pointsby kordlessagainabout 1 month ago

10 comments

jpgvmabout 1 month ago
I&#x27;m looking at using OCI at $DAY_JOB for model distribution for fleets of machines also so it&#x27;s good to see it&#x27;s getting some traction elsewhere.<p>OCI has some benefits over other systems, namely that tiered caching&#x2F;pull-through is already pretty battle-tested as is signing etc, beating more naive distribution methods for reliability, performance and trust.<p>If combined with eStargz or zstd::chunked it&#x27;s also pretty nice for distributed systems as long as you can slice things up into files in such a way that not every machine needs to pull the full model weights.<p>Failing that there are P2P distribution mechanisms for OCI (Dragonfly etc) that can lessen the burden without resorting to DIY on Bittorrent or similar.
评论 #43681299 未加载
评论 #43682381 未加载
israrkhanabout 1 month ago
Be aware of licensing restrictions. Docker Desktop is free for personal use, but it requires a paid license if you work for an organization sized 250+. This feature seems to be available in Docker Desktop only.
评论 #43680750 未加载
leowoo91about 1 month ago
I don&#x27;t understand why add another domain-specific command to a container manager and go out of scope for what the tool was designed for at first place.
评论 #43679076 未加载
评论 #43680621 未加载
评论 #43690303 未加载
rockwotjabout 1 month ago
Looks exactly like ollama but built into Docker desktop? Anyone know of any differences?
评论 #43678593 未加载
评论 #43677457 未加载
评论 #43677209 未加载
评论 #43677230 未加载
tgmattabout 1 month ago
Seems like <a href="https:&#x2F;&#x2F;kitops.org&#x2F;" rel="nofollow">https:&#x2F;&#x2F;kitops.org&#x2F;</a> but fewer features.
Havocabout 1 month ago
Can’t say I&#x27;m a fan of packaging models as docker images. Feels forced - a solution in search of a problem.<p>The existing stack - a server and model file - works just fine. There doesn’t seem to be a need to jam an abstraction layer in there. The core problem docker solves just isn’t there
评论 #43690314 未加载
评论 #43680346 未加载
avs733about 1 month ago
I&#x27;m going to take a contrarian perspective to the theme of comments here...<p>There are currently very good uses for this and likely going to be more. There are increasing numbers of large generative AI models used in technical design work (e.g., semiconductor rules based design&#x2F;validation, EUV mask design, design optimization). Many&#x2F;most don&#x27;t need to run all the time. Some have licensing that is based on length of time running, credits, etc. Some are just huge and intensive, but not run very often in the design glow. Many are run on the cloud but industrial customers are remiss to run them on someone else&#x27;s cloud<p>Being able to have my GPU cluster&#x2F;data center be running a ton of different and smaller models during the day or early in the design, and then be turned over to a full CFD or validation run as your office staff goes home seems to be to be useful. Especially if you are in anyway getting billed by your vendor based on run time or similar. It can mean a more flexible hardware investment. The use casae here is going to be Formula 1 teams, silicon vendors, etc. - not pure tech companies.
superb_devabout 1 month ago
Looks like Docker is feeling left out of the GenAI bubble. It’s a little late…
评论 #43680119 未加载
waffletowerabout 1 month ago
I have used Replicate Cog, built on docker, fairly heavily and and find it is a decent compromise of features. Docker taking this use case more seriously is quite welcome, though surprisingly late. Local metal GPU support (where available to the containerized application APIs), not currently available in Cog, is attractive though it would require generalization of application code to support containers executable via Cuda and Metal etc.
评论 #43688508 未加载
tuananhabout 1 month ago
they are about ~2 years late.
评论 #43681049 未加载
评论 #43690317 未加载