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.

Train an AI model once and deploy on any cloud

199 pointsby GavCoalmost 2 years ago

8 comments

politelemonalmost 2 years ago
I'm failing to see why k8s needs to be involved here - it's overkill for most model serving cases but its involvement here now adds additional overhead. So it's not really any cloud, it's any cloud where you're running your EKS/AKS etc.
评论 #36643160 未加载
评论 #36643317 未加载
thih9almost 2 years ago
Very off topic, every time I see nvidia expand towards AI products I'm reminded that they had every opportunity to expand towards crypto products and didn't. I like that they work on what they believe in - and skip if they don't. In a time when AI is becoming a buzzword, this feels refreshing.
评论 #36643303 未加载
评论 #36643279 未加载
评论 #36643316 未加载
评论 #36643673 未加载
评论 #36643731 未加载
评论 #36643224 未加载
评论 #36644401 未加载
评论 #36643910 未加载
评论 #36646577 未加载
ommzalmost 2 years ago
It would be nice if Nvidia did not enforce artificial driver and legal kneecaps to consumer Geforce cards for cloud usage to prop up their enterprise ones... but shareholder rights come before anyone.
评论 #36642944 未加载
评论 #36643251 未加载
评论 #36643048 未加载
评论 #36642859 未加载
评论 #36642966 未加载
villgaxalmost 2 years ago
It&#x27;s more on the framework that you use than nvidia at this point. Anything dockerized works with any compatible underlying hardware with no issues. Any optimization is again fragmented with FasterTransformer or TensorRT conversion with half baked layer supports which lags by 6months or more pretty much.<p>NVAIE license is what nvidia wants enterprises to pay for using their bespoke cards in shared VRAM configuration by knee capping consumer cards which can very well do the same job better with more cuda cores but lesser memory.<p>And don&#x27;t even get me started on RIVA stack<p>FP8 emulation is also never going to get backported instead only H100 &amp; 4090s can make use of it
评论 #36643118 未加载
评论 #36643220 未加载
csearsalmost 2 years ago
Congrats to the Run:ai team. This looks like a pretty big endorsement from Nvidia.
paganelalmost 2 years ago
The AI shovels industry is doing good business. Other than that, any major use-case behind the recent AI hype? One that has brought tangible benefits, or at the very least a positive ROI.
评论 #36643477 未加载
评论 #36643406 未加载
评论 #36644922 未加载
评论 #36643917 未加载
评论 #36646114 未加载
评论 #36646076 未加载
hospitalJailalmost 2 years ago
We need local models for our confidential data. Nvidia, we already can train using OpenAI or a beefy hosted server.<p>But this particular data is air gapped.
jokethrowawayalmost 2 years ago
Cool!<p>Is the cost AWS level of waste - or something reasonable?<p>I can get an A4000 with 16GB vram which can run some models for 140$ per month.<p>I can&#x27;t say the setup is anything special really but not having to do that has some value