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.

AWS AI Stack – Ready-to-Deploy Serverless AI App on AWS and Bedrock

43 pointsby fitzgera1d8 months ago

7 comments

ac3608 months ago
Increasingly bullish on AWS Bedrock.<p>• Devs forever want choice.<p>• Open-source LLMs are getting better<p>• Anthropic ships fantastic models<p>• Doesn&#x27;t expose your app’s data to multiple companies<p>• Consolidated security, billing, config in AWS<p>• Power of AWS ecosystem
评论 #41513383 未加载
agcat8 months ago
You can check out this technical deep dive on Serverless GPUs offerings&#x2F;Pay-as-you-go way. This includes benchmarks around cold-starts, performance consistency, scalability, and cost-effectiveness for models like Llama2 7Bn &amp; Stable Diffusion across different providers -<a href="https:&#x2F;&#x2F;www.inferless.com&#x2F;learn&#x2F;the-state-of-serverless-gpus" rel="nofollow">https:&#x2F;&#x2F;www.inferless.com&#x2F;learn&#x2F;the-state-of-serverless-gpus</a>... .Can save months of your time. Do give it a read.<p>P.S: I am from Inferless
rmbyrro8 months ago
Last time I checked Bedrock was quite expensive to operate in a small scale.
评论 #41513425 未加载
评论 #41513298 未加载
ethagnawl8 months ago
I have not read too deeply into this but, do any of these serverless environments offer GPUs? I&#x27;m sure there are ... reasons but the lack of GPU support in Lambda and Fargate remains a major paint point for AWS users.<p>It&#x27;s been keeping me wrangling EC2 instances for ML teams but I do wonder how much longer that will last.
评论 #41513391 未加载
评论 #41513411 未加载
评论 #41513267 未加载
评论 #41513233 未加载
评论 #41513284 未加载
fitzgera1d8 months ago
Introducing the AWS AI Stack<p>A serverless boilerplate for AI apps on trusted AWS infra.<p>• Full-Stack w&#x2F; Chat UI + Streaming<p>• Multiple LLM Models + Data Privacy<p>• 100% Serverless<p>• API + Event Architecture<p>• Auth, Multi-Env, GitHub Actions &amp; more!<p>Github: <a href="https:&#x2F;&#x2F;github.com&#x2F;serverless&#x2F;aws-ai-stack">https:&#x2F;&#x2F;github.com&#x2F;serverless&#x2F;aws-ai-stack</a><p>Demo: <a href="https:&#x2F;&#x2F;awsaistack.com" rel="nofollow">https:&#x2F;&#x2F;awsaistack.com</a>
brap8 months ago
I don’t get it. How many people need to deploy their own custom AI chat apps over standard models?
评论 #41513046 未加载
justanotheratom8 months ago
Then need to go one step further and do what Replit did - AI Engineer generates code that gets deployed to this AWS AI Stack.