Top all-time · #5005
Banana
Company blog · banana.dev/blog · on HN as eduntemanaistartups
Banana is the company blog at banana.dev, writing about ai and startups. Since 2022, 16 different Hacker News readers have linked it 23 times, most often “Banana to sunset their serverless GPU platform”. No feed was found, so read it on the site itself.
Too few sampled comments (12) to say how often HN recommends it.?
Why HN links it
HN commenters mention banana.dev as a serverless GPU service for deploying ML models, usually in lists of alternatives. Linked pages are product pages, deployment guides and a sunset notice, not essays.
Summarised by Claude from a sample of 12 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Inference hosting for AI teams who ship fast and scale faster.
Most-linked posts?
- /4 people · 4 mentions · first linked 2023-01-22
- /3 people · 3 mentions · first linked 2022-12-23
- Banana to sunset their serverless GPU platform3 people · 3 mentions · first linked 2024-02-07
- Banana Turboboot: a major decrease in cold boots for Serverless GPUs3 people · 3 mentions · first linked 2023-04-12
- Show HN: Banana.dev Serverless GPUs for Machine Learning Inference3 people · 3 mentions · first linked 2022-07-21
- How to Deploy Stable Diffusion to Production on Serverless GPUs2 people · 2 mentions · first linked 2022-08-29
- Deploy Whisper on Serverless GPUs in seconds2 people · 2 mentions · first linked 2022-09-21
What Hacker News says?
> What about alternatives? Custom models? Apart from the Big 3 (in no particular order): - https://together.ai/ - https://replicate.com/ - https://anyscale.com/ - https://baseten.co/ - https://modal.com/ - https://banana.dev/ - https://runpod.io/ - https://bentoml.com/ - https://brev.dev/ - https://octo.ai/ - https://cerebrium.ai/ ...
Comment linking /
on “Fly.io has GPUs now”Submitted Deploy Whisper on Serverless GPUs in seconds as a story · 24 points
HN discussionhere is a serverless GPU template for Stable Diffusion hosted on Banana's cloud platform. template: https://github.com/bananaml/serverless-template-stable-diffu... setup demo: https://www.banana.dev/blog/how-to-deploy-stable-diffusion-t...
Comment linking /blog/how-to-deploy-stable-diffusion-to-production
on “Try Stable Diffusion's Img2Img Mode”Submitted Show HN: Banana.dev Serverless GPUs for Machine Learning Inference as a story · 16 points
HN discussionFollowed this link to banana.dev. It appears that the company has sunset the product: https://www.banana.dev/blog/sunset
Comment linking /blog/sunset
on “Ask HN: How does deploying a fine-tuned model work”Submitted Banana: GPU Serverless That Doesn't Suck as a story · 5 points
HN discussionFor the inference part, you can dockerise your model and use https://banana.dev for serverless GPU. They have examples on github on how to deploy and I’ve done it last year and was pretty straightforward.
Comment linking /
on “Ask HN: How does deploying a fine-tuned model work”Submitted GPTrillion: A 1.5T Parameter Open-Source Model as a story · 4 points
HN discussionbanana.dev has announced sunsetting of their server GPUs offering on March 31st, 2024 https://www.banana.dev/blog/sunset
Comment linking /blog/sunset
on “Replicate vs. Fly GPU cold-start latency”Submitted Banana to sunset their serverless GPU platform as a story · 3 points
HN discussionHey! Would love to have you try https://banana.dev (bias: I'm one of the founders). We run A100s for you and scale 0->1->n->0 on demand, so you only pay for what you use. I'm at erik@banana.dev if you want any help with it :)
Comment linking /
on “Ask HN: What do you use for ML Hosting”Submitted Banana Turboboot: a major decrease in cold boots for Serverless GPUs as a story · 3 points
HN discussionIf you want to just dick around a bit check out https://www.banana.dev/ They offer serverless GPU deployments, pretty hassle free (compared to using AWS or azure)
Comment linking /
on “OpenAI CEO warns that GPT-4 could be misused for nefarious purposes”Submitted How to Deploy Stable Diffusion to Production on Serverless GPUs as a story · 2 points
HN discussionShoutout to https://banana.dev , couldn't have made this demo without their hosting
Comment linking /
on “Reverse engineer Stable Diffusion images”Submitted Serverless GPUs without the cold boots as a story · 1 points
HN discussionCaltech machine learning intro course: https://www.youtube.com/watch?v=mbyG85GZ0PI karpathy's Zero to Hero series ( https://www.youtube.com/playlist?list=PLAqhIrjkxbuWI23v9cThs... ) meta llama 2 - is open source https://github.com/facebookresearch/llama/tree/main Tools: ai - hosting Banana - Machine Learning Model Deployment on Serverless GPUs https://www.banana.dev pinecone - vector database: https://www.pinecone.i…
Comment linking /
on “Ask HN: In 2023 which is the best path to get good at machine and deep learning?”> 1 hour of audio processing with Whisper on Banana costs <30 cents. From their page on Whisper: https://www.banana.dev/deploy-whisper
Comment linking /deploy-whisper
on “Show HN: PodText.ai – Search anything said on a podcast, Highlight text to play”I think there's https://brev.dev and https://banana.dev
Comment linking /
on “New AI edits images based on text instructions (instructPix2Pix/imaginAIry)”Maybe not quite what you’re looking for, but I’ve seen some people mention banana.dev https://www.banana.dev/ Never used it myself, but looks like AWS Lambda/GCP Cloud Functions tailored to ML models.
Comment linking /
on “New AI edits images based on text instructions (instructPix2Pix/imaginAIry)”- nl · 2022-12-23
https://www.banana.dev/ have been working on the Lambda-style thing. I haven't tried it but looks very impressive.
Comment linking /
on “Bunny AI” Can only publicly answer one of these: - reusability of workloads: yes, introducing the community templates feature ( https://banana.dev/templates ) for common models has dramatically cut back on storage requirements and transfers. We're still majority custom code, but it's helped prevent us from exploding storage over people running the same "model of the week" As for caching / chunking, sounds like you're thinking…
Comment linking /templates
on “The State of Serverless GPUs”Hey! Banana cofounder here. Firstly, thank you so much for trying our service, we'll do our best to meet performance expectations and win you back! Re: #1 and #2, cold boots are the most vital thing for us to solve, because it fixes #1 directly and helps #2 indirectly. As we drive cold starts exponentially toward 0s (obv impossible but there's a near-zero asymptote to what's possible, limited only by disk read throu…
Comment linking /blog/turboboot
on “The State of Serverless GPUs”
