@BananaDev_

Serverless GPUs for Inference 🍌

 San Francisco
banana.dev
Joined August 2019
  • Tweets1.3K
  • Following23
  • Followers3.9K
218Media
Have you tried out our new experiment yet? anythingtojson.com 100% guaranteed output structure. Give it a go. API access available.
3
2
21
10,420
Announcing ✨Adequately General Intelligence✨ LLMs are overrated. You can now use our Fructose LLM client to swap out your LLM with (mostly) intelligent humans to answer your queries! Just use the @human decorator instead of @ai
3
2
3
43
14,120
One of the biggest magic-feeling AI moments for me: Using "Fructose" Python library allows you to simply write what your function does, and AI will do the rest, guaranteeing conversion the correct type! github.com/bananaml/fructose #GPT4 #AI #python
2
2
13
4,056
Banana retweeted
swlkr
@swlkr6 Mar 2024
im really excited about this fructose idea there's no reason it should be just python this can be done in rust with proc macro attributes on fns and structs check the link
6
5
26
5,002
I built a very simple demo for an alien creature merging/breeding game with infinitely varied and never-ending content using Scenario and a strongly typed LLM function framework that we’re tinkering with at Banana. Key steps in thread below, as well as the link to try it. 🧵👇
5
13
9
53
16,260
What's next? 👇
2
2
3,294
🤷
1
1,936
Some bittersweet news to share: We've decided to sunset the @BananaDev_ serverless GPU product The platform will remain up for two months to allow our users to find alternatives. Users were informed of this yesterday, and we've received nothing but love and support.
14
3
2
121
32,599
Changelog! This week we bring you - Pricing change (re-announcement) - Multicloud support, Runpod VM backend added - Private docker registry banana.dev/blog/changelog-04…
1
3
1,816
Do 🦀 eat 🍌?
Erik Kaunismäki
@ErikKaum10 Jan 2024
Looking into the @huggingface candle library (github.com/huggingface/candl…) - minimal ML framework - written in rust so compiles to a single binary - get's the job done 🚀
4
2,192
lawyers said we can post this now
9
1,387
DON'T DIE (from GPU burn)
1
3
8
5,105
Changelog #043 All About Builds! banana.dev/blog/changelog-04…

Changelog 043 - Banana

Changelog for Friday, December 15, 2023

banana.dev
1
2
6
2,129
pro tip: name your company after an incredibly affordable fruit
jan
@ironcarbs10 Dec 2023
In case you are wondering: 468 pounds of bananas 🍌 are $310.44 at Costco 🫡
4
1,836
Happy to meet @kylejohnmorris from @BananaDev_ at @AGIHouseSF I tell you all, he is bananas 🍌🍌 – at San Francisco, CA
1
11
1,283
Announcement✨ @BananaDev_ now takes ZERO margin on GPU time. After working with thousands of teams running AI inference in production, it’s become clear that platform margins are misaligned. Our incentives are to help you scale, not to take a cut. banana.dev

Banana - GPUs For Inference

Inference hosting for AI teams who ship fast and scale faster.

banana.dev
5
23
3
138
47,637
No one knows how the future AI stack will look So we’re bringing the creators who're shaping it to @AGIHouseSF for a workshop-style hackathon - @perplexity_ai, @arizeai, @MultiON_AI, @sid_ai, @BananaDev_, @llama_index , @weaviate_io, @anyscalecompute Come by this Saturday & get first-hand feedback tailored to your product across the LLM stack!! join@ partiful.com/e/4pU3wpG0yzKga…
2
14
2
48
16,498
We fought the crypto bots and won: banana.dev/blog/changelog-04…
1
3
1,033
Changelog time! This week we bring you: - Billing Analytics - Rolling Deploys - Mistral 7B Template banana.dev/blog/changelog-04…
1
1
7
2,154
We've put together a guide for deploying Mistral 7B (with token streaming), for teams who are looking to diversify their LLM deployments to open-source models. Check it out: banana.dev/blog/how-to-deplo…
1
19
1,468
Load more