Exafunction

Efficient deep learning at scale

[Exafunction @exafunction]

1/ [New Post] ML Deployment: When the Big Problem is… Going Big

The first of our non-technical blog posts, on the problems with ML deployment:

https://t.co/2Gf5SpNBqd

[Exafunction @exafunction]

What our team has been up the last few months! Live on @ProductHunt
🔗https://t.co/wI2M9c84hl

[Windsurf Current @WindsurfCurrent]

100 upvotes and counting on @ProductHunt today!! Check out what early users have been saying about their Codeium experience: https://t.co/fE2IgxdRdQ

One of our favorite testimonials so far: "Be smart and sign up, it's free."

[Windsurf Current @WindsurfCurrent]

You could say the Codeium.vim plugin was a success 🎉

🏆 Top 5 on HackerNews for hours
⭐️ Over 400 stars on Github
🖋️ Featured in newsletters like TLDR and Changelog Nightly

Get *free* AI powered autocomplete in your favorite IDE at https://t.co/b9pkFq4PX9 - don't miss out!

[Windsurf Current @WindsurfCurrent]

We made a lot of progress in December, and the party is going to continue into 2023! 📈

https://t.co/ceDLqpv6Yq

[Exafunction @exafunction]

We've been working on @codeiumdev the last couple months, and published some of our infra-related learnings on realtime LLM serving with @swyx - check out the post and Codeium!

[swyx 🔜 @aiDotEngineer @swyx]

🆕 What Building "Copilot for X" Really Takes

https://t.co/pQ33bmehUW

Everyone's talking about "Copilot for X", but few have actually built one.

Presenting my first guest-post from @_anshulr, on building @codeiumdev! The first ever roadmap to a "generative AI moat" I've seen.

[Exafunction @exafunction]

7/ Together, ExaDeploy and AWS Inferentia unlock increased performance and cost-savings for inference workloads at scale.

Check out the AWS ML blog for the full post with a code sample :)

https://t.co/v28MHJT73p

[Exafunction @exafunction]

1/ [New Post] Exafunction With Inferentia

In this post, we dive into how Exafunction can be used with AWS Inferentia to give you both the best software and hardware efficiency gains:

https://t.co/v28MHJT73p

[Exafunction @exafunction]

6/ We arrive at the following cost and latency results:

[Exafunction @exafunction]

Ew!!!!!

[Aditya Naganath @anaganath]

An emergent class of infrastructure companies uniquely built for the era of deep learning / LLMs in the enterprise:

Training: @MosaicML
Inference Hosting: @exafunction , @BananaDev_
Security: @hiddenlayersec
Debugging: Chroma
Networking: @dust4ai

[Exafunction @exafunction]

9/ Join our community Slack to stay in the loop and learn more about ExaDeploy! And check out our website for the full case study :)

https://t.co/vyo14GfR4K

[Exafunction @exafunction]

1/ [New Post] Case Study: Motive

In this post, we dive into our first case study on how ExaDeploy has helped cutting-edge ML companies save money and accelerate their time-to-market, all with minimal engineering integration time!

https://t.co/cPDlsWTIis

[Exafunction @exafunction]

8/ ExaDeploy has enabled Motive to take on projects that were previously financially unfeasible. Moving forwards, Exafunction also plans on working with Motive to make their models run even faster on different kinds of GPUs, among other potential avenues of exploration.