Sam Armstrong

Huge congrats to the team at Ivy 👏🔥 Kornia is the leading computer vision library, and now it now supports TensorFlow, JAX and NumPy out the box! Check out the example below ⬇️, integrations with many more libraries coming soon 👀 Keep up the great work @S_Armstr, @itsharismahmood, Yusha💪

We’re excited to announce Ivy is partnering with Kornia, allowing Kornia to be used with TensorFlow, JAX, and NumPy for the first time! You can use Kornia's new `to_tensorflow()`, `to_jax()` and `to_numpy()` methods, which take advantage of Ivy’s transpiler, to use Kornia in your framework of choice. Try it out now in the latest Kornia version! (0.7.4) kornia.readthedocs.io/en/latest/get-… Ivy on GitHub: github.com/ivy-llc/ivy Ivy Demos: docs.ivy.dev/demos/examples…

Very excited to release our Model Hub unify.ai/hub 😍 - a collection of LLM endpoints with live runtime benchmarks all plotted across time 📈 We currently have 21 models provided by: @anyscalecompute, @perplexity_ai, @replicate, @togethercompute, @octoml, @MistralAI and @OpenAI, with many more on the roadmap. We test across different regions (Asia, US, Europe), with varied concurrency and sequence length. By plotting across time, our dashboard highlights the stability and variability of the different endpoints, and their ongoing evolution across API updates and system changes. Our benchmarking code is open source: github.com/unifyai/aibenc… Following the great work from @withmartian last week, we mention several new findings in the thread below, focusing on llama-2-70b-chat and mixtral-8x7b-instruct-v0.1 ⬇️ Our unified API also makes it very easy to test and deploy these different endpoints in production, without needing to create several accounts 🔑 Our Hub is a work in progress, and we will be releasing new features every week 🚀 We are granting everyone $5 starting credits with a free top up of $2.50 every week, compatible with all major LLM providers (more coming soon!). You can sign up here console.unify.ai. Please tell us what you think, and we’ll quickly incorporate feedback into the next weekly release! 😊 As always - let’s unify AI! 🟢💪

Very excited to announce our brand new Reading Group YouTube Series, which kicks off with a livestream tomorrow at: 09:30 PT, 12:30 ET, 16:30 GMT, 18:30 CET, 22:00 IST [youtube.com/watch?v=bJFywl…] !👨‍💻 Dan FU [danfu.org] will be presenting his great work on Flash Attention ⚡[arxiv.org/abs/2205.14135] (Tri Dao, Daniel Y. Fu, Stefano Ermon, Atri Rudra, Christopher Ré) .Flash Attention has taken the world of transformers by storm, with SOTA runtime performance, and now integrations into most major frameworks and toolchains, including PyTorch, OpenAI/Triton etc. Going forward, we will continue the series with a new paper (and livestream) every week, with papers new and old, on a broad range of ML topics 📉🤖 Everyone is welcome to join in, follow along, and ask questions, regardless of your skill-level in AI. No question is too silly or too small! We will strive to answer all questions from the community during the reading group, and potentially expand into some interesting discussions during the course of the event 💡🤔 See you there - youtube.com/watch?v=bJFywl… #ai #community #sota #ml #researchpaper #research