RT by @yadong_xie: 🚀 Lepton AI's model API now supports #NodeJS calls! 🖥️ Build smarter and faster with the power of AI in your favorite runtime. Dive in now! #LeptonAIUpdate

RT by @brianzhan1: 🚀 Introducing Illusion Diffusion Model Apis by Lepton AI Transform your wildest creative ideas into mesmerizing visuals! 🎨✨ Dive into a world where imagination meets reality. #IllusionDiffusion #UnleashCreativity https://www.lepton.ai/playground/artistic?mode=illusion-diffusion

Check out the replay of the insightful talk by @leptonai's Head of Product on leveraging LLMs for investment insights from earnings calls. Learn how AI can help portfolio managers make informed decisions. https://youtu.be/-0_qvYaM_ZE #AI #InvestmentInsights

🚀Be sure to check out this week's UL! Featuring: ⚒️CloudGrep - a game-changing tool for searching through your cloud data @CadoSecurity ⚒️Python Magic - Running LLMs has been simplified to a single line of Python code, no Docker needed @LeptonAI https://bit.ly/3Q03CkO

R to @CalcCon: As a service, with hosted inference, @anyscalecompute ,@thefireworksai , http://gradient.ai. @LeptonAI does hosted inference.

R to @jiayq: (3/n) If you look at the total throughput, that translates to something like 1700 tokens/s! We did some optimizations at @LeptonAI and found that with additional optimizations, one can go north of 2500 tokens/s. Again, this is single A10 on the LLaMA 7B model.

Come to this year's #K1stWorld Symposium to hear from Yangqing Jia @jiayq, CEO & founder at @LeptonAI, former Director of @Facebook @Meta AI, and former VP of AI at @AlibabaGroup. Register here: https://www.k1st.world/#registrations #industrialAI #genAI #xAI #AIsolutions

R to @savvyRL: Fun fact: Lamini is based on the lamini tribe https://en.wikipedia.org/wiki/Lamini, including llamas!

R to @savvyRL: That was a good coincident!

R to @savvyRL: @LaminiAI @LeptonAI @LelapaAI

R to @LeptonAI: Ok，Thanks

R to @LeptonAI: 有没有chat那种直接使用的计划？

GPT is not always the best model. Mistral is better at legal reasoning, Llama is better at stories. @LeptonAI : ML engineering = Vercel : web dev. With a couple lines, you can deploy and fine tune any model, w/ metrics, monitoring, autoscaling in place: https://leptonai.medium.com/build-ai-the-easy-way-2a8b68c63723

R to @LeptonAI: Lepton is created by a group of passionate open source contributors behind caffe, onnx, pytorch 1.0, etcd and more. We’ve open-sourced substantial portions of our stack, and will continue to open-source more in the upcoming months. Stay tuned!

R to @LeptonAI: We transparently support PyTorch, HuggingFace Transformer, and other common AI libraries at the base. We also work closely with awesome open source libraries like vLLM - in fact, launching vLLM has never been easier.