Lago’s Post

I *LOVE* their name 🍱 🇯🇵 🥢... but it's not the only thing to love about BentoML 😇 BentoML enables companies to build "compound AI systems", by unifying the development and development experience across: 1️⃣ Efficient model inference 2️⃣ Fully customizable application code 3️⃣ Scalable compute infrastructure to work seamlessly together AI teams can therefore focus on building the core product and ship faster! For example, TomTom, a leader in mapmaking and navigation technologies, uses BentoML for rapid AI experimentation and deployment, helping streamline its model serving process, especially for large language models (LLMs). Their user base is diverse (both geographically and in terms of industries!) and counts other enterprises such as: - NAVER Corp, South Korea’s *largest search engine*, which employs BentoML for multiple machine learning use cases - Mission Lane (Credit card/Financial services), which benefits from its ability to rapidly scale and future-proof their ML infrastructure. Our team at Lago also deeply resonate with BentoML's commitment to open-source and their "enterprise ready approach", check out their repos, and join their massive community! - 🍱 BentoML: The Unified Serving Framework for AI Systems - 🦾 OpenLLM: Self-Hosting LLMs Made Easy (Links in the comments!) We've been excited and very honored to partner with the all star team: 🙌 Sean Sheng Steve G. Fog Dong and of course Chaoyu Yang ✨