Stories, updates, and other resources from Baseten.
New in May
Open-source models continue to bridge the gap on results quality versus their closed-source counterparts. Discover new models for text generation and text-to-speech, learn more about the GPUs they run on, and plug in to the community forming around open-source models in this newsletter.
Understanding NVIDIA’s Datacenter GPU line
NVIDIA has dozens of GPUs that can serve ML models of different sizes. But understanding the performance and cost of these different cards, not to mention just keeping the names straight, is a challenge. This guide helps you navigate NVIDIA’s datacenter GPU lineup.
Comparing GPUs across architectures and tiers
Advertising for GPUs is designed to drive excitement and demand year after year. But as the industry evolves, certain benchmarks remain consistent from generation to generation. This guide helps you make fair comparisons between graphics cards based on your real-world needs.
Comparing NVIDIA GPUs for AI: T4 vs A10
This post outlines the key specs to understand when comparing GPUs as well as factors to consider like price, availability, and opportunities for horizontal scaling. Then, we apply these ideas to choose between two common datacenter GPUs—the NVIDIA T4 and A10—for realistic generative AI workloads.
How we achieved SOC 2 and HIPAA compliance as an early-stage company
In March of 2023, we announced that Baseten is SOC 2 Type II certified and HIPAA compliant. Pursuing compliance isn’t a trivial decision, but our existing security posture and development practices made becoming compliant a relatively seamless process.
Deploy StableLM with Baseten and Truss
Stability AI has released StableLM, a series of models that are ideal for generating both text and code. This post will show you how to quickly and easily deploy these models and make them available behind a REST API endpoint by using Baseten and Truss.
Announcing Blueprint: fine-tuning and serving infrastructure for developers
Today we're launching Blueprint. Blueprint is a fine-tuning and serving infrastructure platform for software developers who are comfortable with backend and frontend engineering but lack expertise in model development and hosting.
DreamCanvas: a FigJam plugin for fine-tuning Stable Diffusion
We have only started to see is how Stable Diffusion will get incorporated into existing and greenfield creative workflows. And this will be an exciting step in the evolution of AI-powered tools over the next months and years. DreamCanvas is an exploration of this space built with Blueprint.
Building a Lensa-like app with Blueprint
Blueprint works great for building user-facing applications with fine-tuned models. One popular type of app using fine-tuning is AI avatar generation apps. This project implements a simple version of an avatar generation app like Lensa using Blueprint.