How to run multi-model inference in production with Baseten Chains
Learn how Baseten Chains can upgrade your multi-model inference workflows. In this session, we dive deep into what Baseten Chains is, the vision behind its creation, its underlying mechanics, and how you can use it to enhance your AI products.
What you'll learn:
Introduction to Baseten Chains: Understand the core features and capabilities that set Baseten Chains apart in the AI landscape.
The why behind Chains: Discover the motivations driving the development of Baseten Chains, and how it addresses key challenges in AI deployment.
How Baseten Chains works: Gain insights into the architecture and technology stack powering Baseten Chains, and how you can get started today.
Best practices and use cases: Explore practical examples and best practices to maximize the impact of Baseten Chains on your AI initiatives.
Watch this webinar on-demand: Fill out the form and the webinar link will be emailed to you!
Host
Speakers
Comparing tokens per second across LLMs
To accurately compare tokens per second between different large language models, we need to adjust for tokenizer efficiency.
New in May 2024
AI events, multicluster model serving architecture, tokenizer efficiency, and forward-deployed engineering
Comparing few-step image generation models
Few-step image generation models like LCMs, SDXL Turbo, and SDXL Lightning can generate images fast, but there's a tradeoff when it comes to speed vs quality.
How latent consistency models work
Latent Consistency Models (LCMs) improve on generative AI methods to produce high-quality images in just 2-4 steps, taking less than a second for inference.
New in April 2024
Use four new best in class LLMs, stream synthesized speech with XTTS, and deploy models with CI/CD
Create custom environments for deployments on Baseten
Test and deploy ML models reliably with production-ready custom environments, persistent endpoints, and seamless CI/CD.
Introducing canary deployments on Baseten
Our canary deployments feature lets you roll out new model deployments with minimal risk to your end-user experience.
