How to deploy low-latency compound AI systems at scale with Baseten Chains
Deploying AI workflows with multiple models is hard. Keeping them performant at scale is even harder.
Traditional approaches force developers to manually orchestrate models and processing steps, tightly couple entire workflows to hardware, and accept excess latency from data egress and compute bottlenecks. This results in complex, monolithic deployments that are costly, inefficient, and difficult to maintain.
With Baseten Chains, you can build and deploy ultra-low-latency compound AI systems. Chains simplifies model orchestration, eliminates performance bottlenecks, and keeps inference cost-efficient—all with a developer-friendly experience.
Join us on March 6th and learn how to:
Deploy multi-model AI workflows without managing complex orchestration
Optimize latency and scale with per-step autoscaling and custom hardware
Reduce infrastructure costs while improving reliability and performance
Build AI pipelines for use cases like RAG, transcription, agents, and AI phone calling
We’ll walk through real-world use cases, showcase live demos, and answer your questions about deploying compound AI in production live.
Register now and secure your spot!
Host
Speakers
Announcing Baseten’s $75M Series C
Baseten raised a $75M Series C to power mission-critical AI inference for leading AI companies.
How multi-node inference works for massive LLMs like DeepSeek-R1
Running DeepSeek-R1 on H100 GPUs requires multi-node inference to connect the 16 H100s needed to hold the model weights.
Testing Llama 3.3 70B inference performance on NVIDIA GH200 in Lambda Cloud
The NVIDIA GH200 Superchip combines an NVIDIA Hopper GPU with an ARM CPU via high-bandwidth interconnect
Baseten Chains is now GA for production compound AI systems
Baseten Chains delivers ultra-low-latency compound AI at scale, with custom hardware per model and simplified model orchestration.
San Jose Sharks Vs Carolina Hurricanes @ GTC
Join us in a private suite for the Hurricanes vs Sharks game during NVIDIA GTC.
NYC Tech Breakfast Club: ML Engineering Leaders
Tech Breakfast Club is teaming up with Baseten to host a Tech Breakfast Club for CTOs and machine learning leaders in New York.
Private, secure DeepSeek-R1 in production in US & EU data centers
Dedicated deployments of DeepSeek-R1 and DeepSeek-V3 offer private, secure, high-performance inference that's cheaper than OpenAI
How to run DeepSeek-R1 in production
Learn what sets DeepSeek-R1 apart from other LLMs, why running it in production is challenging, and how to get a dedicated and secure DeepSeek-R1 deployment.
NYC Tech Breakfast Club: ML Engineering Leaders
Join us for the NYC Tech Breakfast Club for ML Engineers
