MK1 Docs#
Welcome to the MK1 Docs, where you’ll find all the information you need to get started with MK1 products.
MK1 Flywheel#
We believe that the new AI economy will be powered by efficient Generative AI Inference.
Enter MK1 Flywheel, our enterprise-grade inference engine designed from the ground up for large scale Generative AI workloads. Our current version targets inference for Large Language Models, and unlocks the best performance and the lowest cost on both NVIDIA and AMD GPUs.
The easiest way to take Flywheel for a spin is through one of our cloud offerings:
- Modal
Be up and running with powerful GPUs on Modal’s easy-to-use cloud platform.
Experience up to 2x cost savings for document processing and up to 3x faster latency for real-time chat apps.
- SageMaker
Great option for customers already in the AWS ecosystem.
For self hosting options, we invite you to reach out to us with your specific needs and discover how Flywheel can help you boost performance and cut costs.