Products 5
From its own site
- Shared EndpointsAn API service for accessing and running open AI models without managing infrastructure.
- Dedicated EndpointsAn AI inference service that runs models on reserved GPUs across hardware vendors.
- Custom ModelsA service for deploying custom AI models with kernel-level control.
- MAXA modeling and serving framework that optimizes AI model execution across different hardware accelerators.
- MojoA systems programming language for writing GPU kernels and other AI infrastructure code.
Products 5
From its own site
- Shared EndpointsAn API service for accessing and running open AI models without managing infrastructure.
- Dedicated EndpointsAn AI inference service that runs models on reserved GPUs across hardware vendors.
- Custom ModelsA service for deploying custom AI models with kernel-level control.
- MAXA modeling and serving framework that optimizes AI model execution across different hardware accelerators.
- MojoA systems programming language for writing GPU kernels and other AI infrastructure code.