Ampere instances on OCI are some of the most cost-effective instances available in the Cloud today. OCI Ampere A1 started this with extremely high-performance shapes that with the ability to use the OCI Flex Shapes feature to provision at the single core resolution making this infrastructure very efficient. Ampere A2 recently launched adds the new AmpereOne architecture to the inventory for shapes with up to 160 cores. Ampere publishes 3 optimized frameworks for ease of access on OCI tested and proven AI inference for any model compatible with the framework.
Ampere Frameworks offer the best-in-class Artificial Intelligence inference performance on any Ampere Processor platform in the cloud or bare metal. Models and software written to the optimized framework’s respective API’s can run as-is, without any modifications.
