CodeProject.AI Server is a self contained service that software developers can include in, and distribute with, their applications in order to augment their apps with the power of AI.
The new TPURunner architecture allows for any number of TPUs to share the work on any model segment. This way, with multi-TPU systems, we aren't stuck with a single segment being a bottleneck. Additional TPUs are dynamically allocated from fast segments to help with slow segments. This opens up additional strategies with how the segments are compiled and allocated for systems with many TPUs. Many-TPU systems also scale up much more elegantly, as do systems with mixed TPU architectures or interface types.
The new TPURunner architecture allows for any number of TPUs to share the work on any model segment. This way, with multi-TPU systems, we aren't stuck with a single segment being a bottleneck. Additional TPUs are dynamically allocated from fast segments to help with slow segments. This opens up additional strategies with how the segments are compiled and allocated for systems with many TPUs. Many-TPU systems also scale up much more elegantly, as do systems with mixed TPU architectures or interface types.
New segment archives can be downloaded from this archive. Also contains ipcam-general for YOLOv8: https://drive.google.com/file/d/1EZMvBW9ykcj3k-SZPuUl5gIDDSiRR7lU/view?usp=sharing