Inference scaling and optimization

Model Acceleration and Optimization

Inference system and infrastructure

https://eng.snap.com/applying_gpu_to_snap

https://eng.snap.com/introducing-bento

https://eng.snap.com/machine-learning-snap-ad-ranking

https://blog.tensorflow.org/2023/04/training-recommendation-model-with-dynamic-embeddings.html

GCP globally distributed control plane

Andromeda: https://research.google/pubs/pub48645/

Private Service Connect: https://cloud.google.com/blog/products/networking/access-managed-services-globally-with-private-service-connect

Cloud Computing: http://www.cs.cmu.edu/~msakr/15619-s18/index.html