Comparing techniques in LLM application development

LLM inference optimization: Speculative Decoding

Implementing distributed transformer MLP layer in pytorch

Serving latency considerations for embedding recommender systems

Mixed precision training

Voyager LLM paper notes

Deep learning book(Goodfellow) Chapter 8 Optimization

Deep learning book(Goodfellow) Chapter 7 Regularization

Deep learning book(Goodfellow) Chapter 6

Optimizers

Use einops to patchify image

Tech talk notes on "Building Software Systems At Google and Lessons Learned"

Work in progress Notes CIFAR10 resnet exploration