#ai

23 notes

• 2026
  • DecodeOctober 23
  • PrefillOctober 23
  • Building a Tiny Inference ServerOctober 21
  • Adam and AdamWOctober 12
  • Flavors of OptimizersOctober 12
  • PyTorch Fundamentals - From Tensors to Training a Neural NetworkOctober 12
  • SGD and SGD with MomentumOctober 12
  • Distributed Data ParallelismOctober 2
  • Model parallelismOctober 2
  • Strategies for scaling neural networks across multiple GPUsOctober 1
  • Knowledge DistillationSeptember 27
  • Proper distillation - type of knowledge distillationSeptember 27
  • ReLu activation functionSeptember 27
  • Tanh activation functionSeptember 27
  • LogitsSeptember 26
  • Sigmoid activation functionSeptember 26
  • Vanishing GradientSeptember 26
  • JevSeptember 20
  • LLM Compute constraintsSeptember 18
  • Prompt InjectionSeptember 18
  • Semantic CachingSeptember 18
  • Agent Memory TypesJanuary 18
  • How Agents write to external long term memoryJanuary 18