Tensors & Neural Plumbing

Shapes, matmuls, forward and backward passes, parameter counts, memory footprints.

18concepts
211flashcards
138minutes of reading
  1. 01 Accumulation Precision and Mixed-Dtype Plumbing Storing weights in 16 bits is safe because almost nothing is actually computed in 16 bits — matmuls accumulate in fp32, reductions run in fp32, and the master copy is fp32, and every documented failure of low-precision training is one of these rules being broken. advanced 8m 15 cards
  2. 02 Batch Invariance and Numerical Reproducibility Temperature zero does not give the same answer twice, and the reason is neither random seeds nor GPU atomics; it is that reduction kernels change their split strategy with batch shape, so your logits depend on which other requests happened to be in flight. advanced 8m 28 cards
  3. 03 Signal Propagation and Initialisation How a network's weights are initialised decides, before a single gradient step, whether activations and gradients stay in a trainable range or collapse to zero or explode across depth. advanced 9m 4 cards
  4. 04 Training Memory Footprint A model's weights are the smallest part of its training memory bill; optimiser state, gradients, and activations usually cost several times more, and knowing the breakdown explains why training needs far more memory than inference. advanced 9m 4 cards
  5. 05 muP and Hyperparameter Transfer Under standard parametrisation the best learning rate drifts as a model gets wider, so every scale-up is a fresh search; muP rescales initialisation, learning rates, and multipliers per layer so the optimum stays put and can be tuned on a small proxy model. advanced 8m 15 cards