tl.where(mask, x, 0) does: conditional select to handle boundary conditions

tl.arange(0, BLOCK_SIZE) creates: a range of indices within the current block

How do you pick specific items from a list without going through them one by one?

KL divergence is always ≥ 0 and equals 0 only when P = Q exactly

Why can't we just compare two things directly?

classifier-free guidance does: interpolates between conditional and unconditional generation

"Classifies samples as either conditioned or unconditioned, guiding generation towards desired outcomes."

tl.program_id(0) returns: the index of the current parallel block

tl.program_id(0) returns: the index of the current parallel block

sinusoidal position encoding works: each dimension has a different frequency

Sinusoidal position encoding assigns unique frequencies to each dimension, enabling the model to distinguish positions effectively

Conditional probability

P(A|B) = P(A ∩ B) / P(B)