Deep-learning 4

• KV cache – The how not to waste your FLOPS starter Nov 21, 2024
• Attention scores, Scaling and Softmax Nov 11, 2024
• The Hidden Beauty of Sinusoidal Positional Encodings in Transformers Nov 1, 2024
• Vanishing and exploding Gradients – A non-flat-earther's perspective. Oct 28, 2024