Decode Phase

Find the wrong move in 'decode is slow, so let's switch to a smaller-FLOP model'

Walk through what actually happens during the prefill phase of an LLM forward pass.

What unit measures GPU memory bandwidth and why does that number cap decode speed?

max_tokens vs stop: pair each parameter with the cap it enforces on the completion.

Define LLM inference and explain how it differs from training.

Predict the bandwidth-vs-compute latency of a single Llama-70B decode step on H100

Spot the errors in this 'API is slow because of network and tokenizer' explanation