Glossary · Term

fp16

← all terms

Definition

Plain language

A compact way of storing the numbers inside a neural network using sixteen bits, to save memory and run faster.

As stated in the literature

Half-precision floating point, a 16-bit format with a 5-bit exponent and 10-bit mantissa; distinct from bf16, which trades mantissa bits for a wider exponent range. Common in inference kernels and as a quantization target.

Also called: half-precision

Why it matters: It lets large models run faster and on less memory, which is why it's a common choice for serving models efficiently.

For example, storing a model's weights in this format uses half the memory of full-precision numbers, so a model can fit on a smaller graphics card.

Heard on the show

“… context, the kind of context you'd want for agentic workloads — at the same hidden dimension, in half-precision, would need three hundred eighty-four megabytes. …”
Episode 033 — Echo: The Paper Arguing You Never Needed a KV Cache for Retrieval

Mentioned in 2 episodes

  1. 033
    Echo: The Paper Arguing You Never Needed a KV Cache for Retrieval
  2. 027
    When AI Agents Build the Serving Stack: A Bet on Bespoke Infrastructure

Related terms