What is Sliding Window Attention?

Removing less important model weights or neurons to reduce size and compute.

Pricing where costs scale with API calls, tokens, inference time, or consumed compute.

An empirical relationship showing how performance improves with model size, data, or compute.

A model where many parameters are zero or inactive to reduce computation.

An inference acceleration method where a small draft model proposes tokens that a larger model verifies in parallel.

The maximum amount of input tokens a language model can process at once.