Concept
Quantisation
Storing a model's weights, and sometimes its activations or cache, with fewer bits per number, such as 8 or 4 instead of 16, to cut memory use and speed up computation at some possible cost in accuracy.
Relations
- influences
Concept
Storing a model's weights, and sometimes its activations or cache, with fewer bits per number, such as 8 or 4 instead of 16, to cut memory use and speed up computation at some possible cost in accuracy.