AI engineering glossary · Inference serving optimisation
What is zero-point?
Zero-point: An integer offset in asymmetric quantisation that says which stored integer represents the real value zero. It lets an uneven range of values, such as post-activation outputs that are all positive, use the whole integer range without wasting codes.
Zero-point: an example
For values between 0 and 6 stored as unsigned 8-bit, the zero-point is 0; for values between -1 and 5 it is about 43.
Related terms
More Inference serving optimisation terms
- Acceptance rate
- Activation quantisation
- All-reduce
- Arithmetic intensity
- Asymmetric quantisation
- Autoscaling
- AWQ
- Batch inference
Where you learn it
Zero-point is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.