AI engineering glossary · Inference serving optimisation
What is asymmetric quantisation?
Asymmetric quantisation: A scheme that uses both a scale and a zero-point, so the integer range can be shifted to fit data that is not centred on zero. It represents skewed ranges more precisely, at the cost of extra computation to handle the offset.
Asymmetric quantisation: an example
ReLU outputs lie in 0 to 6, so an asymmetric 8-bit mapping uses all 256 codes for that range.
Related terms
More Inference serving optimisation terms
- Autoscaling
- AWQ
- Batch inference
- Block table
- Cache-aware routing
- Calibration dataset
- Chunked prefill
- Cold start
Where you learn it
Asymmetric quantisation is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.