AI engineering glossary · Inference serving optimisation
What is symmetric quantisation?
Symmetric quantisation: A scheme that maps real values onto integers using only a scale, with zero mapped to integer zero. The range is centred, which simplifies arithmetic and speeds up kernels, but wastes some codes if the data is lopsided.
Symmetric quantisation: an example
For weights between -3 and 3 in INT8, the scale is 3 / 127 and zero stays exactly 0.
Related terms
More Inference serving optimisation terms
- Tail latency
- Target model
- Tensor core
- TensorRT
- TensorRT-LLM
- Time per output token
- Time to first token
- Tokens per second
Where you learn it
Symmetric 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.