Model techniques map
Techniquesinference & servinginference quantization

specific method · filed under inference & serving

W4A8 quantization

Uses a W4A8 mixed-precision scheme, with 4-bit weights and 8-bit activations.

Also called W4A8 mixed-precision quantization strategy.

source
1
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

we implemented a sophisticated W4A8 mixed-precision quantization strategy

usedsoftware implementationin GLM-5Z.ai

Filed alongside

Other methods under inference & serving :: inference quantization.