Model techniques map
Techniquesinference & servinginference quantization

specific method · filed under inference & serving

Empirical bits-per-element budget selection

Selects a quantization budget by evaluating a fixed checkpoint across BPE settings on a curated evaluation suite.

Also called Bits per Element Selection.

source
1
model
1
labs adopt it
0
strongest
evaluated

How sources treat it

One count per evidence span, weakest treatment to strongest.

evaluated 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

We selected the model’s bits-per-element (BPE) budget empirically, by quantizing a fixed intermediate checkpoint at a range of BPE settings and scoring each against a curated suite of evaluations

evaluatedevaluation onlyin Nemotron 3 UltraNVIDIA

Filed alongside

Other methods under inference & serving :: inference quantization.