implementation detail · filed under optimization
Stochastic Rounding for Mamba Cache
Stochastic rounding used for the Mamba cache, as indicated by the cache-specific option in the evidence.
Also called mamba-cache-stochastic-rounding.
- 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.
enable-mamba-cache-stochastic-rounding
usedinference servingin Nemotron 3 UltraNVIDIA
Filed alongside
Other methods under optimization :: quantization-aware training.
Quantization-Aware TrainingFP4 QuantizationFP4 Quantization-Aware TrainingMXFP4 Weights with MXFP8 ActivationsStochastic RoundingINT4 Quantization-Aware TrainingMXFP4 Quantization-Aware Post-TrainingNVFP4 TrainingPer-Block Scalar ScalingQ4_0 Quantization FormatQuantize-Dequantize TrainingRandom Hadamard TransformsStochastic Rounding of GradientsStraight-Through Estimator