specific method · filed under inference & serving
SSM cache quantization
Reduces the Mamba SSM cache from FP32 to a lower-precision representation.
Also called quantize the Mamba SSM cache.
- sources
- 2
- model
- 1
- lab adopt it
- 1
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 2
Documented in
Evidence
2 spans quoted from the sources, strongest treatment first.
we quantize the Mamba SSM cache from the original FP32 precision to lower precisions
usedpost trainingin Nemotron 3 UltraNVIDIA
we quantize the Mamba SSM cache from the original FP32 precision to lower precisions.
usedinference servingin Nemotron 3 UltraNVIDIA
Filed alongside
Other methods under inference & serving :: inference quantization.
FP8 KV-cache quantizationFP8FP4 KV-cache quantizationNVFP4 quantizationFour-Over-SixMXFP4 weight quantizationPost-training quantizationQuantizationBlock-scaled INT8 quantization with stochastic roundingFP8 E4M3 quantizationGGUFMax-based scalingMSE-based scalingMXFP8 activation quantizationNVFP4 KV-cache quantizationNVFP4 ModelOpt re-quantizationAWQ INT4 weight quantization (W4A16)BF16 inferenceBlock-wise E4M3 FP8 weight quantizationChannel-wise quantizationDynamic activation scalingEmbedding and KV-cache quantizationEmpirical bits-per-element budget selectionFine-grained FP8 quantization