implementation detail · filed under model architecture
Mamba-2 SSM cache
A cache implementation detail for Mamba-2 state-space models, with evidence specifying a cache data type option.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- optional
How sources treat it
One count per evidence span, weakest treatment to strongest.
optional 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
--mamba-ssm-cache-dtype float16
optionalinference servingin Nemotron 3 UltraNVIDIA
Filed alongside
Other methods under model architecture :: token mixer :: linear attention & state space :: Mamba.