implementation detail · filed under inference & serving
8-bit Mamba cache quantization
Quantizes Mamba cache values using 8-bit formats.
- 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 also explore 8-bit Mamba cache quantization formats. We evaluated this on Nemotron 3 Super.
evaluatedinference servingin Nemotron 3 SuperNVIDIA
Filed alongside
Other methods under inference & serving :: KV cache management.
Chunked prefillPrefix cachingPrompt cachingSWA Bounded ReplayLanguage-model-only serving modePeriodic cache checkpointingCompressed KV cachingKDA-aware prefix-cache managementRadixCacheZero SWA cachingAsynchronous cache offloading and restorationAutomatic cacheBlock-based KV cacheCross-layer KV-cache reuseCustomized heterogeneous KV-cache layoutDisable prefix caching for benchmarkingDynamic allocation of fixed-size state-cache poolsEncoder SWA bounded replayExact SWA KV reconstruction via full multi-layer replayFine-grained prefix hashingHierarchical KV cachingInference-side KV-cache reset on weight synchronizationKDA with prefill cacheKey-value reuse in global attention layers