implementation detail · filed under inference & serving
Unified paged cache layout for KDA states and MLA KV
Places KDA states and MLA KV in a shared paged block pool with common allocation, reference-counting, and eviction machinery.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- core
How sources treat it
One count per evidence span, weakest treatment to strongest.
core 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
We therefore pack KDA states into the same paged block pool as MLA KV , unifying pages to the same byte size so that both page types share one implementation of allocation, reference counting, and eviction.
coreinference servingin Kimi K3Moonshot AI
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 caching8-bit Mamba cache quantizationAsynchronous 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 cache