specific method · filed under model architecture
Fine-grained token selection
Retrieves key-value entries corresponding to the Top-K index scores.
Also called fine-grained token selection mechanism.
- sources
- 2
- model
- 1
- lab adopt it
- 1
- strongest
- core
How sources treat it
One count per evidence span, weakest treatment to strongest.
core 2
Documented in
Evidence
2 spans quoted from the sources, strongest treatment first.
our fine-grained token selection mechanism retrieves only the key-value entries {c_s} corresponding to the top-k index scores.
coremodel architecturein DeepSeek-V3.2DeepSeek
our fine-grained token selection mechanism retrieves only the key-value entries corresponding to the top-k index scores.
coremodel architecturein DeepSeek-V3.2DeepSeek
Filed alongside
Other methods under model architecture :: token mixer :: sparse attention :: sparse attention indexer.
Compressed Sparse Attention 2Hierarchical Sparse IndexerIndexCacheIndexShareLightning IndexerReindex ModeReuse ModeDense Warm-up StageIndex BranchIndexer WarmupReuse QSA index selection across speculative decoding stepsAverage poolingBlock-causal scoringCompressed lightweight indexerCross-stage shared-state management for attention reuseDetached indexer-input optimizationIndex Branch outputIndex Branch value headIndexPoolMQA indexerSingle-head index key