ML: Kv cache

Machine-learning ideas tagged Kv cache in the ML taxonomy of the Math2NN corpus.

2 ideas found

Solves: Generalization ML: Kv cache Clear all

✗ Mechanism failed 2026

Support-Scenario Attention Pruning

Turn attention weights into a Boolean support scenario and prune edges using local-surjectivity constraints rather than independently thresholding each row. Preserve at least one compatible continuation for every local window, then favor a strongly connected support graph so pruning removes redundant mixtures while maintaining a globally coherent sparse attention pattern.

Useful6/10

Difficulty5/10

Novelty7/10

Memory Speedup Memory Generalization

Paper: Possibilistic collapse and extremality of simplicial distributions arXiv:2607.02754

Unverified 2026

Global-Shift Randomized Batching

Sample one batching aggressiveness parameter once per serving epoch and use it for all busy periods, instead of independently randomizing every batch. This globally coupled randomness preserves nested batching behavior while preventing a fixed traffic pattern from repeatedly aligning with a deterministic timeout.

Useful5/10

Difficulty3/10

Novelty7/10

Sampling Speedup Stability Generalization

Paper: Online Multi-Level Aggregation with Per-Batch Maximum Delay arXiv:2608.06796