Treating KV Cache as a bottleneck to compress is the standard move for million-token context LLM services. But most work only compresses on a single axis of sequence or channel — compress more, and accuracy drops off a cliff. MosaicKV (2607.00760), posted to arXiv on July 1, pushes this to two dimensions: first identify the truly important positions within each KV vector, cut the cache into segments, apply different compression strategies to each segment, then use idle GPU/CPU to maintain the compressed state, and compute attention directly from the compressed cache. On H800, the results are hard: attention speedup up to 16×, decode latency down 4.8×, throughput up 7.3×, memory down to 1/3, with only 1.76% average accuracy drop on LongBench/RULER. Three points worth noting: the key to 2D compression isn't "compress harder", but acknowledging that the KV interior is inherently unevenly sparse — continuing the "soft threshold" route of STAR-KV and InfoKV; compression management is bound to compute scheduling, meaning no light dependence on the framework, landing most likely through SGLang/vLLM integration; 1.76% accuracy for 4-7× throughput, the marginal benefit of million-context Agents is being realized as "long-tail tasks finally runnable". MosaicKV won't make "infinite context length" a reality overnight, but pushes "long prompt can't run" in the Agent era one more step toward production. With accuracy loss compressed to 1%, throughput quintupled, the service pricing of long-context LLM and local inference capability will have a quiet reshuffle.