Search papers, labs, and topics across Lattice.
2
0
4
This paper proposes OmniKVQuant, a training-free framework that enables 2-bit KV caches while substantially preserving performance across seven audio-visual benchmarks and provides a fused Triton decode kernel that unpacks the 2-bit cache during attention, so no dense FP16 cache is ever built.
Motif 3 achieves unprecedented efficiency and performance in language modeling by leveraging a novel Mixture-of-Experts architecture that activates only a fraction of its parameters per token.
