Search papers, labs, and topics across Lattice.
. Seoul National University , Republic of Korea
5
0
5
3
HeteroFold unlocks $10.7\times$ faster cross-family KV cache transfer for LLMs, eliminating receiver prefill and matching text-based communication performance.
Recovering 87% of accuracy lost to KV eviction could redefine efficiency in reasoning tasks for large language models.
The secret to effectively pruning LLMs might not be *how* you search for redundant layers, but *what* you're optimizing for.
Diffusion language models can achieve up to 26x inference speedups with almost no accuracy loss, thanks to a clever entropy-based KV caching strategy that avoids costly full forward passes.
