WhiteMatter: All-to-All Cross-Layer Connections via KV Source Mixing
WhiteMatter mixes key-value sources across Transformer layers, matching deeper models with a smaller KV cache.
1 stories, newest first · one card per story
WhiteMatter mixes key-value sources across Transformer layers, matching deeper models with a smaller KV cache.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views