view article Article Making Knowledge Distillation Cheap Enough to Run at Scale MultiverseComputingCAI • 7 days ago • 30
view article Article Making Knowledge Distillation Cheap Enough to Run at Scale MultiverseComputingCAI • 7 days ago • 30
Efficient Knowledge Distillation for LLMs: Offline Top-K Logits and a Fused Chunked KL Loss Paper • 2608.03796 • Published 14 days ago • 14
Efficient Knowledge Distillation for LLMs: Offline Top-K Logits and a Fused Chunked KL Loss Paper • 2608.03796 • Published 14 days ago • 14