view article Article Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original MultiverseComputingCAI • 10 days ago • 45
Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs Paper • 2608.20953 • Published 15 days ago • 11
Efficient Knowledge Distillation for LLMs: Offline Top-K Logits and a Fused Chunked KL Loss Paper • 2608.03796 • Published Aug 4 • 17
Efficient Knowledge Distillation for LLMs: Offline Top-K Logits and a Fused Chunked KL Loss Paper • 2608.03796 • Published Aug 4 • 17
view article Article Making Knowledge Distillation Cheap Enough to Run at Scale MultiverseComputingCAI • 25 days ago • 40