Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs Paper • 2608.20953 • Published Aug 21 • 14
Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs Paper • 2608.20953 • Published Aug 21 • 14
Efficient Knowledge Distillation for LLMs: Offline Top-K Logits and a Fused Chunked KL Loss Paper • 2608.03796 • Published Aug 4 • 20
Efficient Knowledge Distillation for LLMs: Offline Top-K Logits and a Fused Chunked KL Loss Paper • 2608.03796 • Published Aug 4 • 20