A single fused int4 KV cache kernel on Apple Silicon outperforms fp16 in latency with 3x memory compression and near-zero quality loss on tested models.
ButterflyQuant: Ultra-low- bit LLM quantization through learnable orthogonal butterfly transforms
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
ReSpinQuant achieves state-of-the-art accuracy in W4A4 and W3A3 LLM quantization by using efficient residual subspace rotation approximations that match layer-wise performance while retaining the inference speed of global rotation methods.
citing papers explorer
-
When Quantization Is Free: An int4 KV Cache That Outruns fp16 on Apple Silicon
A single fused int4 KV cache kernel on Apple Silicon outperforms fp16 in latency with 3x memory compression and near-zero quality loss on tested models.
-
ReSpinQuant: Efficient Layer-Wise LLM Quantization via Subspace Residual Rotation Approximation
ReSpinQuant achieves state-of-the-art accuracy in W4A4 and W3A3 LLM quantization by using efficient residual subspace rotation approximations that match layer-wise performance while retaining the inference speed of global rotation methods.