Dense Structural Compression of Transformers via Gauge-Correct Channel Removal
arXiv stat.ML6d4 min read
arXiv:2609.07264v1 Announce Type: cross Abstract: Inference energy per token drives the cost and carbon footprint of deployed transformers. It is dominated by dense matrix products that incur fused multiply-accumulate (FMA) operations and memory traffic. To reduce these computations while retaining dense tensors for high GPU throughput, we develop a methodology from first principles to adapt structural complexity during training to maximize inference utility per unit compute. Channel penalties drive entire tensor slices to zero to enable physical removal while preserving density and the networ
