2 papers
cs.LG2026
XOR-Trellis: Ultra-Low-Complexity Dequantization and Curvature-Aware Hadamard-Free LLM Quantization
Xiaofan Que, Nir Elkayam, Spandan Pyakurel +2
Trellis-coded quantization enables high-dimensional compression of large language model (LLM) weights at ultra-low bit widths without the exponentially large codebooks required by…
cs.CV2024
Data-Free Group-Wise Fully Quantized Winograd Convolution via Learnable Scales
Shuokai Pan, Gerti Tuzi, Sudarshan Sreeram +1
Despite the revolutionary breakthroughs of large-scale text-to-image diffusion models for complex vision and downstream tasks, their extremely high computational and storage costs…