Zhe jiang

NLI : Non-uniform Linear Interpolation Approximation of Nonlinear Operations for Efficient LLMs Inference

Towards W2A4 LLM Inference: Hybrid SQ-VQ Framework with Adaptive Error Compensation

OSTQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting

GenBen:A Genarative Benchmark for LLM-Aided Design