Picture for Daning Cheng

Daning Cheng

A General Error-Theoretical Analysis Framework for Constructing Compression Strategies

Add code
Feb 19, 2025
Viaarxiv icon

FP=xINT:A Low-Bit Series Expansion Algorithm for Post-Training Quantization

Add code
Dec 09, 2024
Viaarxiv icon

Compression for Better: A General and Stable Lossless Compression Framework

Add code
Dec 09, 2024
Viaarxiv icon

Lossless Model Compression via Joint Low-Rank Factorization Optimization

Add code
Dec 09, 2024
Viaarxiv icon

Mixed-Precision Inference Quantization: Radically Towards Faster inference speed, Lower Storage requirement, and Lower Loss

Add code
Jul 20, 2022
Figure 1 for Mixed-Precision Inference Quantization: Radically Towards Faster inference speed, Lower Storage requirement, and Lower Loss
Figure 2 for Mixed-Precision Inference Quantization: Radically Towards Faster inference speed, Lower Storage requirement, and Lower Loss
Figure 3 for Mixed-Precision Inference Quantization: Radically Towards Faster inference speed, Lower Storage requirement, and Lower Loss
Figure 4 for Mixed-Precision Inference Quantization: Radically Towards Faster inference speed, Lower Storage requirement, and Lower Loss
Viaarxiv icon

Quantization in Layer's Input is Matter

Add code
Feb 10, 2022
Viaarxiv icon