238 citations · 694 across the 33 of their papers we have counts for
7 papers · 1 filter
LLM-FP4: 4-Bit Floating-Point Quantized Transformers
Shih-yang Liu, Zechun Liu, Xijie Huang +2
We propose LLM-FP4 for quantizing both weights and activations in large language models (LLMs) down to 4-bit floating-point values, in a post-training manner. Existing post-trainin…
Binary and Ternary Natural Language Generation
Zechun Liu, Barlas Oguz, Aasish Pappu +2
Ternary and binary neural networks enable multiplication-free computation and promise multiple orders of magnitude efficiency gains over full-precision networks if implemented on s…
Efficient and Robust Quantization-aware Training via Adaptive Coreset Selection
Xijie Huang, Zechun Liu, Shih-Yang Liu +1
Quantization-aware training (QAT) is a representative model compression method to reduce redundancy in weights and activations. However, most existing QAT methods require end-to-en…
Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts
Ganesh Jawahar, Haichuan Yang, Yunyang Xiong +10
Weight-sharing supernets are crucial for performance estimation in cutting-edge neural architecture search (NAS) frameworks. Despite their ability to generate diverse subnetworks w…
LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
Zechun Liu, Barlas Oguz, Changsheng Zhao +6
Several post-training quantization methods have been applied to large language models (LLMs), and have been shown to perform well down to 8-bits. We find that these methods break d…
SCALES: Boost Binary Neural Network for Image Super-Resolution with Efficient Scalings
Renjie Wei, Zechun Liu, Yuchen Fan +3
Deep neural networks for image super-resolution (SR) have demonstrated superior performance. However, the large memory and computation consumption hinders their deployment on resou…
Oscillation-free Quantization for Low-bit Vision Transformers
Shih-Yang Liu, Zechun Liu, Kwang-Ting Cheng
Weight oscillation is an undesirable side effect of quantization-aware training, in which quantized weights frequently jump between two quantized levels, resulting in training inst…