2 papers
cs.CV2025
JAQ: Joint Efficient Architecture Design and Low-Bit Quantization with Hardware-Software Co-Exploration
Mingzi Wang, Yuan Meng, Chen Tang +9
The co-design of neural network architectures, quantization precisions, and hardware accelerators offers a promising approach to achieving an optimal balance between performance an…
cs.LG2024
MixPE: Quantization and Hardware Co-design for Efficient LLM Inference
Yu Zhang, Mingzi Wang, Lancheng Zou +4
Transformer-based large language models (LLMs) have achieved remarkable success as model sizes continue to grow, yet their deployment remains challenging due to significant computa…