Cheng Zhang

Cheng Zhang, Jianyi Cheng, George A. Constantinides et al.

Post-training quantization of Large Language Models (LLMs) is challenging. In this work, we introduce Low-rank Quantization Error Reduction (LQER), which combines quantization and low-rank approximation to recover the model capability. LQER leverages an activation-induced scale matrix to drive the singular value distribution of quantization error towards a desirable distribution, which enables nearly-lossless W4A8 quantization on various LLMs and downstream tasks without the need for knowledge distillation, grid search, or gradient-base iterative optimization. Unlike existing methods, the computation pattern of LQER eliminates the need for specialized Scatter and Gather processes to collect high-precision weights from irregular memory locations. Our W4A8 LLMs achieve near-lossless performance on six popular downstream tasks, while using 1.36$\times$ fewer hardware resources than the leading state-of-the-art method. We open-source our framework at https://github.com/ChengZhang-98/lqer

Tian Zhan, Chunfeng Xu, Cheng Zhang et al.

The Perspective-n-Point (PnP) problem has been widely studied in the literature and applied in various vision-based pose estimation scenarios. However, existing methods ignore the anisotropy uncertainty of observations, as demonstrated in several real-world datasets in this paper. This oversight may lead to suboptimal and inaccurate estimation, particularly in the presence of noisy observations. To this end, we propose a generalized maximum likelihood PnP solver, named GMLPnP, that minimizes the determinant criterion by iterating the GLS procedure to estimate the pose and uncertainty simultaneously. Further, the proposed method is decoupled from the camera model. Results of synthetic and real experiments show that our method achieves better accuracy in common pose estimation scenarios, GMLPnP improves rotation/translation accuracy by 4.7%/2.0% on TUM-RGBD and 18.6%/18.4% on KITTI-360 dataset compared to the best baseline. It is more accurate under very noisy observations in a vision-based UAV localization task, outperforming the best baseline by 34.4% in translation estimation accuracy.

Jeffrey T. H. Wong, Cheng Zhang, Xinye Cao et al.

Large language models have demonstrated remarkable performance; however, their massive parameter counts make deployment highly expensive. Low-rank approximation offers a promising compression solution, yet existing approaches have two main limitations: (1) They focus on minimizing the output error of individual linear layers, without considering the architectural characteristics of Transformers, and (2) they decompose a large weight matrix into two small low-rank matrices. Consequently, these methods often fall short compared to other compression techniques like pruning and quantization, and introduce runtime overhead such as the extra GEMM kernel launches for decomposed small matrices. To address these limitations, we propose $\tt A^\tt 3$, a post-training low-rank approximation framework. $\tt A^\tt 3$ splits a Transformer layer into three functional components, namely $\tt QK$, $\tt OV$, and $\tt MLP$. For each component, $\tt A^\tt 3$ provides an analytical solution that reduces the hidden dimension size inside each component while minimizing the component's functional loss ($\it i.e.$, error in attention scores, attention outputs, and MLP outputs). This approach directly reduces model sizes, KV cache sizes, and FLOPs without introducing any runtime overheads. In addition, it provides a new narrative in advancing the optimization problem from singular linear layer loss optimization toward improved end-to-end performance. Through extensive experiments, we show that $\tt A^\tt 3$ maintains superior performance compared to SoTAs. For example, under the same reduction budget in computation and memory, our low-rank approximated LLaMA 3.1-70B achieves a perplexity of 4.69 on WikiText-2, outperforming the previous SoTA's 7.87 by 3.18. We also demonstrate the versatility of $\tt A^\tt 3$, including KV cache compression, quantization, and mixed-rank assignments for enhanced performance.