paper-with-me

홈 › Papers

Towards Next-Level Post-Training Quantization of Hyper-Scale Transformers

2024-02-14 · Junhan Kim, Chungman Lee, Eulrang Cho, Kyungphil Park, Ho-young Kim, Joonyoung Kim, Yongkweon Jeon

With the increasing complexity of generative AI models, post-training quantization (PTQ) has emerged as a promising solution for deploying hyper-scale models on edge devices such as mobile and TVs. Existing PTQ schemes, however, consume considerable time and resources, which could be a bottleneck in real situations where frequent model updates and multiple hyperparameter tunings are required. As a cost-effective alternative, learning-free PTQ schemes have been proposed. However, the performance is somewhat limited because they cannot consider the inter-layer dependency within the attention module, which is a significant feature of Transformers. In this paper, we thus propose a novel PTQ algorithm that balances accuracy and efficiency. The key idea of the proposed algorithm called aespa is to perform quantization layer-wise for efficiency while targeting attention-wise reconstruction to consider the cross-layer dependency. Through extensive experiments on various language models and complexity analysis, we demonstrate that aespa is accurate and efficient in quantizing Transformer models.

📄 PDF Abstract BibTeX arXiv:2402.08958

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

Q-Rater: Non-Convex Optimization for Post-Training Uniform Quantization

2021-05-05 · Byeongwook Kim, Dongsoo Lee, Yeonju Ro, Yongkweon Jeon 외

Various post-training uniform quantization methods have usually been studied based on convex optimization. As a result, most previous ones rely on the quantization error minimization and/or quadratic approximations. Such…

Quantization

Training Dynamics Impact Post-Training Quantization Robustness

2025-10-07 · Albert Catalan-Tatjer, Niccolò Ajroldi, Jonas Geiping arxiv

While post-training quantization is widely adopted for efficient deployment of large language models, the mechanisms underlying quantization robustness remain unclear. We conduct a comprehensive analysis of quantization …

RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers

2022-12-16 · ICCV 2023 1 · Zhikai Li, Junrui Xiao, Lianwei Yang, Qingyi Gu

Post-training quantization (PTQ), which only requires a tiny dataset for calibration without end-to-end retraining, is a light and practical model compression technique. Recently, several PTQ schemes for vision transform…

Model CompressionQuantization

Hyper-Compression: Model Compression via Hyperfunction

2024-09-01 · Fenglei Fan, Juntong Fan, Dayang Wang, Jingbo Zhang 외

The rapid growth of large models' size has far outpaced that of computing resources. To bridge this gap, encouraged by the parsimonious relationship between genotype and phenotype in the brain's growth and development, w…

modelModel CompressionQuantization

MesonGS++: Post-training Compression of 3D Gaussian Splatting with Hyperparameter Searching

2026-04-29 · Shuzhao Xie, Junchen Ge, Weixiang Zhang, Jiahang Liu 외 arxiv

3D Gaussian Splatting (3DGS) achieves high-quality novel view synthesis with real-time rendering, but its storage cost remains prohibitive for practical deployment. Existing post-training compression methods still rely o…

Novel View Synthesis