paper-with-me

Papers

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

2022-07-20 · Daning Cheng, WenGuang Chen

Based on the model's resilience to computational noise, model quantization is important for compressing models and improving computing speed. Existing quantization techniques rely heavily on experience and "fine-tuning" skills. In the majority of instances, the quantization model has a larger loss than a full precision model. This study provides a methodology for acquiring a mixed-precise quantization model with a lower loss than the full precision model. In addition, the analysis demonstrates that, throughout the inference process, the loss function is mostly affected by the noise of the layer inputs. In particular, we will demonstrate that neural networks with massive identity mappings are resistant to the quantization method. It is also difficult to improve the performance of these networks using quantization.

📄 PDF Abstract BibTeX arXiv:2207.10083

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Similar Papers 제목 키워드 기반

SAMP: A Model Inference Toolkit of Post-Training Quantization for Text Processing via Self-Adaptive Mixed-Precision

2022-09-19 · Rong Tian, Zijing Zhao, Weijie Liu, Haoyan Liu 외

The latest industrial inference engines, such as FasterTransformer and TurboTransformers, have verified that half-precision floating point (FP16) and 8-bit integer (INT8) quantization can greatly improve model inference …

Quantization

Patch-wise Mixed-Precision Quantization of Vision Transformer

2023-05-11 · Junrui Xiao, Zhikai Li, Lianwei Yang, Qingyi Gu

As emerging hardware begins to support mixed bit-width arithmetic computation, mixed-precision quantization is widely used to reduce the complexity of neural networks. However, Vision Transformers (ViTs) require complex …

QuantizationSensitivity

Efficient and Effective Methods for Mixed Precision Neural Network Quantization for Faster, Energy-efficient Inference

2023-01-30 · Deepika Bablani, Jeffrey L. McKinstry, Steven K. Esser, Rathinakumar Appuswamy 외

For efficient neural network inference, it is desirable to achieve state-of-the-art accuracy with the simplest networks requiring the least computation, memory, and power. Quantizing networks to lower precision is a powe…

Efficient Neural NetworkQuantization

Cocktail: Chunk-Adaptive Mixed-Precision Quantization for Long-Context LLM Inference

2025-03-30 · Wei Tao, Bin Zhang, Xiaoyang Qu, Jiguang Wan 외

Recently, large language models (LLMs) have been able to handle longer and longer contexts. However, a context that is too long may cause intolerant inference latency and GPU memory usage. Existing methods propose mixed-…

GPUQuantization

WindowQuant: Mixed-Precision KV Cache Quantization based on Window-Level Similarity for VLMs Inference Optimization

2026-05-04 · Wei Tao, Xiaoyang Qu, Peiqiang Wang, Guokuan Li 외 arxiv

Recently, video language models (VLMs) have been applied in various fields. However, the visual token sequence of the VLM is too long, which may cause intolerant inference latency and GPU memory usage. Existing methods p…