Quick Review: SmoothQuant: Accurate and Efficient Post-Training Quantization for LLMs| 东毅居士

Quick Review: SmoothQuant: Accurate and Efficient Post-Training Quantization for LLMs

作者：XD / 发表： 2023年12月7日 00:45 / 更新： 2023年12月7日 00:57 / 科研学习 / 阅读量：198

SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

Paper: SmoothQuant on arXiv
Code: SmoothQuant on GitHub
Organization: MIT

Highlight:

Hyper-parameter for Outliers: Implements a novel approach using a specific hyper-parameter to manage outliers effectively during the quantization process.

本文作者：XD 转载请标明出处：http://www.eadst.com/blog/229

本站采用知识共享署名-非商业性使用-相同方式共享 4.0 国际许可协议进行许可。

上一篇
Quick Review: AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

下一篇
Setting Up v2rayNG with Tencent Cloud Silicon Valley Lighthouse

Category

标签云

Image2Text PDF CEIR CV Pandas Hungarian Review Password Tiktoken Pickle 阿里云签证 Crawler BTC uWSGI TensorFlow DeepStream Jetson Quantization transformers JSON Pytorch Augmentation Template VPN SQLite Translation Shortcut Django logger 搞笑域名 SPIE Tracking HuggingFace Clash Input Numpy v2ray LoRA GoogLeNet Distillation Random ModelScope Paper Nginx Dataset Proxy Use UNIX Attention Bipartite EXCEL Knowledge CUDA CAM GGML Quantize Data Ubuntu ONNX Safetensors Paddle Heatmap Ptyhon Video PIP ResNet-50 GIT Diagram Disk Food Pillow Excel Google GPT4 COCO diffusers 腾讯云 OpenAI Website OCR LaTeX Bin Sklearn PyCharm TensorRT FlashAttention Bitcoin QWEN Tensor Michelin Permission OpenCV Land CSV Algorithm TSV AI Streamlit uwsgi Git CTC 报税 scipy Color BeautifulSoup XML InvalidArgumentError Github RGB Qwen Baidu Bert WebCrawler Datetime Plotly GPTQ VGG-16 Python SQL Interview C++ Markdown llama.cpp Base64 Domain NLP HaggingFace LLM YOLO NameSilo XGBoost Statistics LLAMA Cloudreve Plate Web SVR Conda Zip Linux Anaconda tar LeetCode Docker NLTK Windows torchinfo 关于博主 Gemma ChatGPT

站点统计

本站现有博文242篇,共被浏览291508次

本站已经建立1781天!

原 Quick Review: SmoothQuant: Accurate and Efficient Post-Training Quantization for LLMs

作者：XD / 发表： 2023年12月7日 00:45 / 更新： 2023年12月7日 00:57 / 科研学习 / 阅读量：198

SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

Highlight:

Quick Review: SmoothQuant: Accurate and Efficient Post-Training Quantization for LLMs