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：1867

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

mmap Transformers FP64 多进程音频 ChatGPT Safetensors WAN git-lfs Shortcut Datetime Website UI 强化学习 FlashAttention DeepSeek COCO 顶会 SQLite Claude BF16 Jupyter Excel Disk git tqdm Base64 Data Domain 递归学习法 Markdown Hilton 域名 LeetCode torchinfo printf Pandas 搞笑 Git News diffusers Pytorch Permission Paddle PIP Quantization 净利润 Paper Translation ONNX hf Miniforge Pillow Gemma 多线程 VGG-16 VSCode Vim Zip Breakpoint CEIR Windows Firewall GPTQ Tensor FP32 Qwen2.5 Qwen 算法题版权 LLM Jetson logger transformers FP8 Bert TensorRT Streamlit Algorithm Nginx Cloudreve Conda Docker Hotel Proxy 报税 OpenCV Ptyhon Magnet FastAPI v2ray tar Random CLAP LoRA CAM Tiktoken CUDA InvalidArgumentError Food Augmentation SAM 证件照阿里云 JSON Github Llama GoogLeNet Ubuntu XML TSV Django Quantize Math HuggingFace 关于博主 Linux NLP Color 第一性原理 OpenAI uwsgi PyTorch scipy Crawler BTC Review QWEN Card Google Python Sklearn SQL Clash Land PyCharm DeepStream NLTK Anaconda 继承 Qwen2 公式 Baidu Freesound Use AI Statistics Mixtral Heatmap Agent Video SPIE LaTeX MD5 PDF TensorFlow Template CC Knowledge HaggingFace Tracking Search TTS GIT XGBoost RAR VPN Input 飞书财报 Web UNIX 签证 Bipartite uWSGI Plotly Diagram v0.dev PDB Plate CSV WebCrawler 图形思考法 FP16 YOLO Michelin Bitcoin C++ Distillation Interview llama.cpp Hungarian API Animate Bin Numpy Vmess BeautifulSoup Logo NameSilo Image2Text 腾讯云 CTC Pickle CV ModelScope ResNet-50 EXCEL IndexTTS2 GGML Password GPT4 OCR SVR Attention RGB Dataset LLAMA

站点统计

本站现有博文320篇,共被浏览759200次

本站已经建立2427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：1867

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

Highlight:

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