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：1893

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

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

站点统计

本站现有博文321篇,共被浏览767789次

本站已经建立2451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：1893

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

Highlight:

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