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：1805

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

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

站点统计

本站现有博文311篇,共被浏览740053次

本站已经建立2377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：1805

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

Highlight:

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