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：1963

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

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

站点统计

本站现有博文323篇,共被浏览796634次

本站已经建立2494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：1963

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

Highlight:

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