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：1924

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

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

站点统计

本站现有博文321篇,共被浏览779326次

本站已经建立2471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：1924

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

Highlight:

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