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：2291

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

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

站点统计

本站现有博文333篇,共被浏览922429次

本站已经建立2628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：2291

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

Highlight:

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