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：1923

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

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

站点统计

本站现有博文321篇,共被浏览779286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：1923

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

Highlight:

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