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：1958

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

站点统计

本站现有博文323篇,共被浏览795324次

本站已经建立2493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：1958

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

Highlight:

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