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：2088

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

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

站点统计

本站现有博文327篇,共被浏览835370次

本站已经建立2540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：2088

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

Highlight:

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